From c3ba206b8157b73a0672136cc57a0d927f32aae6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 10:01:10 +0200
Subject: [PATCH 01/24] set version of complexitymeasures

---
 docs/Project.toml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/docs/Project.toml b/docs/Project.toml
index c3872cdf..614195e8 100644
--- a/docs/Project.toml
+++ b/docs/Project.toml
@@ -25,5 +25,6 @@ Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 TimeseriesSurrogates = "c804724b-8c18-5caa-8579-6025a0767c70"
 
 [compat]
+ComplexityMeasures = "^3.8"
 DynamicalSystemsBase = "3"
 julia = "^1.10.6"

From cfeed538dfe0dce4723f2cf783db2bb249eb9532 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 10:01:28 +0200
Subject: [PATCH 02/24] use @extref

---
 docs/src/api/counts_and_probabilities_api.md  |   2 +-
 .../api/discretization_counts_probs_api.md    |   8 +-
 docs/src/api/information_multivariate_api.md  |   8 +-
 .../api/information_single_variable_api.md    |  44 +------
 docs/src/examples/examples_associations.md    | 116 +++++++++---------
 docs/src/examples/examples_independence.md    |   4 +-
 src/independence_tests/secmi/secmi_test.jl    |  26 ++--
 src/methods/information/core.jl               |  14 +--
 .../information/counts_and_probs/counts.jl    |  26 ++--
 .../encoding/codify_variables.jl              |  24 ++--
 .../counts_and_probs/probabilities.jl         |  24 ++--
 .../ConditionalEntropyShannon.jl              |   8 +-
 .../ConditionalEntropyTsallisAbe.jl           |  12 +-
 .../ConditionalEntropyTsallisFuruichi.jl      |  10 +-
 .../CMIRenyiJizba.jl                          |  34 ++---
 .../CMIShannon.jl                             |  44 +++----
 .../HellingerDistance.jl                      |   4 +-
 .../divergences_and_distances/KLDivergence.jl |   4 +-
 .../RenyiDivergence.jl                        |  10 +-
 .../VariationDistance.jl                      |   4 +-
 .../joint_entropies/JointEntropyRenyi.jl      |  10 +-
 .../joint_entropies/JointEntropyShannon.jl    |   6 +-
 .../joint_entropies/JointEntropyTsallis.jl    |   8 +-
 .../mutual_informations/MIRenyiJizba.jl       |  36 +++---
 .../mutual_informations/MIRenyiSarbu.jl       |  12 +-
 .../mutual_informations/MIShannon.jl          |  54 ++++----
 .../mutual_informations/MITsallisFuruichi.jl  |  26 ++--
 .../mutual_informations/MITsallisMartin.jl    |  24 ++--
 ...xpansion_conditional_mutual_information.jl |  12 +-
 .../transferentropy/TERenyiJizba.jl           |  36 +++---
 .../definitions/transferentropy/TEShannon.jl  |  36 +++---
 .../estimators/JointProbabilities.jl          |   8 +-
 .../estimators/codify_marginals.jl            |  18 +--
 .../FPVP.jl                                   |   6 +-
 .../Rahimzamani.jl                            |   8 +-
 .../decomposition/EntropyDecomposition.jl     |  66 +++++-----
 .../decomposition/MIDecomposition.jl          |   4 +-
 .../GaoKannanOhViswanath.jl                   |  12 +-
 .../transfer_entropy_estimators/Hilbert.jl    |  10 +-
 .../SymbolicTransferEntropy.jl                |  14 +--
 40 files changed, 395 insertions(+), 437 deletions(-)

diff --git a/docs/src/api/counts_and_probabilities_api.md b/docs/src/api/counts_and_probabilities_api.md
index 794e0cdf..042b20ac 100644
--- a/docs/src/api/counts_and_probabilities_api.md
+++ b/docs/src/api/counts_and_probabilities_api.md
@@ -27,7 +27,7 @@ marginal
 ## [Example: estimating [`Counts`](@ref) and [`Probabilities`](@ref)](@id tutorial_probabilities)
 
 Estimating multivariate counts (contingency matrices) and PMFs is simple. If the data are pre-discretized, then
-we can use [`UniqueElements`](@ref) to simply count the number of occurrences.
+we can use [`UniqueElements`](@extref ComplexityMeasures) to simply count the number of occurrences.
 
 ```@example counts_probs_tutorial
 using Associations
diff --git a/docs/src/api/discretization_counts_probs_api.md b/docs/src/api/discretization_counts_probs_api.md
index d74770b5..8fe28698 100644
--- a/docs/src/api/discretization_counts_probs_api.md
+++ b/docs/src/api/discretization_counts_probs_api.md
@@ -125,7 +125,7 @@ FixedRectangularBinning
 #### Example: encoding *columns* (one variable at a time)
 
 Some [`OutcomeSpace`](@ref)s dictate a sliding window which has the width of one element
-when used with [`CodifyVariables`](@ref). [`ValueBinning`](@ref) is such an outcome space.
+when used with [`CodifyVariables`](@ref). [`ValueBinning`](@extref ComplexityMeasures) is such an outcome space.
 
 ```@example example_encode_vars
 using Associations
@@ -136,17 +136,17 @@ o = ValueBinning(3)
 cx = codify(CodifyVariables(o), x)
 ```
 
-We can verify that [`ValueBinning`](@ref) preserves the cardinality of the input dataset.
+We can verify that [`ValueBinning`](@extref ComplexityMeasures) preserves the cardinality of the input dataset.
 
 ```@example example_encode_vars
 length(x) == length(cx)
 ```
 
-Other outcome spaces such as [`Dispersion`](@ref) or [`OrdinalPatterns`](@ref) do not 
+Other outcome spaces such as [`Dispersion`](@extref ComplexityMeasures) or [`OrdinalPatterns`](@extref ComplexityMeasures) do not 
 preserve the cardinality of the input dataset when used with [`CodifyVariables`](@ref). This is 
 because when they are applied in a sliding window, they compress sliding windows consisting of 
 potentially multiple points into single integers. This means that some points at the 
-end of each input variable are lost. For example, with [`OrdinalPatterns`](@ref), the number 
+end of each input variable are lost. For example, with [`OrdinalPatterns`](@extref ComplexityMeasures), the number 
 of encoded points decrease with the embedding parameter `m`.
 
 ```@example example_encode_vars
diff --git a/docs/src/api/information_multivariate_api.md b/docs/src/api/information_multivariate_api.md
index 1d79b318..5674b650 100644
--- a/docs/src/api/information_multivariate_api.md
+++ b/docs/src/api/information_multivariate_api.md
@@ -110,7 +110,7 @@ find those that we implement [here](@ref divergences_and_distances).
 
 As an example, let's quantify the [`KLDivergence`](@ref) between two probability 
 mass functions estimated by symbolizing two input vectors `x` and `y` using 
-[`OrdinalPatterns`](@ref). Since the discrete [`KLDivergence`](@ref) can be 
+[`OrdinalPatterns`](@extref ComplexityMeasures). Since the discrete [`KLDivergence`](@ref) can be 
 expressed as a function of a joint pmf, we can use the [`JointProbabilities`](@ref)
 estimator.
 
@@ -157,7 +157,7 @@ association(est, x, y)
 
 [Joint entropies](@ref joint_entropies), on the other hand, are *symmetric*. Joint
 entropies are functionals of a joint pmf, so we can still use the
-[`JointProbabilities`](@ref) estimator. This time, we use a [`Dispersion`](@ref)
+[`JointProbabilities`](@ref) estimator. This time, we use a [`Dispersion`](@extref ComplexityMeasures)
 based discretization.
 
 ```@example INFO_TUTORIAL
@@ -176,7 +176,7 @@ Mutual informations, in particular [`MIShannon`](@ref) is an often-used symmetri
 measure for quantifing the (possibly nonlinear) association between variables. It appears
 in both  discrete and differential form, and can be estimated in a multitude of ways. For 
 example, one can use dedicated [`MutualInformationEstimator`](@ref)s such as 
-[`KraskovStögbauerGrassberger2`](@ref) or [`GaussianMI`](@ref):
+[`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) or [`GaussianMI`](@ref):
 
 ```@example INFO_TUTORIAL
 using Associations
@@ -196,7 +196,7 @@ association(est, x, y) ≈ association(est, y, x) # should be true
 
 One can also estimate mutual information using the [`EntropyDecomposition`](@ref) 
 estimator, or (like above) using the [`JointProbabilities`](@ref) estimator.
-Let's construct a differential entropy based estimator based on the [`Kraskov`](@ref)
+Let's construct a differential entropy based estimator based on the [`Kraskov`](@extref ComplexityMeasures)
 estimator.
 
 ```@example INFO_TUTORIAL
diff --git a/docs/src/api/information_single_variable_api.md b/docs/src/api/information_single_variable_api.md
index 35ce51be..6f987d01 100644
--- a/docs/src/api/information_single_variable_api.md
+++ b/docs/src/api/information_single_variable_api.md
@@ -8,46 +8,4 @@ Below we list some relevant functions types from
 [ComplexityMeasures.jl](https://github.com/JuliaDynamics/ComplexityMeasures.jl) that 
 are used for the [`EntropyDecomposition`](@ref) estimator.
 
-```@docs
-information
-```
-
-## Single-variable information measures
-
-```@docs
-Shannon
-Renyi
-Tsallis
-Kaniadakis
-```
-
-## Discrete information estimators
-
-```@docs
-DiscreteInfoEstimator
-PlugIn
-MillerMadow
-Schuermann
-GeneralizedSchuermann
-Jackknife
-HorvitzThompson
-ChaoShen
-```
-
-## Differential information estimators
-
-```@docs
-DifferentialInfoEstimator
-Kraskov
-KozachenkoLeonenko
-Zhu
-ZhuSingh
-Gao
-Goria
-Lord
-LeonenkoProzantoSavani
-Vasicek
-AlizadehArghami
-Ebrahimi
-Correa
-```
\ No newline at end of file
+- [`information`](@extref ComplexityMeasures)
diff --git a/docs/src/examples/examples_associations.md b/docs/src/examples/examples_associations.md
index 887ecc91..d1c1fb7f 100644
--- a/docs/src/examples/examples_associations.md
+++ b/docs/src/examples/examples_associations.md
@@ -12,7 +12,7 @@ p2 = Probabilities([0.3, 0.3, 0.2, 0.2])
 association(HellingerDistance(), p1, p2)
 ```
 
-### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@ref)](@id example_HellingerDistance_JointProbabilities_OrdinalPatterns)
+### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_HellingerDistance_JointProbabilities_OrdinalPatterns)
 
 We expect the Hellinger distance between two uncorrelated variables to be close to zero.
 
@@ -37,7 +37,7 @@ p2 = Probabilities([0.3, 0.3, 0.2, 0.2])
 association(KLDivergence(), p1, p2)
 ```
 
-### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@ref)](@id example_KLDivergence_JointProbabilities_OrdinalPatterns)
+### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_KLDivergence_JointProbabilities_OrdinalPatterns)
 
 We expect the [`KLDivergence`](@ref) between two uncorrelated variables to be close to zero.
 
@@ -63,7 +63,7 @@ p2 = Probabilities([0.3, 0.3, 0.2, 0.2])
 association(RenyiDivergence(), p1, p2)
 ```
 
-### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@ref)](@id example_RenyiDivergence_JointProbabilities_OrdinalPatterns)
+### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_RenyiDivergence_JointProbabilities_OrdinalPatterns)
 
 We expect the [`RenyiDivergence`](@ref) between two uncorrelated variables to be close to zero.
 
@@ -89,7 +89,7 @@ p2 = Probabilities([0.3, 0.3, 0.2, 0.2])
 association(VariationDistance(), p1, p2)
 ```
 
-### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@ref)](@id example_VariationDistance_JointProbabilities_OrdinalPatterns)
+### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_VariationDistance_JointProbabilities_OrdinalPatterns)
 
 We expect the [`VariationDistance`](@ref) between two uncorrelated variables to be close to zero.
 
@@ -104,7 +104,7 @@ div_hd = association(est, x, y) # pretty close to zero
 
 ## [`JointEntropyShannon`](@ref)
 
-### [[`JointProbabilities`](@ref) with [`Dispersion`](@ref)](@id example_JointEntropyShannon_Dispersion)
+### [[`JointProbabilities`](@ref) with [`Dispersion`](@extref ComplexityMeasures)](@id example_JointEntropyShannon_Dispersion)
 
 ```@example example_JointEntropyShannon
 using Associations
@@ -118,7 +118,7 @@ association(est, x, y)
 
 ## [`JointEntropyTsallis`](@ref)
 
-### [[`JointProbabilities`](@ref) with [`OrdinalPatterns`](@ref)](@id example_JointEntropyTsallis_OrdinalPatterns)
+### [[`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_JointEntropyTsallis_OrdinalPatterns)
 
 ```@example example_JointEntropyTsallis
 using Associations
@@ -133,7 +133,7 @@ association(est, x, y)
 
 ## [`JointEntropyRenyi`](@ref)
 
-### [[`JointProbabilities`](@ref) with [`OrdinalPatterns`](@ref)](@id example_JointEntropyRenyi_ValueBinning)
+### [[`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_JointEntropyRenyi_ValueBinning)
 
 ```@example example_JointEntropyRenyi
 using Associations
@@ -190,7 +190,7 @@ pyx = Probabilities(transpose(freqs_yx))
 ce_y_given_x = association(ConditionalEntropyShannon(), pyx) |> Rational
 ```
 
-### [[`JointProbabilities`](@ref) + [`CodifyVariables`](@ref) + [`UniqueElements`](@ref)](@id example_ConditionalEntropyShannon_JointProbabilities_CodifyVariables_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`CodifyVariables`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_ConditionalEntropyShannon_JointProbabilities_CodifyVariables_UniqueElements)
 
 We can of course also estimate conditional entropy from data. To do so, we'll use the 
 [`JointProbabilities`](@ref) estimator, which constructs a multivariate PMF for us.
@@ -198,7 +198,7 @@ Thus, we don't explicitly need a set of counts, like in the example above, becau
 are estimated under the hood for us. 
 
 Let's first demonstrate on some categorical data. For that, we must use
-[`UniqueElements`](@ref) as the discretization (i.e. just count unique elements).
+[`UniqueElements`](@extref ComplexityMeasures) as the discretization (i.e. just count unique elements).
 
 ```@example example_ConditionalEntropyShannon_JointProbabilities_CodifyVariables_UniqueElements
 using Associations
@@ -227,7 +227,7 @@ association(est, X, Y)
 
 ## [`ConditionalEntropyTsallisAbe`](@ref)
 
-### [[`JointProbabilities`](@ref) + [`CodifyVariables`](@ref) + [`UniqueElements`](@ref)](@id example_ConditionalEntropyTsallisAbe_JointProbabilities_CodifyVariables_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`CodifyVariables`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_ConditionalEntropyTsallisAbe_JointProbabilities_CodifyVariables_UniqueElements)
 
 We'll here repeat the analysis we did for [`ConditionalEntropyShannon`](@ref) above.
 
@@ -259,7 +259,7 @@ association(est, X, Y)
 
 ## [`ConditionalEntropyTsallisFuruichi`](@ref)
 
-### [[`JointProbabilities`](@ref) + [`CodifyVariables`](@ref) + [`UniqueElements`](@ref)](@id example_ConditionalEntropyTsallisFuruichi_JointProbabilities_CodifyVariables_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`CodifyVariables`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_ConditionalEntropyTsallisFuruichi_JointProbabilities_CodifyVariables_UniqueElements)
 
 We'll here repeat the analysis we did for [`ConditionalEntropyShannon`](@ref) and [`ConditionalEntropyTsallisAbe`](@ref) above.
 
@@ -291,7 +291,7 @@ association(est, X, Y)
 
 ## [`MIShannon`](@ref)
 
-### [[`JointProbabilities`](@ref) + [`ValueBinning`](@ref)](@id example_MIShannon_JointProbabilities_ValueBinning)
+### [[`JointProbabilities`](@ref) + [`ValueBinning`](@extref ComplexityMeasures)](@id example_MIShannon_JointProbabilities_ValueBinning)
 
 ```@example mi_demonstration
 using Associations
@@ -304,7 +304,7 @@ association(est, x, y)
 ```
 
 
-### [[`JointProbabilities`](@ref) + [`UniqueElements`](@ref)](@id example_MIShannon_JointProbabilities_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_MIShannon_JointProbabilities_UniqueElements)
 
 The [`JointProbabilities`](@ref) estimator can also be used with categorical data.
 For example, let's compare the Shannon mutual information between the preferences
@@ -343,7 +343,7 @@ y = rand(1000) .+ x
 association(GaussianMI(MIShannon()), x, y) # defaults to `MIShannon()`
 ```
 
-### [Dedicated [`KraskovStögbauerGrassberger1`](@ref) estimator](@id example_MIShannon_KSG1)
+### [Dedicated [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator](@id example_MIShannon_KSG1)
 
 ```@example mi_demonstration
 using Associations
@@ -351,7 +351,7 @@ x, y = rand(1000), rand(1000)
 association(KSG1(MIShannon(); k = 5), x, y)
 ```
 
-### [Dedicated [`KraskovStögbauerGrassberger2`](@ref) estimator](@id example_MIShannon_KSG2)
+### [Dedicated [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator](@id example_MIShannon_KSG2)
 
 ```@example mi_demonstration
 using Associations
@@ -359,7 +359,7 @@ x, y = rand(1000), rand(1000)
 association(KSG2(MIShannon(); k = 5), x, y)
 ```
 
-### [Dedicated [`GaoKannanOhViswanath`](@ref) estimator](@id example_MIShannon_GaoKannanOhViswanath)
+### [Dedicated [`GaoKannanOhViswanath`](@extref ComplexityMeasures) estimator](@id example_MIShannon_GaoKannanOhViswanath)
 
 ```@example mi_demonstration
 using Associations
@@ -367,9 +367,9 @@ x, y = rand(1000), rand(1000)
 association(GaoKannanOhViswanath(MIShannon(); k = 10), x, y)
 ```
 
-### [[`EntropyDecomposition`](@ref) + [`Kraskov`](@ref)](@id example_MIShannon_EntropyDecomposition_Kraskov)
+### [[`EntropyDecomposition`](@ref) + [`Kraskov`](@extref ComplexityMeasures)](@id example_MIShannon_EntropyDecomposition_Kraskov)
 
-We can compute [`MIShannon`](@ref) by naively applying a [`DifferentialInfoEstimator`](@ref).
+We can compute [`MIShannon`](@ref) by naively applying a [`DifferentialInfoEstimator`](@extref ComplexityMeasures).
 Note that this doesn't apply any bias correction.
 
 ```@example mi_demonstration
@@ -381,7 +381,7 @@ association(EntropyDecomposition(MIShannon(), Kraskov(k = 3)), x, y)
 
 ### [[`EntropyDecomposition`](@ref) + [`BubbleSortSwaps`](@ref)](@id example_MIShannon_EntropyDecomposition_BubbleSortSwaps)
 
-We can also compute [`MIShannon`](@ref) by naively applying a [`DiscreteInfoEstimator`](@ref).
+We can also compute [`MIShannon`](@ref) by naively applying a [`DiscreteInfoEstimator`](@extref ComplexityMeasures).
 Note that this doesn't apply any bias correction.
 
 ```@example mi_demonstration
@@ -393,10 +393,10 @@ association(EntropyDecomposition(MIShannon(), hest, disc), x, y)
 ```
 
 
-### [[`EntropyDecomposition`](@ref) + [`Jackknife`](@ref) + [`ValueBinning`](@ref)](@id example_MIShannon_EntropyDecomposition_Jackknife_ValueBinning)
+### [[`EntropyDecomposition`](@ref) + [`Jackknife`](@extref ComplexityMeasures) + [`ValueBinning`](@extref ComplexityMeasures)](@id example_MIShannon_EntropyDecomposition_Jackknife_ValueBinning)
 
 Shannon mutual information can be written as a sum of marginal entropy terms.
-Here, we use [`CodifyVariables`](@ref) with [`ValueBinning`](@ref) bin the data 
+Here, we use [`CodifyVariables`](@ref) with [`ValueBinning`](@extref ComplexityMeasures) bin the data 
 and compute discrete Shannon mutual information.
 
 ```@example mi_demonstration
@@ -421,7 +421,7 @@ Here, we'll reproduce Figure 4 from [Kraskov2004](@citet)'s seminal paper on the
 between marginals of a bivariate Gaussian for a fixed time series length of 1000,
 varying the number of neighbors. *Note: in the original paper, they show multiple
 curves corresponding to different time series length. We only show two single curves:
-one for the [`KraskovStögbauerGrassberger1`](@ref) estimator and one for the [`KraskovStögbauerGrassberger2`](@ref) estimator*.
+one for the [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator and one for the [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator*.
 
 ```@example ex_mutualinfo
 using Associations
@@ -468,10 +468,10 @@ Most estimators suffer from significant bias when applied to discrete, finite da
 
 But instead of adding noise to your data, you can also consider using an
 estimator that is specifically designed to deal with continuous-discrete mixture data. 
-One example is the [`GaoKannanOhViswanath`](@ref) estimator. Below, we compare its
-performance to [`KraskovStögbauerGrassberger1`](@ref) on uniformly distributed discrete multivariate data.
-The true mutual information is zero. While the "naive" [`KraskovStögbauerGrassberger1`](@ref) estimator 
-diverges from the true value for these data, the [`GaoKannanOhViswanath`](@ref)
+One example is the [`GaoKannanOhViswanath`](@extref ComplexityMeasures) estimator. Below, we compare its
+performance to [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) on uniformly distributed discrete multivariate data.
+The true mutual information is zero. While the "naive" [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator 
+diverges from the true value for these data, the [`GaoKannanOhViswanath`](@extref ComplexityMeasures)
 converges to the true value.
 
 ```@example ex_mutualinfo
@@ -548,7 +548,7 @@ axislegend(position = :rb)
 fig
 ```
 
-### Estimation using [`DifferentialInfoEstimator`](@ref)s: a comparison
+### Estimation using [`DifferentialInfoEstimator`](@extref ComplexityMeasures)s: a comparison
 
 Let's compare the performance of a subset of the implemented mutual information estimators. We'll use example data from Lord et al., where the analytical mutual information is known.
 
@@ -775,15 +775,15 @@ fig = plot_results(family3, ifamily3;
     estimators = estimators, base = base)
 ```
 
-We see that the [`Lord`](@ref) estimator, which estimates local volume elements using a singular-value decomposition (SVD) of local neighborhoods, outperforms the other estimators by a large margin.
+We see that the [`Lord`](@extref ComplexityMeasures) estimator, which estimates local volume elements using a singular-value decomposition (SVD) of local neighborhoods, outperforms the other estimators by a large margin.
 
 
 ## [`MIRenyiJizba`](@ref)
 
-### [[`JointProbabilities`](@ref) + [`UniqueElements`](@ref)](@id example_MIRenyiJizba_JointProbabilities_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_MIRenyiJizba_JointProbabilities_UniqueElements)
 
 [`MIRenyiJizba`](@ref) can be estimated for categorical data using [`JointProbabilities`](@ref) estimator
-with the [`UniqueElements`](@ref) outcome space.
+with the [`UniqueElements`](@extref ComplexityMeasures) outcome space.
 
 ```@example example_mirenyijizba
 using Associations
@@ -794,11 +794,11 @@ est = JointProbabilities(MIRenyiJizba(), UniqueElements())
 association(est, x, y)
 ```
 
-### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@ref)](@id example_MIRenyiJizba_JointProbabilities_LeonenkoProzantoSavani)
+### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures)](@id example_MIRenyiJizba_JointProbabilities_LeonenkoProzantoSavani)
 
 [`MIRenyiJizba`](@ref) can also estimated for numerical data using [`EntropyDecomposition`](@ref)
-in combination with any [`DifferentialInfoEstimator`](@ref) capable of estimating differential 
-[`Renyi`](@ref) entropy.
+in combination with any [`DifferentialInfoEstimator`](@extref ComplexityMeasures) capable of estimating differential 
+[`Renyi`](@extref ComplexityMeasures) entropy.
 
 ```@example example_MIRenyiJizba
 using Associations
@@ -809,11 +809,11 @@ est_diff = EntropyDecomposition(def, LeonenkoProzantoSavani(Renyi(), k=3))
 association(est_diff, x, y) 
 ```
 
-### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@ref)](@id example_MIRenyiJizba_EntropyDecomposition_ValueBinning)
+### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures)](@id example_MIRenyiJizba_EntropyDecomposition_ValueBinning)
 
 [`MIRenyiJizba`](@ref) can also estimated for numerical data using [`EntropyDecomposition`](@ref)
-in combination with any [`DiscreteInfoEstimator`](@ref) capable of estimating differential 
-[`Renyi`](@ref) entropy over some [`OutcomeSpace`](@ref), e.g. [`ValueBinning`](@ref).
+in combination with any [`DiscreteInfoEstimator`](@extref ComplexityMeasures) capable of estimating differential 
+[`Renyi`](@extref ComplexityMeasures) entropy over some [`OutcomeSpace`](@ref), e.g. [`ValueBinning`](@extref ComplexityMeasures).
 
 
 ```@example example_MIRenyiJizba
@@ -832,7 +832,7 @@ association(est_disc, x, y)
 [`MIRenyiSarbu`](@ref) can be estimated using the [`JointProbabilities`](@ref) estimator 
 in combination with any [`CodifyVariables`](@ref) or [`CodifyPoints`](@ref) discretization scheme.
 
-### [[`JointProbabilities`](@ref) + [`UniqueElements`](@ref)](@id example_MIRenyiSarbu_JointProbabilities_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_MIRenyiSarbu_JointProbabilities_UniqueElements)
 
 ```@example example_MIRenyiSarbu
 using Associations
@@ -858,7 +858,7 @@ association(est, x, y)
 
 ## [`MITsallisFuruichi`](@ref)
 
-### [[`JointProbabilities`](@ref) + [`UniqueElements`](@ref)](@id example_MITsallisFuruichi_JointProbabilities_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_MITsallisFuruichi_JointProbabilities_UniqueElements)
 
 [`MITsallisFuruichi`](@ref) can be estimated using the [`JointProbabilities`](@ref) estimator 
 in combination with any [`CodifyVariables`](@ref) or [`CodifyPoints`](@ref) discretization scheme.
@@ -873,7 +873,7 @@ est = JointProbabilities(MITsallisFuruichi(q = 0.3), UniqueElements())
 association(est, x, y) 
 ```
 
-### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@ref)](@id example_MITsallisFuruichi_EntropyDecomposition_LeonenkoProzantoSavani)
+### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures)](@id example_MITsallisFuruichi_EntropyDecomposition_LeonenkoProzantoSavani)
 
 ```@example example_MITsallisFuruichi
 using Associations
@@ -886,7 +886,7 @@ association(est_diff, x, y)
 ```
 
 
-### [[`EntropyDecomposition`](@ref) + [`Dispersion`](@ref)](@id example_MITsallisFuruichi_EntropyDecomposition_Dispersion)
+### [[`EntropyDecomposition`](@ref) + [`Dispersion`](@extref ComplexityMeasures)](@id example_MITsallisFuruichi_EntropyDecomposition_Dispersion)
 
 ```@example example_MITsallisFuruichi
 using Associations
@@ -902,7 +902,7 @@ association(est_disc, x, y)
 
 ## [`MITsallisMartin`](@ref)
 
-### [[`JointProbabilities`](@ref) + [`UniqueElements`](@ref)](@id example_MITsallisMartin_JointProbabilities_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_MITsallisMartin_JointProbabilities_UniqueElements)
 
 ```@example example_MITsallisMartin
 using Associations
@@ -914,11 +914,11 @@ est = JointProbabilities(MITsallisMartin(q = 1.5), UniqueElements())
 association(est, x, y) 
 ```
 
-### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@ref)](@id example_MITsallisMartin_EntropyDecomposition_LeonenkoProzantoSavani)
+### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures)](@id example_MITsallisMartin_EntropyDecomposition_LeonenkoProzantoSavani)
 
 [`MITsallisMartin`](@ref) can be estimated using a decomposition into entropy 
 terms using [`EntropyDecomposition`](@ref) with any compatible estimator 
-that can estimate differential [`Tsallis`](@ref) entropy. 
+that can estimate differential [`Tsallis`](@extref ComplexityMeasures) entropy. 
 
 
 ```@example example_MITsallisMartin
@@ -931,7 +931,7 @@ est_diff = EntropyDecomposition(MITsallisMartin(), LeonenkoProzantoSavani(Tsalli
 association(est_diff, x, y)
 ```
 
-### [[`EntropyDecomposition`](@ref) + [`OrdinalPatterns`](@ref)](@id example_MITsallisMartin_EntropyDecomposition_OrdinalPatterns)
+### [[`EntropyDecomposition`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_MITsallisMartin_EntropyDecomposition_OrdinalPatterns)
 
 
 ```@example 
@@ -1072,7 +1072,7 @@ taking the difference of mutual information terms.
 
 ## [`CMIShannon`](@ref)
 
-### [[`MIDecomposition`](@ref) + [`KraskovStögbauerGrassberger1`](@ref)](@id example_CMIShannon_MIDecomposition_KSG1)
+### [[`MIDecomposition`](@ref) + [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures)](@id example_CMIShannon_MIDecomposition_KSG1)
 
 ```@example mi_demonstration
 using Associations
@@ -1095,7 +1095,7 @@ association(est, x, z, y)
 
 ## [`ShortExpansionConditionalMutualInformation`](@ref)
 
-### [[`JointProbabilities`](@ref) with [`CodifyVariables`](@ref) and [`ValueBinning`](@ref)](@id example_ShortExpansionConditionalMutualInformation_JointProbabilities_CodifyVariables_ValueBinning)
+### [[`JointProbabilities`](@ref) with [`CodifyVariables`](@ref) and [`ValueBinning`](@extref ComplexityMeasures)](@id example_ShortExpansionConditionalMutualInformation_JointProbabilities_CodifyVariables_ValueBinning)
 
 ```@example
 using Associations
@@ -1111,9 +1111,9 @@ est = JointProbabilities(SECMI(base = 2), CodifyVariables(ValueBinning(3)))
 association(est, x, z, y)
 ```
 
-### [[`EntropyDecomposition`](@ref) + [`Kraskov`](@ref)](@id example_CMIShannon_EntropyDecomposition_Kraskov)
+### [[`EntropyDecomposition`](@ref) + [`Kraskov`](@extref ComplexityMeasures)](@id example_CMIShannon_EntropyDecomposition_Kraskov)
 
-Any [`DifferentialInfoEstimator`](@ref) can also be used to compute conditional
+Any [`DifferentialInfoEstimator`](@extref ComplexityMeasures) can also be used to compute conditional
 mutual information using a sum of entropies. For that, we 
 usethe [`EntropyDecomposition`](@ref) estimator. No bias correction is applied for 
 [`EntropyDecomposition`](@ref) either.
@@ -1131,12 +1131,12 @@ est = EntropyDecomposition(CMIShannon(), Kraskov(k = 5))
 association(est, x, z, y)
 ```
 
-Any [`DiscreteInfoEstimator`](@ref) that computes entropy can also be used to compute
+Any [`DiscreteInfoEstimator`](@extref ComplexityMeasures) that computes entropy can also be used to compute
 conditional mutual information using a sum of entropies. For that, we also
 use [`EntropyDecomposition`](@ref). In the discrete case, we also have to specify a
 discretization (an [`OutcomeSpace`](@ref)).
 
-### [[`EntropyDecomposition`](@ref) + [`ValueBinning`](@ref)](@id example_CMIShannon_EntropyDecomposition_ValueBinning)
+### [[`EntropyDecomposition`](@ref) + [`ValueBinning`](@extref ComplexityMeasures)](@id example_CMIShannon_EntropyDecomposition_ValueBinning)
 
 ```@example
 using Associations
@@ -1169,7 +1169,7 @@ association(est, x, z, y)
 ```
 
 
-### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@ref)](@id example_CMIRenyiJizba_EntropyDecomposition_LeonenkoProzantoSavani)
+### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures)](@id example_CMIRenyiJizba_EntropyDecomposition_LeonenkoProzantoSavani)
 
 ```@example example_CMIRenyiJizba
 using Associations
@@ -1183,7 +1183,7 @@ association(est, x, y, z)
 ```
 
 
-### [[`EntropyDecomposition`](@ref) + [`OrdinalPatterns`](@ref)](@id example_CMIRenyiJizba_EntropyDecomposition_OrdinalPatterns)
+### [[`EntropyDecomposition`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_CMIRenyiJizba_EntropyDecomposition_OrdinalPatterns)
 
 ```@example example_CMIRenyiJizba
 using Associations
@@ -1198,7 +1198,7 @@ association(est, x, y, z)
 
 ## [`TEShannon`](@ref)
 
-### [[`EntropyDecomposition`](@ref) + [`TransferOperator`](@ref)](@id example_TEShannon_EntropyDecomposition_TransferOperator)
+### [[`EntropyDecomposition`](@extref ComplexityMeasures) + [`TransferOperator`](@extref ComplexityMeasures)](@id example_TEShannon_EntropyDecomposition_TransferOperator)
 
 For transfer entropy examples, we'll construct some time series for which 
 there is time-delayed forcing between variables.
@@ -1280,7 +1280,7 @@ association(est, x, z, y) # should be near 0 (and can be negative)
 ### [[`SymbolicTransferEntropy`](@ref) estimator](@id example_TEShannon_SymbolicTransferEntropy)
 
 The [`SymbolicTransferEntropy`](@ref) estimator is just a convenience wrapper which utilizes
-[`CodifyVariables`](@ref)with the [`OrdinalPatterns`](@ref) outcome space to 
+[`CodifyVariables`](@ref)with the [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space to 
 discretize the input time series before computing transfer entropy.
 
 We'll use coupled time series from the `logistic4` system above, where `x → y → z → w`.
@@ -1306,9 +1306,9 @@ We will test
 
 - The [`Lindner`](@ref) and [`Zhu1`](@ref) dedicated transfer entropy estimators,
     which try to eliminate bias.
-- The [`KraskovStögbauerGrassberger1`](@ref) estimator, which computes TE naively as a sum of mutual information
+- The [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator, which computes TE naively as a sum of mutual information
     terms (without guaranteed cancellation of biases for the total sum).
-- The [`Kraskov`](@ref) estimator, which computes TE naively as a sum of entropy 
+- The [`Kraskov`](@extref ComplexityMeasures) estimator, which computes TE naively as a sum of entropy 
     terms (without guaranteed cancellation of biases for the total sum).
 
 ```@example
@@ -1383,7 +1383,7 @@ fig
 Let's try to reproduce the results from Schreiber's original paper [Schreiber2000](@cite) where
 he introduced the transfer entropy. We'll here use the [`JointProbabilities`](@ref) estimator,
 discretizing per column of the input data using the [`CodifyVariables`](@ref) discretization
-scheme with the [`ValueBinning`](@ref) outcome space.
+scheme with the [`ValueBinning`](@extref ComplexityMeasures) outcome space.
 
 ```@example example_te_schreiber
 using Associations
@@ -1484,7 +1484,7 @@ The plot above shows the original transfer entropies (solid lines) and the 95th
 
 ## [`TERenyiJizba`](@ref)
 
-### [[`EntropyDecomposition`](@ref) + [`TransferOperator`](@ref)](@id example_TERenyiJizba_EntropyDecomposition_TransferOperator)
+### [[`EntropyDecomposition`](@extref ComplexityMeasures) + [`TransferOperator`](@extref ComplexityMeasures)](@id example_TERenyiJizba_EntropyDecomposition_TransferOperator)
 
 We can perform the same type of analysis as above using [`TERenyiJizba`](@ref)
 instead of [`TEShannon`](@ref).
diff --git a/docs/src/examples/examples_independence.md b/docs/src/examples/examples_independence.md
index c29986f9..0ccad560 100644
--- a/docs/src/examples/examples_independence.md
+++ b/docs/src/examples/examples_independence.md
@@ -387,7 +387,7 @@ end
 
 ### [[`CMIShannon`](@ref)](@id example_LocalPermutationTest_CMIShannon)
 
-To estimate CMI, we'll use the [`Kraskov`](@ref) differential
+To estimate CMI, we'll use the [`Kraskov`](@extref ComplexityMeasures) differential
 entropy estimator, which naively computes CMI as a sum of entropy terms without guaranteed
 bias cancellation.
 
@@ -504,7 +504,7 @@ independence(test, x, z, y)
 
 ## [[`JointProbabilities`](@ref) estimation on categorical data](@id example_SECMITEST_JointProbabilities_CodifyVariables_UniqueElements)
 
-Note that this also works for categorical variables. Just use [`UniqueElements`](@ref) to 
+Note that this also works for categorical variables. Just use [`UniqueElements`](@extref ComplexityMeasures) to 
 discretize!
 
 ```@example example_SECMITest_categorical
diff --git a/src/independence_tests/secmi/secmi_test.jl b/src/independence_tests/secmi/secmi_test.jl
index 2e4af9c2..5f8527a0 100644
--- a/src/independence_tests/secmi/secmi_test.jl
+++ b/src/independence_tests/secmi/secmi_test.jl
@@ -7,26 +7,26 @@ export SECMITestResult
 
 A test for conditional independence based on the [`ShortExpansionConditionalMutualInformation`](@ref) measure [Kubkowski2021](@cite).
 
-The first argument `est` must be a [`InformationMeasureEstimator`](@ref) that provides the 
+The first argument `est` must be a [`ComplexityMeasures.InformationMeasureEstimator`](@extref) that provides the 
 [`ShortExpansionConditionalMutualInformation`](@ref) instance. See examples below.
 
 ## Examples
 
 - [Example 1](@ref example_SECMITEST_JointProbabilities_CodifyVariables_ValueBinning): Independence test for small sample sizes using [`CodifyVariables`](@ref) with 
-    [`ValueBinning`](@ref) discretization.
+    [`ComplexityMeasures.ValueBinning`](@extref) discretization.
 - [Example 2](@ref example_SECMITEST_JointProbabilities_CodifyVariables_UniqueElements): Independence test for small sample
-    sizes with categorical data (using [`CodifyVariables`](@ref) with [`UniqueElements`](@ref) discretization).
+    sizes with categorical data (using [`CodifyVariables`](@ref) with [`ComplexityMeasures.UniqueElements`](@extref) discretization).
 """
-struct SECMITest{E, S, I, RNG} <: IndependenceTest{E}
+struct SECMITest{E,S,I,RNG} <: IndependenceTest{E}
     # really, this can only be an estimator, but we name it `est_or_measure` for consistency 
     # with the remaining tests, so we don't have to write custom code.
-    est_or_measure::E 
+    est_or_measure::E
     surrogate::S
     nshuffles::I
     rng::RNG
 end
 
-function SECMITest(est; nshuffles = 19, surrogate = RandomShuffle(), rng = Random.default_rng())
+function SECMITest(est; nshuffles=19, surrogate=RandomShuffle(), rng=Random.default_rng())
     return SECMITest(est, surrogate, nshuffles, rng)
 end
 
@@ -50,7 +50,7 @@ with [`independence`](@ref), as described in [Kubkowski2021](@cite).
 - `D𝒩`: The ``D_{N(\\hat{\\mu}, \\hat{\\sigma})}`` statistic.
 - `D𝒳²`: The ``D_{\\chi^2}`` statistic.
 """
-struct SECMITestResult{S0, SK, P, MU, S, E, DN, DCHI} <: IndependenceTestResult
+struct SECMITestResult{S0,SK,P,MU,S,E,DN,DCHI} <: IndependenceTestResult
     n_vars::Int # 3 vars = conditional (always 3)
     secmi₀::S0 # the value of the measure, non-permuted
     secmiₖ::SK # the values of the measure, permuted `nshuffles` times
@@ -74,7 +74,7 @@ function Base.show(io::IO, test::SECMITestResult)
 
         $(pvalue_text_summary(test))
         """
-        )
+    )
 end
 
 function independence(test::SECMITest, x, y, z)
@@ -85,9 +85,9 @@ function independence(test::SECMITest, x, y, z)
     for k = 1:nshuffles
         secmiₖ[k] = association(est_or_measure, sx(), y, z)
     end
-    μ̂ = 1/nshuffles * sum(secmiₖ)
-    σ̂ = 1/(nshuffles - 1) * sum((sₖ - μ̂)^2 for sₖ in secmiₖ)
-    emp_cdf = ecdf(secmiₖ) 
+    μ̂ = 1 / nshuffles * sum(secmiₖ)
+    σ̂ = 1 / (nshuffles - 1) * sum((sₖ - μ̂)^2 for sₖ in secmiₖ)
+    emp_cdf = ecdf(secmiₖ)
     F𝒩 = Normal(μ̂, σ̂)
 
     if μ̂ ≤ 0.0
@@ -99,7 +99,7 @@ function independence(test::SECMITest, x, y, z)
         # so we put μ̂ <= 0.0 in a separate criterion first to avoid errors.
         F𝒳² = Chisq(μ̂)
         D𝒩, D𝒳² = sup_values(emp_cdf, F𝒩, F𝒳², secmiₖ)
-        if  D𝒩 < D𝒳²
+        if D𝒩 < D𝒳²
             p = 1 - cdf(F𝒩, secmi₀)
         else
             p = 1 - cdf(F𝒳², secmi₀)
@@ -108,7 +108,7 @@ function independence(test::SECMITest, x, y, z)
 
     end
 
-   
+
     return SECMITestResult(3, secmi₀, secmiₖ, p, μ̂, σ̂, emp_cdf, D𝒩, D𝒳²)
 end
 
diff --git a/src/methods/information/core.jl b/src/methods/information/core.jl
index 3aa65975..b1a95008 100644
--- a/src/methods/information/core.jl
+++ b/src/methods/information/core.jl
@@ -1,4 +1,4 @@
-import ComplexityMeasures: information 
+import ComplexityMeasures: information
 export information
 
 export MultivariateInformationMeasure
@@ -27,10 +27,10 @@ The supertype for all estimators of multivariate information measures.
 
 [`MutualInformationEstimator`](@ref)s:
 
-- [`KraskovStögbauerGrassberger1`](@ref)
-- [`KraskovStögbauerGrassberger2`](@ref)
+- [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures)
+- [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures)
 - [`GaoOhViswanath`](@ref)
-- [`GaoKannanOhViswanath`](@ref)
+- [`GaoKannanOhViswanath`](@extref ComplexityMeasures)
 - [`GaussianMI`](@ref)
 
 [`ConditionalMutualInformationEstimator`](@ref)s:
@@ -56,10 +56,10 @@ The supertype for dedicated [`MutualInformation`](@ref) estimators.
 
 ## Concrete implementations
 
-- [`KraskovStögbauerGrassberger1`](@ref)
-- [`KraskovStögbauerGrassberger2`](@ref)
+- [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures)
+- [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures)
 - [`GaoOhViswanath`](@ref)
-- [`GaoKannanOhViswanath`](@ref)
+- [`GaoKannanOhViswanath`](@extref ComplexityMeasures)
 - [`GaussianMI`](@ref)
 """
 abstract type MutualInformationEstimator{M} <: BivariateInformationMeasureEstimator{M} end
diff --git a/src/methods/information/counts_and_probs/counts.jl b/src/methods/information/counts_and_probs/counts.jl
index abd4ecc9..dd6dc996 100644
--- a/src/methods/information/counts_and_probs/counts.jl
+++ b/src/methods/information/counts_and_probs/counts.jl
@@ -20,7 +20,7 @@ Construct an `N`-dimensional contingency table from the input iterables
 `x₁, x₂, ..., xₙ` which are such that 
 `length(x₁) == length(x₂) == ⋯ == length(xₙ)`.
 
-If `x₁, x₂, ..., xₙ` are already discrete, then use [`UniqueElements`](@ref) as 
+If `x₁, x₂, ..., xₙ` are already discrete, then use [`UniqueElements`](@extref ComplexityMeasures) as 
 the first argument to directly construct the joint contingency table.
 
 If `x₁, x₂, ..., xₙ` need to be discretized, provide as the first argument
@@ -52,10 +52,10 @@ z = rand([(1, 2), (2, 1)], n)
 counts(UniqueElements(), x, y, z)
 ```
 
-See also: [`CodifyPoints`](@ref), [`CodifyVariables`](@ref), [`UniqueElements`](@ref), [`OutcomeSpace`](@ref),
+See also: [`CodifyPoints`](@ref), [`CodifyVariables`](@ref), [`UniqueElements`](@extref ComplexityMeasures), [`OutcomeSpace`](@ref),
 [`probabilities`](@ref).
 """
-function counts(o::UniqueElements, x::Vararg{VectorOrStateSpaceSet, N}) where N # this extends ComplexityMeasures.jl definition
+function counts(o::UniqueElements, x::Vararg{VectorOrStateSpaceSet,N}) where N # this extends ComplexityMeasures.jl definition
     # Get marginal probabilities and outcomes
     L = length(x)
     cts, lmaps, encoded_outcomes = counts_table(x...)
@@ -66,7 +66,7 @@ function counts(o::UniqueElements, x::Vararg{VectorOrStateSpaceSet, N}) where N
     return Counts(cts, actual_outcomes)
 end
 
-function counts(x::Vararg{VectorOrStateSpaceSet, N}) where N
+function counts(x::Vararg{VectorOrStateSpaceSet,N}) where N
     if N == 1
         return ComplexityMeasures.counts(UniqueElements(), x...)
     else
@@ -81,7 +81,7 @@ function to_outcomes(lmap::Dict, encoded_outcomes::Vector{<:Integer})
 end
 
 function counts_table(x...)
-    Ls = length.(x);
+    Ls = length.(x)
     if !allequal(Ls)
         throw(ArgumentError("Input data must have equal lengths. Got lengths $Ls."))
     end
@@ -96,7 +96,7 @@ function counts_table(x...)
 
     # Create the table with correct dimensions, assumming the outcome space is
     # fully determined by the elements that are present in `x`.
-    table_dims = length.(unique_elements.(x));
+    table_dims = length.(unique_elements.(x))
     cts = zeros(Int, table_dims)
 
     # Each element in `X` isa `SVector{m, Int}`, so can be treated as a cartesian index.
@@ -162,10 +162,10 @@ _levelsmap(x::AbstractStateSpaceSet) = levelsmap(x.data)
 unique_elements(x) = unique(x)
 unique_elements(x::AbstractStateSpaceSet) = unique(x.data)
 
-function marginal(c::Counts; dims = 1:ndims(c))
+function marginal(c::Counts; dims=1:ndims(c))
     alldims = 1:ndims(c)
     reduce_dims = (setdiff(alldims, dims)...,)
-    marginal = dropdims(sum(c.cts, dims = reduce_dims), dims = reduce_dims)
+    marginal = dropdims(sum(c.cts, dims=reduce_dims), dims=reduce_dims)
     include_idxs = setdiff(alldims, reduce_dims)
     new_outcomes = c.outcomes[include_idxs]
     new_dimlabels = c.dimlabels[include_idxs]
@@ -180,13 +180,13 @@ end
 # ----------------------------------------------------------------
 # If multiple encodings are given, the number of encodings must match the number of
 # input variables.
-function counts(encoding::CodifyPoints{N}, x::Vararg{Any, N}) where {N}
+function counts(encoding::CodifyPoints{N}, x::Vararg{Any,N}) where {N}
     x̂ = codify(encoding, x...)
     return counts(UniqueElements(), x̂...)
 end
 
 # If only one encoding is given, apply same encoding to all points
-function counts(encoding::CodifyPoints{1}, x::Vararg{Any, N}) where {Any, N}
+function counts(encoding::CodifyPoints{1}, x::Vararg{Any,N}) where {Any,N}
     e = first(encoding.encodings)
     x̂ = ([encode(e, pt) for pt in xₖ] for xₖ in x)
     return counts(UniqueElements(), x̂...)
@@ -194,7 +194,7 @@ end
 
 # Per variable/column
 # ----------------------------------------------------------------
-function counts(discretization::CodifyVariables{1}, x::Vararg{ArrayOrStateSpaceSet, N}) where N
+function counts(discretization::CodifyVariables{1}, x::Vararg{ArrayOrStateSpaceSet,N}) where N
     o = first(discretization.outcome_spaces)
     # Treat 1D state space sets as vectors, so we can apply the outcome space sequentially.
     # TODO: show warning or not? I think this can be silent, because I can't really think of a situation
@@ -204,7 +204,7 @@ function counts(discretization::CodifyVariables{1}, x::Vararg{ArrayOrStateSpaceS
     return counts(x̂...)
 end
 
-function counts(d::CodifyVariables{1, UniqueElements}, x::Vararg{ArrayOrStateSpaceSet, N}) where N
+function counts(d::CodifyVariables{1,UniqueElements}, x::Vararg{ArrayOrStateSpaceSet,N}) where N
     o = first(d.outcome_spaces)
     return counts(o, x...)
 end
@@ -218,7 +218,7 @@ as_vec(x::AbstractStateSpaceSet{1}) = [first(xᵢ) for xᵢ in vec(x)]
 # guaranteed API-wise that embedding vectors are constructed in the same way
 # (although *in practice* all `OutcomeSpace` that use embeddings do so 
 # per v3.6 of ComplexityMeasures.jl).
-function counts(discretization::CodifyVariables{N}, x::Vararg{Any, N}) where N
+function counts(discretization::CodifyVariables{N}, x::Vararg{Any,N}) where N
     encoded_pts = codify(discretization, x...)
     return counts(encoded_pts...)
 end
diff --git a/src/methods/information/counts_and_probs/encoding/codify_variables.jl b/src/methods/information/counts_and_probs/encoding/codify_variables.jl
index 5eaf4701..f5dbde6d 100644
--- a/src/methods/information/counts_and_probs/encoding/codify_variables.jl
+++ b/src/methods/information/counts_and_probs/encoding/codify_variables.jl
@@ -18,11 +18,11 @@ using the given `outcome_space`.
 
 ## Compatible outcome spaces
 
-- [`UniqueElements`](@ref) (for when data are pre-discretized)
+- [`UniqueElements`](@extref ComplexityMeasures) (for when data are pre-discretized)
 - [`BubbleSortSwaps`](@ref)
 - [`CosineSimilarityBinning`](@ref)
-- [`OrdinalPatterns`](@ref)
-- [`Dispersion`](@ref)
+- [`OrdinalPatterns`](@extref ComplexityMeasures)
+- [`Dispersion`](@extref ComplexityMeasures)
 
 # Description
 
@@ -49,9 +49,9 @@ d = CodifyVariables(OrdinalPatterns(m=2))
 cx, cy = codify(d, x, y)
 ```
 """
-struct CodifyVariables{N, E} <: Discretization{N}
-    outcome_spaces::NTuple{N, OutcomeSpace}
-    function CodifyVariables(outcome_spaces::NTuple{N, OutcomeSpace}) where N
+struct CodifyVariables{N,E} <: Discretization{N}
+    outcome_spaces::NTuple{N,OutcomeSpace}
+    function CodifyVariables(outcome_spaces::NTuple{N,OutcomeSpace}) where N
         if N > 1
             n_outs = [total_outcomes(o) for o in outcome_spaces]
             if !allequal(n_outs)
@@ -60,7 +60,7 @@ struct CodifyVariables{N, E} <: Discretization{N}
                 throw(ArgumentError(s))
             end
         end
-        new{N, eltype(outcome_spaces)}(outcome_spaces)
+        new{N,eltype(outcome_spaces)}(outcome_spaces)
     end
 end
 function CodifyVariables(os...)
@@ -100,20 +100,20 @@ cx, cy = codify(CodifyPoints(OrdinalPatternEncoding(3)), x, y)
 """
 function codify(encoding::CodifyVariables, x) end
 
-function codify(encoding::CodifyVariables{1}, x::Vararg{Any, 1})
+function codify(encoding::CodifyVariables{1}, x::Vararg{Any,1})
     e = first(encoding.outcome_spaces)
     x̂ = ComplexityMeasures.codify(e, first(x))
     return x̂::Vector{<:Integer}
 end
 
 function codify(encoding::CodifyVariables{1}, x::NTuple{1})
-    return (codify(encoding, x...), )
+    return (codify(encoding, x...),)
 end
 
-function codify(encoding::CodifyVariables{1}, x::Vararg{Any, N}) where N
+function codify(encoding::CodifyVariables{1}, x::Vararg{Any,N}) where N
     e = first(encoding.outcome_spaces)
     x̂ = map(xᵢ -> ComplexityMeasures.codify(e, xᵢ), x)
-    return x̂::NTuple{N, Vector{<:Integer}}
+    return x̂::NTuple{N,Vector{<:Integer}}
 end
 
 function codify(encoding::CodifyVariables{1}, x::AbstractStateSpaceSet)
@@ -126,7 +126,7 @@ end
 # guaranteed API-wise that embedding vectors are constructed in the same way
 # (although *in practice* all `OutcomeSpace` that use embeddings do so 
 # per v3.6 of ComplexityMeasures.jl).
-function codify(encoding::CodifyVariables{N}, x::Vararg{Any, N}) where N
+function codify(encoding::CodifyVariables{N}, x::Vararg{Any,N}) where N
     os = encoding.outcome_spaces
     return [codify(CodifyVariables(os[i]), x[i]) for i in 1:N]
 end
diff --git a/src/methods/information/counts_and_probs/probabilities.jl b/src/methods/information/counts_and_probs/probabilities.jl
index 986b4940..3751c3d4 100644
--- a/src/methods/information/counts_and_probs/probabilities.jl
+++ b/src/methods/information/counts_and_probs/probabilities.jl
@@ -21,7 +21,7 @@ Construct an `N`-dimensional [`Probabilities`](@ref) array from the input iterab
 Probabilities are computed by first constructing a joint contingency matrix in the form 
 of a [`Counts`](@ref) instance. 
 
-If `x₁, x₂, ..., xₙ` are already discrete, then use [`UniqueElements`](@ref) as 
+If `x₁, x₂, ..., xₙ` are already discrete, then use [`UniqueElements`](@extref ComplexityMeasures) as 
 the first argument to directly construct the joint contingency table.
 
 If `x₁, x₂, ..., xₙ` need to be discretized, provide as the first argument
@@ -51,24 +51,24 @@ z = rand([(1, 2), (2, 1)], n)
 probabilities(UniqueElements(), x, y, z)
 ```
 
-See also: [`CodifyPoints`](@ref), [`CodifyVariables`](@ref), [`UniqueElements`](@ref), [`OutcomeSpace`](@ref).
+See also: [`CodifyPoints`](@ref), [`CodifyVariables`](@ref), [`UniqueElements`](@extref ComplexityMeasures), [`OutcomeSpace`](@ref).
 """
 function probabilities(o::OutcomeSpace) end
 
-function probabilities(o::OutcomeSpace, x::Vararg{VectorOrStateSpaceSet, N}) where N # this extends ComplexityMeasures.jl definition
+function probabilities(o::OutcomeSpace, x::Vararg{VectorOrStateSpaceSet,N}) where N # this extends ComplexityMeasures.jl definition
     return Probabilities(counts(o, x...))
 end
-function probabilities(est::RelativeAmount, c::Counts{<:Integer, N}) where N
+function probabilities(est::RelativeAmount, c::Counts{<:Integer,N}) where N
     probs = Probabilities(c)
     return Probabilities(probs.p, c.outcomes, c.dimlabels)
 end
 
-function probabilities(est::ProbabilitiesEstimator, c::Counts{<:Integer, N}) where N
+function probabilities(est::ProbabilitiesEstimator, c::Counts{<:Integer,N}) where N
     return Probabilities(probs.p, c.outcomes, c.dimlabels)
 end
 
 # Not providing any discretization defaults to `RelativeAmount` estimation.
-function probabilities(x::Vararg{VectorOrStateSpaceSet, N}) where N
+function probabilities(x::Vararg{VectorOrStateSpaceSet,N}) where N
     cts = counts(UniqueElements(), x...)
     probs = probabilities(RelativeAmount(), cts)
     return Probabilities(probs.p, cts.outcomes, cts.dimlabels)
@@ -81,14 +81,14 @@ end
 Given a set of counts `c` (a contingency table), or a multivariate probability mass
 function `p`, return the marginal counts/probabilities along the given `dims`.
 """
-function marginal(p::Probabilities; dims = 1:ndims(p))
+function marginal(p::Probabilities; dims=1:ndims(p))
     alldims = 1:ndims(p)
     reduce_dims = (setdiff(alldims, dims)...,)
     # if all(a == b for (a, b) in zip(reduce_dims, alldims))
     #     @show "not taking marginal for $dims and $p"
     #     return p
     # end
-    marg = dropdims(sum(p.p, dims = reduce_dims), dims = reduce_dims)
+    marg = dropdims(sum(p.p, dims=reduce_dims), dims=reduce_dims)
     include_idxs = setdiff(alldims, reduce_dims)
     N = length(include_idxs)
     if N > 0
@@ -101,7 +101,7 @@ function marginal(p::Probabilities; dims = 1:ndims(p))
         return Probabilities(marg, new_outcomes, new_dimlabels)
     end
     return Probabilities(marg)
-   
+
 end
 
 # ----------------------------------------------------------------
@@ -110,19 +110,19 @@ end
 
 # Per point/row
 # ----------------------------------------------------------------
-function probabilities(encoding::CodifyPoints{1}, x::Vararg{Any, N}) where {N}
+function probabilities(encoding::CodifyPoints{1}, x::Vararg{Any,N}) where {N}
     cts = counts(encoding, x...)
     return Probabilities(cts)
 end
 
-function probabilities(encoding::CodifyPoints{N}, x::Vararg{Any, N}) where {N}
+function probabilities(encoding::CodifyPoints{N}, x::Vararg{Any,N}) where {N}
     cts = counts(encoding, x...)
     return Probabilities(cts)
 end
 
 # Per variable/column
 # ----------------------------------------------------------------
-function probabilities(discretization::CodifyVariables, x::Vararg{ArrayOrStateSpaceSet, N}) where N
+function probabilities(discretization::CodifyVariables, x::Vararg{ArrayOrStateSpaceSet,N}) where N
     cts = counts(discretization, x...)
     return probabilities(RelativeAmount(), cts)
 end
\ No newline at end of file
diff --git a/src/methods/information/definitions/conditional_entropies/ConditionalEntropyShannon.jl b/src/methods/information/definitions/conditional_entropies/ConditionalEntropyShannon.jl
index aebecc38..51afae9b 100644
--- a/src/methods/information/definitions/conditional_entropies/ConditionalEntropyShannon.jl
+++ b/src/methods/information/definitions/conditional_entropies/ConditionalEntropyShannon.jl
@@ -55,14 +55,14 @@ H^S(X | Y) = h^S(X, Y) - h^S(Y),
 where ``h^S(\\cdot)`` and ``h^S(\\cdot | \\cdot)`` are the [`Shannon`](@ref)
 differential entropy and Shannon joint differential entropy, respectively. This is the
 definition used when calling [`association`](@ref) with a
-[`DifferentialInfoEstimator`](@ref).
+[`DifferentialInfoEstimator`](@extref ComplexityMeasures).
 
 ## Estimation
 
 - [Example 1](@ref example_ConditionalEntropyShannon_analytical): Analytical example from Cover & Thomas's book.
 - [Example 2](@ref example_ConditionalEntropyShannon_JointProbabilities_CodifyVariables_UniqueElements): 
     [`JointProbabilities`](@ref) estimator with[`CodifyVariables`](@ref) discretization and 
-    [`UniqueElements`](@ref) outcome space on categorical data.
+    [`UniqueElements`](@extref ComplexityMeasures) outcome space on categorical data.
 - [Example 3](@ref example_ConditionalEntropyShannon_JointProbabilities_CodifyPoints_UniqueElementsEncoding): 
     [`JointProbabilities`](@ref) estimator with [`CodifyPoints`](@ref) discretization and [`UniqueElementsEncoding`](@ref)
     encoding of points on numerical data.
@@ -79,10 +79,10 @@ function association(est::JointProbabilities{<:ConditionalEntropyShannon}, input
     return association(est.definition, probs)
 end
 
-function association(definition::ConditionalEntropyShannon, pxy::Probabilities{T, 2}) where {T}
+function association(definition::ConditionalEntropyShannon, pxy::Probabilities{T,2}) where {T}
     base = definition.base
     Nx, Ny = size(pxy)
-    py = marginal(pxy, dims = 2)
+    py = marginal(pxy, dims=2)
 
     ce = 0.0
     log0 = log_with_base(base)
diff --git a/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisAbe.jl b/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisAbe.jl
index 5721d94f..7f4205d8 100644
--- a/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisAbe.jl
+++ b/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisAbe.jl
@@ -26,19 +26,19 @@ Abe & Rajagopal's Tsallis conditional entropy between discrete random variables
 H_q^{T_A}(X | Y) = \\dfrac{H_q^T(X, Y) - H_q^T(Y)}{1 + (1-q)H_q^T(Y)},
 ```
 
-where ``H_q^T(\\cdot)`` and ``H_q^T(\\cdot, \\cdot)`` is the [`Tsallis`](@ref)
+where ``H_q^T(\\cdot)`` and ``H_q^T(\\cdot, \\cdot)`` is the [`Tsallis`](@extref ComplexityMeasures)
 entropy and the joint Tsallis entropy.
 
 ## Estimation
 
 - [Example 1](@ref example_ConditionalEntropyTsallisAbe_JointProbabilities_CodifyVariables_UniqueElements): 
     [`JointProbabilities`](@ref) estimator with[`CodifyVariables`](@ref) discretization and 
-    [`UniqueElements`](@ref) outcome space on categorical data.
+    [`UniqueElements`](@extref ComplexityMeasures) outcome space on categorical data.
 - [Example 2](@ref example_ConditionalEntropyTsallisAbe_JointProbabilities_CodifyPoints_UniqueElementsEncoding): 
     [`JointProbabilities`](@ref) estimator with [`CodifyPoints`](@ref) discretization and [`UniqueElementsEncoding`](@ref)
     encoding of points on numerical data.
 """
-Base.@kwdef struct ConditionalEntropyTsallisAbe{B, Q} <: ConditionalEntropy
+Base.@kwdef struct ConditionalEntropyTsallisAbe{B,Q} <: ConditionalEntropy
     base::B = 2
     q::Q = 1.5
 end
@@ -51,14 +51,14 @@ function association(est::JointProbabilities{<:ConditionalEntropyTsallisAbe}, in
     return association(est.definition, probs)
 end
 
-function association(definition::ConditionalEntropyTsallisAbe, pxy::Probabilities{T, 2}) where {T}
+function association(definition::ConditionalEntropyTsallisAbe, pxy::Probabilities{T,2}) where {T}
     (; base, q) = definition
 
     if q == 1 # if shannon, normalize
         return association(ConditionalEntropyShannon(; base), pxy)
     end
 
-    py = marginal(pxy, dims = 2)
+    py = marginal(pxy, dims=2)
     # Definition 7 in Abe & Rajagopal (2001)
     hjoint = 1 / (1 - q) * (sum(pxy .^ 2) - 1)
 
@@ -66,7 +66,7 @@ function association(definition::ConditionalEntropyTsallisAbe, pxy::Probabilitie
     hy = information(Tsallis(; q, base), py)
 
     # Equation 13 in Abe & Rajagopal (2001)
-    ce = (hjoint - hy) / (1 + (1 - q)*hy)
+    ce = (hjoint - hy) / (1 + (1 - q) * hy)
 
     return ce
 end
\ No newline at end of file
diff --git a/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisFuruichi.jl b/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisFuruichi.jl
index ec91235d..98d81879 100644
--- a/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisFuruichi.jl
+++ b/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisFuruichi.jl
@@ -40,12 +40,12 @@ is undefined for a particular value, then the measure is undefined and `NaN` is
 
 - [Example 1](@ref example_ConditionalEntropyTsallisFuruichi_JointProbabilities_CodifyVariables_UniqueElements): 
     [`JointProbabilities`](@ref) estimator with[`CodifyVariables`](@ref) discretization and 
-    [`UniqueElements`](@ref) outcome space on categorical data.
+    [`UniqueElements`](@extref ComplexityMeasures) outcome space on categorical data.
 - [Example 2](@ref example_ConditionalEntropyTsallisFuruichi_JointProbabilities_CodifyPoints_UniqueElementsEncoding): 
     [`JointProbabilities`](@ref) estimator with [`CodifyPoints`](@ref) discretization and [`UniqueElementsEncoding`](@ref)
     encoding of points on numerical data.
 """
-Base.@kwdef struct ConditionalEntropyTsallisFuruichi{B, Q} <: ConditionalEntropy
+Base.@kwdef struct ConditionalEntropyTsallisFuruichi{B,Q} <: ConditionalEntropy
     base::B = 2
     q::Q = 1.5
 end
@@ -58,13 +58,13 @@ function association(est::JointProbabilities{<:ConditionalEntropyTsallisFuruichi
     return association(est.definition, probs)
 end
 
-function association(definition::ConditionalEntropyTsallisFuruichi, pxy::Probabilities{T, 2}) where {T}
+function association(definition::ConditionalEntropyTsallisFuruichi, pxy::Probabilities{T,2}) where {T}
     (; base, q) = definition
     Nx, Ny = size(pxy)
     if q == 1
         return association(ConditionalEntropyShannon(; base), pxy)
     end
-    py = marginal(pxy, dims = 2)
+    py = marginal(pxy, dims=2)
     ce = 0.0
     qlog = logq0(q)
     for j in 1:Ny
@@ -83,7 +83,7 @@ function logq0(q)
     if q == 1.0
         return x -> zero(x)
     else
-        return x -> (x^(1 - q) - 1)/(1 - q)
+        return x -> (x^(1 - q) - 1) / (1 - q)
     end
 end
 
diff --git a/src/methods/information/definitions/conditional_mutual_informations/CMIRenyiJizba.jl b/src/methods/information/definitions/conditional_mutual_informations/CMIRenyiJizba.jl
index 5d63a3c5..65a9ad5b 100644
--- a/src/methods/information/definitions/conditional_mutual_informations/CMIRenyiJizba.jl
+++ b/src/methods/information/definitions/conditional_mutual_informations/CMIRenyiJizba.jl
@@ -34,11 +34,11 @@ where ``I_q^{R_{J}}(X; Z)`` is the [`MIRenyiJizba`](@ref) mutual information.
 - [Example 1](@ref example_CMIRenyiJizba_JointProbabilities_BubbleSortSwaps): 
     [`JointProbabilities`](@ref) with [`BubbleSortSwaps`](@ref) outcome space.
 - [Example 2](@ref example_CMIRenyiJizba_EntropyDecomposition_OrdinalPatterns): 
-    [`EntropyDecomposition`](@ref) with [`OrdinalPatterns`](@ref) outcome space.
+    [`EntropyDecomposition`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space.
 - [Example 3](@ref example_CMIRenyiJizba_EntropyDecomposition_LeonenkoProzantoSavani): 
-    [`EntropyDecomposition`](@ref) with differential entropy estimator [`LeonenkoProzantoSavani`](@ref).
+    [`EntropyDecomposition`](@ref) with differential entropy estimator [`LeonenkoProzantoSavani`](@extref ComplexityMeasures).
 """
-Base.@kwdef struct CMIRenyiJizba{B, Q} <: ConditionalMutualInformation
+Base.@kwdef struct CMIRenyiJizba{B,Q} <: ConditionalMutualInformation
     base::B = 2
     q::Q = 1.5
 end
@@ -48,10 +48,10 @@ end
 # ----------------------------------------------------------------
 function association(est::JointProbabilities{<:CMIRenyiJizba}, x, y, z)
     pxyz = probabilities(est.discretization, x, y, z)
-    pxz = marginal(pxyz, dims = [1,3])
-    pyz = marginal(pxyz, dims = [2,3])
-    pz = marginal(pxyz, dims = 3)
-    infodef = Renyi(q = est.definition.q, base = est.definition.base)
+    pxz = marginal(pxyz, dims=[1, 3])
+    pyz = marginal(pxyz, dims=[2, 3])
+    pz = marginal(pxyz, dims=3)
+    infodef = Renyi(q=est.definition.q, base=est.definition.base)
     HXYZ = information(infodef, pxyz)
     HXZ = information(infodef, pxz)
     HYZ = information(infodef, pyz)
@@ -59,13 +59,13 @@ function association(est::JointProbabilities{<:CMIRenyiJizba}, x, y, z)
     return HXZ + HYZ - HXYZ - HZ
 end
 
-function association(est::EntropyDecomposition{<:CMIRenyiJizba, <:DifferentialInfoEstimator{<:Renyi}}, x, y, z)
+function association(est::EntropyDecomposition{<:CMIRenyiJizba,<:DifferentialInfoEstimator{<:Renyi}}, x, y, z)
     HXZ, HYZ, HXYZ, HZ = marginal_entropies_cmi4h_differential(est, x, y, z)
     cmi = HXZ + HYZ - HXYZ - HZ
     return cmi
 end
 
-function association(est::EntropyDecomposition{<:CMIRenyiJizba, <:DiscreteInfoEstimator{<:Renyi}}, x, y, z)
+function association(est::EntropyDecomposition{<:CMIRenyiJizba,<:DiscreteInfoEstimator{<:Renyi}}, x, y, z)
     HXZ, HYZ, HXYZ, HZ = marginal_entropies_cmi4h_discrete(est, x, y, z)
     cmi = HXZ + HYZ - HXYZ - HZ
     return cmi
@@ -75,17 +75,17 @@ end
 # Pretty printing for decomposition estimators.
 # ------------------------------------------------
 function decomposition_string(
-        definition::CMIRenyiJizba, 
-        est::EntropyDecomposition{<:CMIRenyiJizba, <:DiscreteInfoEstimator{<:Renyi}}
-    ) 
-    return "Iᵣⱼ(X, Y | Z) = Hᵣ(X,Z) + Hᵣ(Y,Z) - Hᵣ(X,Y,Z) - Hᵣ(Z)";
+    definition::CMIRenyiJizba,
+    est::EntropyDecomposition{<:CMIRenyiJizba,<:DiscreteInfoEstimator{<:Renyi}}
+)
+    return "Iᵣⱼ(X, Y | Z) = Hᵣ(X,Z) + Hᵣ(Y,Z) - Hᵣ(X,Y,Z) - Hᵣ(Z)"
 end
 
 function decomposition_string(
-    definition::CMIRenyiJizba, 
-    est::EntropyDecomposition{<:CMIRenyiJizba, <:DifferentialInfoEstimator{<:Renyi}}
-) 
-    return "Iᵣⱼ(X, Y | Z) = hᵣ(X,Z) + hᵣ(Y,Z) - hᵣ(X,Y,Z) - hᵣ(Z)";
+    definition::CMIRenyiJizba,
+    est::EntropyDecomposition{<:CMIRenyiJizba,<:DifferentialInfoEstimator{<:Renyi}}
+)
+    return "Iᵣⱼ(X, Y | Z) = hᵣ(X,Z) + hᵣ(Y,Z) - hᵣ(X,Y,Z) - hᵣ(Z)"
 end
 
 # ---------------------------------
diff --git a/src/methods/information/definitions/conditional_mutual_informations/CMIShannon.jl b/src/methods/information/definitions/conditional_mutual_informations/CMIShannon.jl
index b70c7b91..0c0f886c 100644
--- a/src/methods/information/definitions/conditional_mutual_informations/CMIShannon.jl
+++ b/src/methods/information/definitions/conditional_mutual_informations/CMIShannon.jl
@@ -50,11 +50,11 @@ differential entropies.
 ## Estimation
 
 - [Example 1](@ref example_CMIShannon_EntropyDecomposition_Kraskov): 
-    [`EntropyDecomposition`](@ref) with [`Kraskov`](@ref) estimator.
+    [`EntropyDecomposition`](@ref) with [`Kraskov`](@extref ComplexityMeasures) estimator.
 - [Example 2](@ref example_CMIShannon_EntropyDecomposition_ValueBinning):
-    [`EntropyDecomposition`](@ref) with [`ValueBinning`](@ref) estimator.
+    [`EntropyDecomposition`](@ref) with [`ValueBinning`](@extref ComplexityMeasures) estimator.
 - [Example 3](@ref example_CMIShannon_MIDecomposition_KSG1): 
-    [`MIDecomposition`](@ref) with [`KraskovStögbauerGrassberger1`](@ref) estimator.
+    [`MIDecomposition`](@ref) with [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator.
 """
 Base.@kwdef struct CMIShannon{B} <: ConditionalMutualInformation
     base::B = 2
@@ -68,11 +68,11 @@ function association(est::JointProbabilities{<:CMIShannon}, x, y, z)
     return association(est.definition, probs)
 end
 
-function association(definition::CMIShannon, pxyz::Probabilities{T, 3}) where T
+function association(definition::CMIShannon, pxyz::Probabilities{T,3}) where T
     dx, dy, dz = size(pxyz)
-    pxz = marginal(pxyz, dims = [1, 3])
-    pyz = marginal(pxyz, dims = [2, 3])
-    pz = marginal(pxyz, dims = 3)
+    pxz = marginal(pxyz, dims=[1, 3])
+    pyz = marginal(pxyz, dims=[2, 3])
+    pz = marginal(pxyz, dims=3)
     cmi = 0.0
     log0 = log_with_base(definition.base)
     for k in 1:dz
@@ -97,13 +97,13 @@ end
 # ------------------------------------------------
 # Four-entropies decompostion of CMIShannon
 # ------------------------------------------------
-function association(est::EntropyDecomposition{<:CMIShannon, <:DifferentialInfoEstimator{<:Shannon}}, x, y, z)
+function association(est::EntropyDecomposition{<:CMIShannon,<:DifferentialInfoEstimator{<:Shannon}}, x, y, z)
     HXZ, HYZ, HXYZ, HZ = marginal_entropies_cmi4h_differential(est, x, y, z)
     cmi = HXZ + HYZ - HXYZ - HZ
     return cmi
 end
 
-function association(est::EntropyDecomposition{<:CMIShannon, <:DiscreteInfoEstimator{<:Shannon}}, x, y, z)
+function association(est::EntropyDecomposition{<:CMIShannon,<:DiscreteInfoEstimator{<:Shannon}}, x, y, z)
     HXZ, HYZ, HXYZ, HZ = marginal_entropies_cmi4h_discrete(est, x, y, z)
     cmi = HXZ + HYZ - HXYZ - HZ
     return cmi
@@ -112,7 +112,7 @@ end
 # ---------------------------------------------------
 # Two-mutual-information decomposition of CMIShannon 
 # ---------------------------------------------------
-function association(est::MIDecomposition{<:ConditionalMutualInformation, <:MutualInformationEstimator{<:MIShannon}}, x, y, z)
+function association(est::MIDecomposition{<:ConditionalMutualInformation,<:MutualInformationEstimator{<:MIShannon}}, x, y, z)
     MI_X_YZ, MI_X_Z = marginal_mutual_informations(est, x, y, z)
     cmi = MI_X_YZ - MI_X_Z
     return cmi
@@ -120,7 +120,7 @@ end
 
 # We don't care if the estimated is mixed, discrete or handles both. The MI estimator 
 # handles that internally.
-function marginal_mutual_informations(est::MIDecomposition{<:ConditionalMutualInformation, <:MutualInformationEstimator{<:MIShannon}}, x, y, z)
+function marginal_mutual_informations(est::MIDecomposition{<:ConditionalMutualInformation,<:MutualInformationEstimator{<:MIShannon}}, x, y, z)
     X = StateSpaceSet(x)
     Y = StateSpaceSet(y)
     Z = StateSpaceSet(z)
@@ -149,22 +149,22 @@ end
 # Pretty printing for decomposition estimators.
 # ------------------------------------------------
 function decomposition_string(
-        definition::CMIShannon, 
-        est::EntropyDecomposition{<:CMIShannon, <:DiscreteInfoEstimator{<:Shannon}}
-    )
-    return "Iₛ(X, Y | Z) = Hₛ(X,Z) + Hₛ(Y,Z) - Hₛ(X,Y,Z) - Hₛ(Z)";
+    definition::CMIShannon,
+    est::EntropyDecomposition{<:CMIShannon,<:DiscreteInfoEstimator{<:Shannon}}
+)
+    return "Iₛ(X, Y | Z) = Hₛ(X,Z) + Hₛ(Y,Z) - Hₛ(X,Y,Z) - Hₛ(Z)"
 end
 
 function decomposition_string(
-        definition::CMIShannon, 
-        est::EntropyDecomposition{<:CMIShannon, <:DifferentialInfoEstimator{<:Shannon}}
-    )
-    return "Iₛ(X, Y | Z) = hₛ(X,Z) + hₛ(Y,Z) - hₛ(X,Y,Z) - hₛ(Z)";
+    definition::CMIShannon,
+    est::EntropyDecomposition{<:CMIShannon,<:DifferentialInfoEstimator{<:Shannon}}
+)
+    return "Iₛ(X, Y | Z) = hₛ(X,Z) + hₛ(Y,Z) - hₛ(X,Y,Z) - hₛ(Z)"
 end
 
 function decomposition_string(
-        definition::CMIShannon, 
-        est::MIDecomposition{<:CMIShannon, <:MutualInformationEstimator}
-    )
+    definition::CMIShannon,
+    est::MIDecomposition{<:CMIShannon,<:MutualInformationEstimator}
+)
     return "Iₛ(X, Y | Z) = Iₛ(X; Y, Z) + Iₛ(X; Z)"
 end
\ No newline at end of file
diff --git a/src/methods/information/definitions/divergences_and_distances/HellingerDistance.jl b/src/methods/information/definitions/divergences_and_distances/HellingerDistance.jl
index dcc3eb18..1f2a7fb0 100644
--- a/src/methods/information/definitions/divergences_and_distances/HellingerDistance.jl
+++ b/src/methods/information/definitions/divergences_and_distances/HellingerDistance.jl
@@ -31,7 +31,7 @@ D_{H}(P_Y(\\Omega) || P_Y(\\Omega)) =
 
 - [Example 1](@ref example_HellingerDistance_precomputed_probabilities): From precomputed probabilities
 - [Example 2](@ref example_HellingerDistance_JointProbabilities_OrdinalPatterns): 
-    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@ref) outcome space
+    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space
 """
 struct HellingerDistance <: DivergenceOrDistance end
 
@@ -45,5 +45,5 @@ function association(est::JointProbabilities{<:HellingerDistance}, x, y)
 end
 
 function association(measure::HellingerDistance, px::Probabilities, py::Probabilities)
-    return 1/sqrt(2) * sum((sqrt(pxᵢ) - sqrt(pyᵢ))^2 for (pxᵢ, pyᵢ) in zip(px, py))
+    return 1 / sqrt(2) * sum((sqrt(pxᵢ) - sqrt(pyᵢ))^2 for (pxᵢ, pyᵢ) in zip(px, py))
 end
diff --git a/src/methods/information/definitions/divergences_and_distances/KLDivergence.jl b/src/methods/information/definitions/divergences_and_distances/KLDivergence.jl
index 1ad7eb6a..04288925 100644
--- a/src/methods/information/definitions/divergences_and_distances/KLDivergence.jl
+++ b/src/methods/information/definitions/divergences_and_distances/KLDivergence.jl
@@ -47,12 +47,12 @@ D_{KL}(P_Y(\\Omega) || P_Y(\\Omega)) =
 
 - [Example 1](@ref example_KLDivergence_precomputed_probabilities): From precomputed probabilities
 - [Example 2](@ref example_KLDivergence_JointProbabilities_OrdinalPatterns): 
-    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@ref) outcome space
+    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space
 """
 struct KLDivergence{B} <: DivergenceOrDistance
     base::B
 end
-KLDivergence(; base = 2) = KLDivergence(base)
+KLDivergence(; base=2) = KLDivergence(base)
 
 # ----------------------------------------------------------------
 # Estimation methods
diff --git a/src/methods/information/definitions/divergences_and_distances/RenyiDivergence.jl b/src/methods/information/definitions/divergences_and_distances/RenyiDivergence.jl
index edaed3cb..f5e127db 100644
--- a/src/methods/information/definitions/divergences_and_distances/RenyiDivergence.jl
+++ b/src/methods/information/definitions/divergences_and_distances/RenyiDivergence.jl
@@ -46,17 +46,17 @@ D_{q}(P_Y(\\Omega) || P_Y(\\Omega)) =
 
 - [Example 1](@ref example_RenyiDivergence_precomputed_probabilities): From precomputed probabilities
 - [Example 2](@ref example_RenyiDivergence_JointProbabilities_OrdinalPatterns): 
-    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@ref) outcome space
+    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space
 """
-struct RenyiDivergence{Q, B} <: DivergenceOrDistance
+struct RenyiDivergence{Q,B} <: DivergenceOrDistance
     q::Q
     base::B
-    function RenyiDivergence(q::Q, base::B) where {Q, B}
+    function RenyiDivergence(q::Q, base::B) where {Q,B}
         q > 0 || throw(ArgumentError("`q` must be positive. Got $q"))
-        new{Q, B}(q, base)
+        new{Q,B}(q, base)
     end
 end
-RenyiDivergence(; q = 0.5, base = 2) = RenyiDivergence(q, base)
+RenyiDivergence(; q=0.5, base=2) = RenyiDivergence(q, base)
 
 # ----------------------------------------------------------------
 # Estimation methods
diff --git a/src/methods/information/definitions/divergences_and_distances/VariationDistance.jl b/src/methods/information/definitions/divergences_and_distances/VariationDistance.jl
index 9dec8b31..1a0d2283 100644
--- a/src/methods/information/definitions/divergences_and_distances/VariationDistance.jl
+++ b/src/methods/information/definitions/divergences_and_distances/VariationDistance.jl
@@ -32,7 +32,7 @@ D_{V}(P_Y(\\Omega) || P_Y(\\Omega)) =
 
 - [Example 1](@ref example_VariationDistance_precomputed_probabilities): From precomputed probabilities
 - [Example 2](@ref example_VariationDistance_JointProbabilities_OrdinalPatterns): 
-    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@ref) outcome space
+    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space
 """
 struct VariationDistance <: DivergenceOrDistance end
 
@@ -46,5 +46,5 @@ function association(est::JointProbabilities{<:VariationDistance}, x, y)
 end
 
 function association(measure::VariationDistance, px::Probabilities, py::Probabilities)
-    return 1/2 * sum(abs(pxᵢ - pyᵢ) for (pxᵢ, pyᵢ) in zip(px, py))
+    return 1 / 2 * sum(abs(pxᵢ - pyᵢ) for (pxᵢ, pyᵢ) in zip(px, py))
 end
diff --git a/src/methods/information/definitions/joint_entropies/JointEntropyRenyi.jl b/src/methods/information/definitions/joint_entropies/JointEntropyRenyi.jl
index 1a6694e4..c119ae63 100644
--- a/src/methods/information/definitions/joint_entropies/JointEntropyRenyi.jl
+++ b/src/methods/information/definitions/joint_entropies/JointEntropyRenyi.jl
@@ -31,9 +31,9 @@ where ``q > 0`` and ``q != 1``.
 ## Estimation
 
 - [Example 1](@ref example_JointEntropyRenyi_ValueBinning): 
-    [`JointProbabilities`](@ref) with [`ValueBinning`](@ref) outcome space
+    [`JointProbabilities`](@ref) with [`ValueBinning`](@extref ComplexityMeasures) outcome space
 """
-Base.@kwdef struct JointEntropyRenyi{B, Q} <: JointEntropy
+Base.@kwdef struct JointEntropyRenyi{B,Q} <: JointEntropy
     base::B = 2
     q::Q = 1.5
 end
@@ -47,15 +47,15 @@ function association(est::JointProbabilities{<:JointEntropyRenyi}, x, y)
     return association(est.definition, probs)
 end
 
-function association(definition::JointEntropyRenyi, pxy::Probabilities{T, 2}) where T
+function association(definition::JointEntropyRenyi, pxy::Probabilities{T,2}) where T
     (; base, q) = definition
-    
+
     h = 0.0
     for p in pxy
         if p != 0
             h += p^q
         end
     end
-    h = 1 / (1 - q) * log(h) 
+    h = 1 / (1 - q) * log(h)
     return _convert_logunit(h, ℯ, base)
 end
\ No newline at end of file
diff --git a/src/methods/information/definitions/joint_entropies/JointEntropyShannon.jl b/src/methods/information/definitions/joint_entropies/JointEntropyShannon.jl
index 2ec11be0..321d6f72 100644
--- a/src/methods/information/definitions/joint_entropies/JointEntropyShannon.jl
+++ b/src/methods/information/definitions/joint_entropies/JointEntropyShannon.jl
@@ -31,7 +31,7 @@ where we define ``log(p(x, y)) := 0`` if ``p(x, y) = 0``.
 ## Estimation
 
 - [Example 1](@ref example_JointEntropyShannon_Dispersion): 
-    [`JointProbabilities`](@ref) with [`Dispersion`](@ref) outcome space
+    [`JointProbabilities`](@ref) with [`Dispersion`](@extref ComplexityMeasures) outcome space
 """
 Base.@kwdef struct JointEntropyShannon{B} <: JointEntropy
     base::B = 2
@@ -45,9 +45,9 @@ function association(est::JointProbabilities{<:JointEntropyShannon}, x, y)
     return association(est.definition, probs)
 end
 
-function association(definition::JointEntropyShannon, pxy::Probabilities{T, 2}) where T
+function association(definition::JointEntropyShannon, pxy::Probabilities{T,2}) where T
     (; base) = definition
-    
+
     h = 0.0
     for p in pxy
         if p != 0 # Define log(0) = 0
diff --git a/src/methods/information/definitions/joint_entropies/JointEntropyTsallis.jl b/src/methods/information/definitions/joint_entropies/JointEntropyTsallis.jl
index f2324c31..090505ae 100644
--- a/src/methods/information/definitions/joint_entropies/JointEntropyTsallis.jl
+++ b/src/methods/information/definitions/joint_entropies/JointEntropyTsallis.jl
@@ -32,9 +32,9 @@ we define ``log_q(x, q) := 0`` if ``q = 0``.
 ## Estimation
 
 - [Example 1](@ref example_JointEntropyTsallis_OrdinalPatterns): 
-    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@ref) outcome space
+    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space
 """
-Base.@kwdef struct JointEntropyTsallis{B, Q} <: JointEntropy
+Base.@kwdef struct JointEntropyTsallis{B,Q} <: JointEntropy
     base::B = 2
     q::Q = 1.5
 end
@@ -47,9 +47,9 @@ function association(est::JointProbabilities{<:JointEntropyTsallis}, x, y)
     return association(est.definition, probs)
 end
 
-function association(definition::JointEntropyTsallis, pxy::Probabilities{T, 2}) where T
+function association(definition::JointEntropyTsallis, pxy::Probabilities{T,2}) where T
     (; base, q) = definition
-    
+
     h = 0.0
     for p in pxy
         if p != 0.0 # Define logq(0) = 0
diff --git a/src/methods/information/definitions/mutual_informations/MIRenyiJizba.jl b/src/methods/information/definitions/mutual_informations/MIRenyiJizba.jl
index 720c404e..da13ffbe 100644
--- a/src/methods/information/definitions/mutual_informations/MIRenyiJizba.jl
+++ b/src/methods/information/definitions/mutual_informations/MIRenyiJizba.jl
@@ -31,11 +31,11 @@ where ``H_q^{R}(\\cdot)`` is the [`Rényi`](@ref) entropy.
 
 ## Estimation
 
-- [Example 1](@ref example_MIRenyiJizba_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@ref) outcome space.
-- [Example 2](@ref example_MIRenyiJizba_JointProbabilities_LeonenkoProzantoSavani): [`EntropyDecomposition`](@ref) with [`LeonenkoProzantoSavani`](@ref).
-- [Example 3](@ref example_MIRenyiJizba_EntropyDecomposition_ValueBinning): [`EntropyDecomposition`](@ref) with [`ValueBinning`](@ref).
+- [Example 1](@ref example_MIRenyiJizba_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures) outcome space.
+- [Example 2](@ref example_MIRenyiJizba_JointProbabilities_LeonenkoProzantoSavani): [`EntropyDecomposition`](@ref) with [`LeonenkoProzantoSavani`](@extref ComplexityMeasures).
+- [Example 3](@ref example_MIRenyiJizba_EntropyDecomposition_ValueBinning): [`EntropyDecomposition`](@ref) with [`ValueBinning`](@extref ComplexityMeasures).
 """
-Base.@kwdef struct MIRenyiJizba{B, Q} <: MutualInformation
+Base.@kwdef struct MIRenyiJizba{B,Q} <: MutualInformation
     base::B = 2
     q::Q = 1.5
 end
@@ -48,12 +48,12 @@ function association(est::JointProbabilities{<:MIRenyiJizba}, x, y)
     return association(est.definition, probs)
 end
 
-function association(definition::MIRenyiJizba, pxy::Probabilities{T, 2}) where T
+function association(definition::MIRenyiJizba, pxy::Probabilities{T,2}) where T
     (; base, q) = definition
 
-    px = marginal(pxy, dims = 1)
-    py = marginal(pxy, dims = 2)
-    
+    px = marginal(pxy, dims=1)
+    py = marginal(pxy, dims=2)
+
     logb = log_with_base(base)
     num = 0.0
     den = 0.0
@@ -78,15 +78,15 @@ end
 # Jizba, P., Lavička, H., & Tabachová, Z. (2021). Rényi Transfer Entropy Estimators for
 # Financial Time Series. Engineering Proceedings, 5(1), 33.
 # --------------------------------------------------------------
-function association(est::EntropyDecomposition{<:MIRenyiJizba, <:DifferentialInfoEstimator{<:Renyi}}, x, y)
+function association(est::EntropyDecomposition{<:MIRenyiJizba,<:DifferentialInfoEstimator{<:Renyi}}, x, y)
     HX, HY, HXY = marginal_entropies_mi3h_differential(est, x, y)
-    mi =  HX + HY - HXY
+    mi = HX + HY - HXY
     return mi
 end
 
-function association(est::EntropyDecomposition{<:MIRenyiJizba, <:DiscreteInfoEstimator{<:Renyi}}, x, y)
+function association(est::EntropyDecomposition{<:MIRenyiJizba,<:DiscreteInfoEstimator{<:Renyi}}, x, y)
     HX, HY, HXY = marginal_entropies_mi3h_discrete(est, x, y)
-    mi =  HX + HY - HXY
+    mi = HX + HY - HXY
     return mi
 end
 
@@ -94,15 +94,15 @@ end
 # Pretty printing for decomposition estimators.
 # ------------------------------------------------
 function decomposition_string(
-        definition::MIRenyiJizba, 
-        est::EntropyDecomposition{<:MIRenyiJizba, <:DifferentialInfoEstimator{<:Renyi}}
-    )
+    definition::MIRenyiJizba,
+    est::EntropyDecomposition{<:MIRenyiJizba,<:DifferentialInfoEstimator{<:Renyi}}
+)
     return "Iᵣⱼ(X, Y) = hᵣ(X) + hᵣ(Y) - hᵣ(X, Y)"
 end
 
 function decomposition_string(
-        definition::MIRenyiJizba, 
-        est::EntropyDecomposition{<:MIRenyiJizba, <:DiscreteInfoEstimator{<:Renyi}}
-    )
+    definition::MIRenyiJizba,
+    est::EntropyDecomposition{<:MIRenyiJizba,<:DiscreteInfoEstimator{<:Renyi}}
+)
     return "Iᵣⱼ(X, Y) = Hᵣ(X) + Hᵣ(Y) - Hᵣ(X, Y)"
 end
diff --git a/src/methods/information/definitions/mutual_informations/MIRenyiSarbu.jl b/src/methods/information/definitions/mutual_informations/MIRenyiSarbu.jl
index 6aa2d321..0c608f5c 100644
--- a/src/methods/information/definitions/mutual_informations/MIRenyiSarbu.jl
+++ b/src/methods/information/definitions/mutual_informations/MIRenyiSarbu.jl
@@ -1,6 +1,6 @@
 using ComplexityMeasures: Renyi
 
-export MIRenyiSarbu 
+export MIRenyiSarbu
 
 """
     MIRenyiSarbu <: BivariateInformationMeasure
@@ -36,10 +36,10 @@ I(X, Y)^R_q =
 
 ## Estimation
 
-- [Example 1](@ref example_MIRenyiSarbu_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@ref) for categorical data.
+- [Example 1](@ref example_MIRenyiSarbu_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures) for categorical data.
 - [Example 2](@ref example_MIRenyiSarbu_JointProbabilities_CosineSimilarityBinning): [`JointProbabilities`](@ref) with [`CosineSimilarityBinning`](@ref) for numerical data.
 """
-Base.@kwdef struct MIRenyiSarbu{B, Q} <: MutualInformation
+Base.@kwdef struct MIRenyiSarbu{B,Q} <: MutualInformation
     base::B = 2
     q::Q = 1.5
 end
@@ -52,11 +52,11 @@ function association(est::JointProbabilities{<:MIRenyiSarbu}, x, y)
     return association(est.definition, probs)
 end
 
-function association(definition::MIRenyiSarbu, pxy::Probabilities{T, 2}) where T
+function association(definition::MIRenyiSarbu, pxy::Probabilities{T,2}) where T
     (; base, q) = definition
 
-    px = marginal(pxy, dims = 1)
-    py = marginal(pxy, dims = 2)
+    px = marginal(pxy, dims=1)
+    py = marginal(pxy, dims=2)
 
     mi = 0.0
     for i in eachindex(px.p)
diff --git a/src/methods/information/definitions/mutual_informations/MIShannon.jl b/src/methods/information/definitions/mutual_informations/MIShannon.jl
index 06a76254..a036858a 100644
--- a/src/methods/information/definitions/mutual_informations/MIShannon.jl
+++ b/src/methods/information/definitions/mutual_informations/MIShannon.jl
@@ -19,10 +19,10 @@ The Shannon mutual information ``I_S(X; Y)``.
 
 - [`JointProbabilities`](@ref) (generic)
 - [`EntropyDecomposition`](@ref) (generic)
-- [`KraskovStögbauerGrassberger1`](@ref)
-- [`KraskovStögbauerGrassberger2`](@ref)
+- [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures)
+- [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures)
 - [`GaoOhViswanath`](@ref)
-- [`GaoKannanOhViswanath`](@ref)
+- [`GaoKannanOhViswanath`](@extref ComplexityMeasures)
 - [`GaussianMI`](@ref)
 
 ## Discrete definition
@@ -73,19 +73,19 @@ I^S(X; Y) = h^S(X) + h_q^S(Y) - h^S(X, Y),
 
 where ``h^S(\\cdot)`` and ``h^S(\\cdot, \\cdot)`` are the marginal and joint
 differential Shannon entropies. This definition is used by [`association`](@ref) when
-called with [`EntropyDecomposition`](@ref) estimator and a [`DifferentialInfoEstimator`](@ref).
+called with [`EntropyDecomposition`](@ref) estimator and a [`DifferentialInfoEstimator`](@extref ComplexityMeasures).
 
 ## Estimation
 
-- [Example 1](@ref example_MIShannon_JointProbabilities_ValueBinning): [`JointProbabilities`](@ref) with [`ValueBinning`](@ref) outcome space.
-- [Example 2](@ref example_MIShannon_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@ref) outcome space on string data.
+- [Example 1](@ref example_MIShannon_JointProbabilities_ValueBinning): [`JointProbabilities`](@ref) with [`ValueBinning`](@extref ComplexityMeasures) outcome space.
+- [Example 2](@ref example_MIShannon_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures) outcome space on string data.
 - [Example 3](@ref example_MIShannon_GaussianMI): Dedicated [`GaussianMI`](@ref) estimator.
-- [Example 4](@ref example_MIShannon_KSG1): Dedicated [`KraskovStögbauerGrassberger1`](@ref) estimator.
-- [Example 5](@ref example_MIShannon_KSG2): Dedicated [`KraskovStögbauerGrassberger2`](@ref) estimator.
-- [Example 6](@ref example_MIShannon_GaoKannanOhViswanath): Dedicated [`GaoKannanOhViswanath`](@ref) estimator.
-- [Example 7](@ref example_MIShannon_EntropyDecomposition_Kraskov): [`EntropyDecomposition`](@ref) with [`Kraskov`](@ref) estimator.
+- [Example 4](@ref example_MIShannon_KSG1): Dedicated [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator.
+- [Example 5](@ref example_MIShannon_KSG2): Dedicated [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator.
+- [Example 6](@ref example_MIShannon_GaoKannanOhViswanath): Dedicated [`GaoKannanOhViswanath`](@extref ComplexityMeasures) estimator.
+- [Example 7](@ref example_MIShannon_EntropyDecomposition_Kraskov): [`EntropyDecomposition`](@ref) with [`Kraskov`](@extref ComplexityMeasures) estimator.
 - [Example 8](@ref example_MIShannon_EntropyDecomposition_BubbleSortSwaps): [`EntropyDecomposition`](@ref) with [`BubbleSortSwaps`](@ref).
-- [Example 9](@ref example_MIShannon_EntropyDecomposition_Jackknife_ValueBinning): [`EntropyDecomposition`](@ref) with [`Jackknife`](@ref) estimator and [`ValueBinning`](@ref) outcome space.
+- [Example 9](@ref example_MIShannon_EntropyDecomposition_Jackknife_ValueBinning): [`EntropyDecomposition`](@ref) with [`Jackknife`](@extref ComplexityMeasures) estimator and [`ValueBinning`](@extref ComplexityMeasures) outcome space.
 - [Example 10](@ref example_MIShannon_reproducing_Kraskov): Reproducing Kraskov et al. (2004).
 """
 Base.@kwdef struct MIShannon{B} <: MutualInformation
@@ -102,11 +102,11 @@ function association(est::JointProbabilities{<:MIShannon}, x, y)
     return association(est.definition, probs)
 end
 
-function association(definition::MIShannon, pxy::Probabilities{T, 2}) where T
+function association(definition::MIShannon, pxy::Probabilities{T,2}) where T
     (; base) = definition
-    
-    px = marginal(pxy, dims = 1)
-    py = marginal(pxy, dims = 2)
+
+    px = marginal(pxy, dims=1)
+    py = marginal(pxy, dims=2)
     mi = 0.0
     logb = log_with_base(base)
     for i in eachindex(px.p)
@@ -126,15 +126,15 @@ end
 # ------------------------------------------------
 # Mutual information through entropy decomposition
 # ------------------------------------------------
-function association(est::EntropyDecomposition{<:MIShannon, <:DifferentialInfoEstimator{<:Shannon}}, x, y)
+function association(est::EntropyDecomposition{<:MIShannon,<:DifferentialInfoEstimator{<:Shannon}}, x, y)
     HX, HY, HXY = marginal_entropies_mi3h_differential(est, x, y)
-    mi =  HX + HY - HXY
+    mi = HX + HY - HXY
     return mi
 end
 
-function association(est::EntropyDecomposition{<:MIShannon, <:DiscreteInfoEstimator{<:Shannon}, D, P}, x, y) where {D, P}
+function association(est::EntropyDecomposition{<:MIShannon,<:DiscreteInfoEstimator{<:Shannon},D,P}, x, y) where {D,P}
     HX, HY, HXY = marginal_entropies_mi3h_discrete(est, x, y)
-    mi =  HX + HY - HXY
+    mi = HX + HY - HXY
     return mi
 end
 
@@ -142,15 +142,15 @@ end
 # Pretty printing for decomposition estimators.
 # ------------------------------------------------
 function decomposition_string(
-        definition::MIShannon, 
-        est::EntropyDecomposition{<:MIShannon, <:DifferentialInfoEstimator{<:Shannon}}
-    )
-    return "Iₛ(X, Y) = hₛ(X) + hₛ(Y) - hₛ(X, Y)";
+    definition::MIShannon,
+    est::EntropyDecomposition{<:MIShannon,<:DifferentialInfoEstimator{<:Shannon}}
+)
+    return "Iₛ(X, Y) = hₛ(X) + hₛ(Y) - hₛ(X, Y)"
 end
 
 function decomposition_string(
-        definition::MIShannon, 
-        est::EntropyDecomposition{<:MIShannon, <:DiscreteInfoEstimator{<:Shannon}}
-    )
-    return "Iₛ(X, Y) = Hₛ(X) + Hₛ(Y) - Hₛ(X, Y)";
+    definition::MIShannon,
+    est::EntropyDecomposition{<:MIShannon,<:DiscreteInfoEstimator{<:Shannon}}
+)
+    return "Iₛ(X, Y) = Hₛ(X) + Hₛ(Y) - Hₛ(X, Y)"
 end
diff --git a/src/methods/information/definitions/mutual_informations/MITsallisFuruichi.jl b/src/methods/information/definitions/mutual_informations/MITsallisFuruichi.jl
index 9f2a5f89..057b8fd0 100644
--- a/src/methods/information/definitions/mutual_informations/MITsallisFuruichi.jl
+++ b/src/methods/information/definitions/mutual_informations/MITsallisFuruichi.jl
@@ -30,15 +30,15 @@ I_q^T(X; Y) = H_q^T(X) - H_q^T(X | Y) = H_q^T(X) + H_q^T(Y) - H_q^T(X, Y),
 ```
 
 where ``H^T(\\cdot)`` and ``H^T(\\cdot, \\cdot)`` are the marginal and joint Tsallis
-entropies, and `q` is the [`Tsallis`](@ref)-parameter.
+entropies, and `q` is the [`Tsallis`](@extref ComplexityMeasures)-parameter.
 
 ## Estimation
 
-- [Example 1](@ref example_MITsallisFuruichi_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@ref) outcome space.
-- [Example 2](@ref example_MITsallisFuruichi_EntropyDecomposition_LeonenkoProzantoSavani): [`EntropyDecomposition`](@ref) with [`LeonenkoProzantoSavani`](@ref) estimator.
-- [Example 3](@ref example_MITsallisFuruichi_EntropyDecomposition_Dispersion): [`EntropyDecomposition`](@ref) with [`Dispersion`](@ref)
+- [Example 1](@ref example_MITsallisFuruichi_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures) outcome space.
+- [Example 2](@ref example_MITsallisFuruichi_EntropyDecomposition_LeonenkoProzantoSavani): [`EntropyDecomposition`](@ref) with [`LeonenkoProzantoSavani`](@extref ComplexityMeasures) estimator.
+- [Example 3](@ref example_MITsallisFuruichi_EntropyDecomposition_Dispersion): [`EntropyDecomposition`](@ref) with [`Dispersion`](@extref ComplexityMeasures)
 """
-Base.@kwdef struct MITsallisFuruichi{B, Q} <: MutualInformation
+Base.@kwdef struct MITsallisFuruichi{B,Q} <: MutualInformation
     base::B = 2
     q::Q = 1.5
 end
@@ -51,11 +51,11 @@ function association(est::JointProbabilities{<:MITsallisFuruichi}, x, y)
     return association(est.definition, probs)
 end
 
-function association(definition::MITsallisFuruichi, pxy::Probabilities{T, 2}) where T
+function association(definition::MITsallisFuruichi, pxy::Probabilities{T,2}) where T
     (; base, q) = definition
 
-    px = marginal(pxy, dims = 1)
-    py = marginal(pxy, dims = 2)
+    px = marginal(pxy, dims=1)
+    py = marginal(pxy, dims=2)
 
     mi = 0.0
     for i in eachindex(px.p)
@@ -64,19 +64,19 @@ function association(definition::MITsallisFuruichi, pxy::Probabilities{T, 2}) wh
             mi += pxyᵢⱼ^q / (px[i]^(q - 1) * py[j]^(q - 1))
         end
     end
-    mi = (1 / (q - 1) * (1 - mi) / (1-q))
+    mi = (1 / (q - 1) * (1 - mi) / (1 - q))
     return _convert_logunit(mi, ℯ, base)
 end
 
 
 
-function association(est::EntropyDecomposition{<:MITsallisFuruichi, <:DifferentialInfoEstimator{<:Tsallis}}, x, y)
+function association(est::EntropyDecomposition{<:MITsallisFuruichi,<:DifferentialInfoEstimator{<:Tsallis}}, x, y)
     HX, HY, HXY = marginal_entropies_mi3h_differential(est, x, y)
     mi = HX + HY - HXY
     return mi
 end
 
-function association(est::EntropyDecomposition{<:MITsallisFuruichi, <:DiscreteInfoEstimator{<:Tsallis}}, x, y)
+function association(est::EntropyDecomposition{<:MITsallisFuruichi,<:DiscreteInfoEstimator{<:Tsallis}}, x, y)
     HX, HY, HXY = marginal_entropies_mi3h_discrete(est, x, y)
     mi = HX + HY - HXY
     return mi
@@ -87,9 +87,9 @@ end
 # Pretty printing for decomposition estimators.
 # ------------------------------------------------
 function decomposition_string(definition::MITsallisFuruichi, est::DiscreteInfoEstimator{<:Tsallis})
-    return "MI_TF(X, Y) = H_T(X) + H_T(Y) - H_T(X, Y)";
+    return "MI_TF(X, Y) = H_T(X) + H_T(Y) - H_T(X, Y)"
 end
 
 function decomposition_string(definition::MITsallisFuruichi, est::DifferentialInfoEstimator{<:Tsallis})
-    return "MI_TF(X, Y) = h_T(X) + h_T(Y) - h_T(X, Y)";
+    return "MI_TF(X, Y) = h_T(X) + h_T(Y) - h_T(X, Y)"
 end
\ No newline at end of file
diff --git a/src/methods/information/definitions/mutual_informations/MITsallisMartin.jl b/src/methods/information/definitions/mutual_informations/MITsallisMartin.jl
index b82d039d..f8d3c790 100644
--- a/src/methods/information/definitions/mutual_informations/MITsallisMartin.jl
+++ b/src/methods/information/definitions/mutual_informations/MITsallisMartin.jl
@@ -30,15 +30,15 @@ I_{\\text{Martin}}^T(X, Y, q) := H_q^T(X) + H_q^T(Y) - (1 - q) H_q^T(X) H_q^T(Y)
 ```
 
 where ``H^S(\\cdot)`` and ``H^S(\\cdot, \\cdot)`` are the marginal and joint Shannon
-entropies, and `q` is the [`Tsallis`](@ref)-parameter.
+entropies, and `q` is the [`Tsallis`](@extref ComplexityMeasures)-parameter.
 
 ## Estimation
 
-- [Example 1](@ref example_MITsallisMartin_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@ref) outcome space.
-- [Example 2](@ref example_MITsallisMartin_EntropyDecomposition_LeonenkoProzantoSavani): [`EntropyDecomposition`](@ref) with [`LeonenkoProzantoSavani`](@ref) estimator.
-- [Example 3](@ref example_MITsallisMartin_EntropyDecomposition_OrdinalPatterns): [`EntropyDecomposition`](@ref) with [`OrdinalPatterns`](@ref) outcome space.
+- [Example 1](@ref example_MITsallisMartin_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures) outcome space.
+- [Example 2](@ref example_MITsallisMartin_EntropyDecomposition_LeonenkoProzantoSavani): [`EntropyDecomposition`](@ref) with [`LeonenkoProzantoSavani`](@extref ComplexityMeasures) estimator.
+- [Example 3](@ref example_MITsallisMartin_EntropyDecomposition_OrdinalPatterns): [`EntropyDecomposition`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space.
 """
-Base.@kwdef struct MITsallisMartin{B, Q} <: MutualInformation
+Base.@kwdef struct MITsallisMartin{B,Q} <: MutualInformation
     base::B = 2
     q::Q = 1.5
 end
@@ -54,12 +54,12 @@ end
 
 # This is definition 3 in Martin et al. (2004), but with pᵢ replaced by the joint
 # distribution and qᵢ replaced by the product of the marginal distributions.
-function association(definition::MITsallisMartin, pxy::Probabilities{T, 2}) where T
+function association(definition::MITsallisMartin, pxy::Probabilities{T,2}) where T
     (; base, q) = definition
     # TODO: return MIShannon if q = 1? otherwise, we don't need `base`.
     q != 1 || throw(ArgumentError("`MITsallisMartin` for q=$(q) not defined."))
-    px = marginal(pxy, dims = 1)
-    py = marginal(pxy, dims = 2)
+    px = marginal(pxy, dims=1)
+    py = marginal(pxy, dims=2)
 
     mi = 0.0
     for (i, pxᵢ) in enumerate(px.p)
@@ -72,14 +72,14 @@ function association(definition::MITsallisMartin, pxy::Probabilities{T, 2}) wher
     return f * (1 - mi)
 end
 
-function association(est::EntropyDecomposition{<:MITsallisMartin, <:DifferentialInfoEstimator{<:Tsallis}}, x, y)
+function association(est::EntropyDecomposition{<:MITsallisMartin,<:DifferentialInfoEstimator{<:Tsallis}}, x, y)
     HX, HY, HXY = marginal_entropies_mi3h_differential(est, x, y)
     q = est.definition.q
     mi = HX + HY - (1 - q) * HX * HY - HXY
     return mi
 end
 
-function association(est::EntropyDecomposition{<:MITsallisMartin, <:DiscreteInfoEstimator{<:Tsallis}}, x, y)
+function association(est::EntropyDecomposition{<:MITsallisMartin,<:DiscreteInfoEstimator{<:Tsallis}}, x, y)
     HX, HY, HXY = marginal_entropies_mi3h_discrete(est, x, y)
     q = est.definition.q
     mi = HX + HY - (1 - q) * HX * HY - HXY
@@ -90,9 +90,9 @@ end
 # Pretty printing for decomposition estimators.
 # ------------------------------------------------
 function decomposition_string(definition::MITsallisMartin, est::DiscreteInfoEstimator{<:Tsallis})
-    return "MI_S(X, Y) = H_T(X) + H_T(Y) - (1 - q)*H_T(X)*H_T(Y) - H_T(X, Y)";
+    return "MI_S(X, Y) = H_T(X) + H_T(Y) - (1 - q)*H_T(X)*H_T(Y) - H_T(X, Y)"
 end
 
 function decomposition_string(definition::MITsallisMartin, est::DifferentialInfoEstimator{<:Tsallis})
-    return "MI_S(X, Y) = h_T(X) + h_T(Y) - (1 - q)*h_T(X)*H_T(Y) - h_T(X, Y)";
+    return "MI_S(X, Y) = h_T(X) + h_T(Y) - (1 - q)*h_T(X)*H_T(Y) - h_T(X, Y)"
 end
\ No newline at end of file
diff --git a/src/methods/information/definitions/short_expansion_conditional_mutual_information/short_expansion_conditional_mutual_information.jl b/src/methods/information/definitions/short_expansion_conditional_mutual_information/short_expansion_conditional_mutual_information.jl
index b8f6ad85..77337c2b 100644
--- a/src/methods/information/definitions/short_expansion_conditional_mutual_information/short_expansion_conditional_mutual_information.jl
+++ b/src/methods/information/definitions/short_expansion_conditional_mutual_information/short_expansion_conditional_mutual_information.jl
@@ -35,7 +35,7 @@ This quantity is estimated from data using one of the estimators below from the
 
 - [Example 1](@ref example_ShortExpansionConditionalMutualInformation_JointProbabilities_CodifyVariables_ValueBinning):
     Estimating [`ShortExpansionConditionalMutualInformation`](@ref) using the [`JointProbabilities`](@ref) estimator using a
-    [`CodifyVariables`](@ref) with [`ValueBinning`](@ref) discretization.
+    [`CodifyVariables`](@ref) with [`ValueBinning`](@extref ComplexityMeasures) discretization.
 """
 Base.@kwdef struct ShortExpansionConditionalMutualInformation{B} <: MultivariateInformationMeasure
     base::B = 2
@@ -51,22 +51,22 @@ max_inputs_vars(::ShortExpansionConditionalMutualInformation) = Inf
 
 # Assumes 1st dimension of `probs` corresponds to X, 2nd dimension of `probs`
 # corresponds to Y, and dimensions `3:ndims(probs)` correspond to marginals Zₖ, 
-function association(definition::SECMI, probs::Probabilities{T, N}) where {T, N}
+function association(definition::SECMI, probs::Probabilities{T,N}) where {T,N}
     @assert N >= 3
     (; base) = definition
 
-    def_mi = MIShannon(; base = base)
-    def_cmi = CMIShannon(; base = base)
+    def_mi = MIShannon(; base=base)
+    def_cmi = CMIShannon(; base=base)
 
     m = ndims(probs) - 2
-    pXY = marginal(probs, dims = 1:2)
+    pXY = marginal(probs, dims=1:2)
     mi_XY = association(def_mi, pXY)
     cmis = 0.0
     for k = 1:m
         # association(definition::CMIShannon, pxyz::Probabilities{T, 3})
         # is the call signature, so we simply replace the last variable
         # with the marginal Zₖ for each Î(X, Y | Zₖ) in the sum
-        cmis += association(def_cmi, marginal(probs, dims = (1, 2, 2 + k)))
+        cmis += association(def_cmi, marginal(probs, dims=(1, 2, 2 + k)))
     end
     return (1 - m) * mi_XY + cmis
 end
diff --git a/src/methods/information/definitions/transferentropy/TERenyiJizba.jl b/src/methods/information/definitions/transferentropy/TERenyiJizba.jl
index dec0fb26..7d48cc02 100644
--- a/src/methods/information/definitions/transferentropy/TERenyiJizba.jl
+++ b/src/methods/information/definitions/transferentropy/TERenyiJizba.jl
@@ -38,36 +38,36 @@ estimator from the list below as its input.
 
 | Estimator                      | Sub-estimator                    | Principle                    |
 | :----------------------------- | :------------------------------- | :--------------------------- |
-| [`EntropyDecomposition`](@ref) | [`LeonenkoProzantoSavani`](@ref) | Four-entropies decomposition |
-| [`EntropyDecomposition`](@ref) | [`ValueBinning`](@ref)           | Four-entropies decomposition |
-| [`EntropyDecomposition`](@ref) | [`Dispersion`](@ref)             | Four-entropies decomposition |
-| [`EntropyDecomposition`](@ref) | [`OrdinalPatterns`](@ref)        | Four-entropies decomposition |
-| [`EntropyDecomposition`](@ref) | [`UniqueElements`](@ref)         | Four-entropies decomposition |
-| [`EntropyDecomposition`](@ref) | [`TransferOperator`](@ref)       | Four-entropies decomposition |
+| [`EntropyDecomposition`](@ref) | [`LeonenkoProzantoSavani`](@extref ComplexityMeasures) | Four-entropies decomposition |
+| [`EntropyDecomposition`](@ref) | [`ValueBinning`](@extref ComplexityMeasures)           | Four-entropies decomposition |
+| [`EntropyDecomposition`](@ref) | [`Dispersion`](@extref ComplexityMeasures)             | Four-entropies decomposition |
+| [`EntropyDecomposition`](@ref) | [`OrdinalPatterns`](@extref ComplexityMeasures)        | Four-entropies decomposition |
+| [`EntropyDecomposition`](@ref) | [`UniqueElements`](@extref ComplexityMeasures)         | Four-entropies decomposition |
+| [`EntropyDecomposition`](@ref) | [`TransferOperator`](@extref ComplexityMeasures)       | Four-entropies decomposition |
 
 Any of these estimators must be given as input to a [`CMIDecomposition](@ref) estimator.
 
 ## Estimation
 
-- [Example 1](@ref example_TERenyiJizba_EntropyDecomposition_TransferOperator): [`EntropyDecomposition`](@ref) with [`TransferOperator`](@ref) outcome space.
+- [Example 1](@ref example_TERenyiJizba_EntropyDecomposition_TransferOperator): [`EntropyDecomposition`](@ref) with [`TransferOperator`](@extref ComplexityMeasures) outcome space.
 
 """
-struct TERenyiJizba{B, Q, EMB} <: TransferEntropy
+struct TERenyiJizba{B,Q,EMB} <: TransferEntropy
     base::B
     q::Q
     embedding::EMB
-    function TERenyiJizba(; base::B = 2, q::Q = 1.5, embedding::EMB = EmbeddingTE()) where {B, Q, EMB}
-        return new{B, Q, EMB}(base, q, embedding)
+    function TERenyiJizba(; base::B=2, q::Q=1.5, embedding::EMB=EmbeddingTE()) where {B,Q,EMB}
+        return new{B,Q,EMB}(base, q, embedding)
     end
 end
 
-function convert_to_cmi_estimator(est::EntropyDecomposition{<:TERenyiJizba, <:DiscreteInfoEstimator{<:Renyi}})
+function convert_to_cmi_estimator(est::EntropyDecomposition{<:TERenyiJizba,<:DiscreteInfoEstimator{<:Renyi}})
     (; definition, est, discretization, pest) = est
     base = definition.base
     return EntropyDecomposition(CMIRenyiJizba(; base), est, discretization, pest)
 end
 
-function convert_to_cmi_estimator(est::EntropyDecomposition{<:TERenyiJizba, <:DifferentialInfoEstimator{<:Renyi}})
+function convert_to_cmi_estimator(est::EntropyDecomposition{<:TERenyiJizba,<:DifferentialInfoEstimator{<:Renyi}})
     return EntropyDecomposition(CMIRenyiJizba(; est.definition.base), est.est)
 end
 
@@ -82,15 +82,15 @@ end
 # = h(t⁺, t⁻,c⁻) - h(t⁻,c⁻) - h(t⁺,s⁻,t⁻,c⁻) + h(s⁻,t⁻,c⁻)"
 
 function decomposition_string(
-        definition::TERenyiJizba, 
-        est::EntropyDecomposition{M, <:DiscreteInfoEstimator}
-    ) where M
+    definition::TERenyiJizba,
+    est::EntropyDecomposition{M,<:DiscreteInfoEstimator}
+) where M
     return "TEᵣⱼ(s → t | c) = Hᵣ(t⁺, t⁻,c⁻) - Hᵣ(t⁻,c⁻) - Hᵣ(t⁺,s⁻,t⁻,c⁻) + Hᵣ(s⁻,t⁻,c⁻)"
 end
 
 function decomposition_string(
-    definition::TERenyiJizba, 
-    est::EntropyDecomposition{M, <:DifferentialInfoEstimator}
-    ) where M
+    definition::TERenyiJizba,
+    est::EntropyDecomposition{M,<:DifferentialInfoEstimator}
+) where M
     return "TEᵣⱼ(s → t | c) = hᵣ(t⁺, t⁻,c⁻) - hᵣ(t⁻,c⁻) - hᵣ(t⁺,s⁻,t⁻,c⁻) + hᵣ(s⁻,t⁻,c⁻)"
 end
\ No newline at end of file
diff --git a/src/methods/information/definitions/transferentropy/TEShannon.jl b/src/methods/information/definitions/transferentropy/TEShannon.jl
index da82cddf..7a12d20b 100644
--- a/src/methods/information/definitions/transferentropy/TEShannon.jl
+++ b/src/methods/information/definitions/transferentropy/TEShannon.jl
@@ -32,26 +32,26 @@ are constructed using present/past values and future values, respectively.
 ## Estimation
 
 - [Example 1](@ref example_TEShannon_EntropyDecomposition_TransferOperator): 
-    [`EntropyDecomposition`](@ref) with [`TransferOperator`](@ref) outcome space.
+    [`EntropyDecomposition`](@ref) with [`TransferOperator`](@extref ComplexityMeasures) outcome space.
 - [Example 2](@ref example_TEShannon_SymbolicTransferEntropy): Estimation using the
     [`SymbolicTransferEntropy`](@ref) estimator.
 """
-struct TEShannon{B, EMB} <: TransferEntropy
+struct TEShannon{B,EMB} <: TransferEntropy
     base::B
     embedding::EMB
-    function TEShannon(; base::B = 2, embedding::EMB = EmbeddingTE()) where {B, EMB}
-        return new{B, EMB}(base, embedding)
+    function TEShannon(; base::B=2, embedding::EMB=EmbeddingTE()) where {B,EMB}
+        return new{B,EMB}(base, embedding)
     end
     # TODO: add constructor that automatically determines the embedding.
 end
 
-function convert_to_cmi_estimator(est::EntropyDecomposition{<:TEShannon, <:DiscreteInfoEstimator})
+function convert_to_cmi_estimator(est::EntropyDecomposition{<:TEShannon,<:DiscreteInfoEstimator})
     (; definition, est, discretization, pest) = est
     base = definition.base
     return EntropyDecomposition(CMIShannon(; base), est, discretization, pest)
 end
 
-function convert_to_cmi_estimator(est::EntropyDecomposition{<:TEShannon, <:DifferentialInfoEstimator})
+function convert_to_cmi_estimator(est::EntropyDecomposition{<:TEShannon,<:DifferentialInfoEstimator})
     return EntropyDecomposition(CMIShannon(; est.definition.base), est.est)
 end
 
@@ -81,30 +81,30 @@ end
 # = h(t⁺, t⁻,c⁻) - h(t⁻,c⁻) - h(t⁺,s⁻,t⁻,c⁻) + h(s⁻,t⁻,c⁻)"
 
 function decomposition_string(
-        definition::TEShannon, 
-        est::EntropyDecomposition{M, <:DiscreteInfoEstimator{<:Shannon}}
-    ) where M
+    definition::TEShannon,
+    est::EntropyDecomposition{M,<:DiscreteInfoEstimator{<:Shannon}}
+) where M
     return "TEₛ(s → t | c) = Hₛ(t⁺, t⁻,c⁻) - Hₛ(t⁻,c⁻) - Hₛ(t⁺,s⁻,t⁻,c⁻) + Hₛ(s⁻,t⁻,c⁻)"
 end
 
 function decomposition_string(
-    definition::TEShannon, 
-    est::EntropyDecomposition{M, <:DifferentialInfoEstimator{<:Shannon}}
-    ) where M
+    definition::TEShannon,
+    est::EntropyDecomposition{M,<:DifferentialInfoEstimator{<:Shannon}}
+) where M
     return "TEₛ(s → t | c) = hₛ(t⁺, t⁻,c⁻) - hₛ(t⁻,c⁻) - hₛ(t⁺,s⁻,t⁻,c⁻) + hₛ(s⁻,t⁻,c⁻)"
 end
 
 function decomposition_string(
-        definition::TEShannon, 
-        est::MIDecomposition{M, <:MutualInformationEstimator{<:MIShannon}}
-    ) where M
+    definition::TEShannon,
+    est::MIDecomposition{M,<:MutualInformationEstimator{<:MIShannon}}
+) where M
     return "TEₛ(s → t | c) = Iₛ(t⁺; s⁻, t⁻, c⁻) - Iₛ(t⁺; t⁻, c⁻)"
 end
 
 
 function decomposition_string(
-        definition::TEShannon, 
-        est::CMIDecomposition{M, <:ConditionalMutualInformationEstimator{<:CMIShannon}}
-    ) where M
+    definition::TEShannon,
+    est::CMIDecomposition{M,<:ConditionalMutualInformationEstimator{<:CMIShannon}}
+) where M
     return "TEₛ(s → t | c) = Iₛ(t⁺; s⁻ | t⁻, c⁻)"
 end
diff --git a/src/methods/information/estimators/JointProbabilities.jl b/src/methods/information/estimators/JointProbabilities.jl
index 9b972ba5..b28846c9 100644
--- a/src/methods/information/estimators/JointProbabilities.jl
+++ b/src/methods/information/estimators/JointProbabilities.jl
@@ -42,14 +42,14 @@ Works for any [`OutcomeSpace`](@ref) that implements [`codify`](@ref).
     Pick your estimator according to your needs.
 
 See also: [`Counts`](@ref), [`Probabilities`](@ref), [`ProbabilitiesEstimator`](@ref),
-[`OutcomeSpace`](@ref), [`DiscreteInfoEstimator`](@ref).
+[`OutcomeSpace`](@ref), [`DiscreteInfoEstimator`](@extref ComplexityMeasures).
 """
-struct JointProbabilities{M <: MultivariateInformationMeasure, O, P} <: MultivariateInformationMeasureEstimator{M}
+struct JointProbabilities{M<:MultivariateInformationMeasure,O,P} <: MultivariateInformationMeasureEstimator{M}
     definition::M # API from complexity measures: definition must be the first field of the infoestimator.
     discretization::O
     pest::P # Not exposed to user for now.
 
-    function JointProbabilities(def::M, disc::D, pest = RelativeAmount()) where {M, D}
-        new{M, D, typeof(pest)}(def, disc, pest)
+    function JointProbabilities(def::M, disc::D, pest=RelativeAmount()) where {M,D}
+        new{M,D,typeof(pest)}(def, disc, pest)
     end
 end
diff --git a/src/methods/information/estimators/codify_marginals.jl b/src/methods/information/estimators/codify_marginals.jl
index 4b02603a..5f00f4b0 100644
--- a/src/methods/information/estimators/codify_marginals.jl
+++ b/src/methods/information/estimators/codify_marginals.jl
@@ -1,5 +1,5 @@
 using ComplexityMeasures
-export codified_marginals 
+export codified_marginals
 
 """
     codified_marginals(o::OutcomeSpace, x::VectorOrStateSpaceSet...)
@@ -18,23 +18,23 @@ to handle discretization.
 
 ## Supported estimators
 
-- [`ValueBinning`](@ref). Bin visitation frequencies are counted in the joint space `XY`,
+- [`ValueBinning`](@extref ComplexityMeasures). Bin visitation frequencies are counted in the joint space `XY`,
     then marginal visitations are obtained from the joint bin visits.
     This behaviour is the same for both [`FixedRectangularBinning`](@ref) and
     [`RectangularBinning`](@ref) (which adapts the grid to the data).
     When using [`FixedRectangularBinning`](@ref), the range along the first dimension
     is used as a template for all other dimensions.
-- [`OrdinalPatterns`](@ref). Each timeseries is separately [`codify`](@ref)-ed by 
+- [`OrdinalPatterns`](@extref ComplexityMeasures). Each timeseries is separately [`codify`](@ref)-ed by 
     embedding the timeseries, then sequentially encoding the ordinal patterns of 
     the embedding vectors.
-- [`Dispersion`](@ref). Each timeseries is separately [`codify`](@ref)-ed by 
+- [`Dispersion`](@extref ComplexityMeasures). Each timeseries is separately [`codify`](@ref)-ed by 
     embedding the timeseries, then sequentially encoding the embedding vectors
     according to their dispersion pattern (which for each embedding vector is computed
     relative to all other embedding vectors).
 - [`CosineSimilarityBinning`](@ref). Each timeseries is separately [`codify`](@ref)-ed
     by embedding the timeseries, the encoding the embedding points in a 
     in a sequential manner according to the cosine similarity of the embedding vectors.
-- [`UniqueElements`](@ref). Each timeseries is [`codify`](@ref)-ed according to 
+- [`UniqueElements`](@extref ComplexityMeasures). Each timeseries is [`codify`](@ref)-ed according to 
     its unique values (i.e. each unique element gets assigned a specific integer).
 
 More implementations are possible.
@@ -72,8 +72,8 @@ end
 # TODO: maybe construct a convenience wrapper where the user can avoid constructing the
 # joint space, for performance benefits (but increased bias).
 function codify_marginal(
-        o::ValueBinning{<:FixedRectangularBinning{D}},
-        x::AbstractVector) where D
+    o::ValueBinning{<:FixedRectangularBinning{D}},
+    x::AbstractVector) where D
     range = first(o.binning.ranges)
     ϵmin = minimum(range)
     ϵmax = maximum(range)
@@ -100,7 +100,7 @@ function codified_marginals(o::ValueBinning{<:RectangularBinning}, x::VectorOrSt
     s = 1
     encodings = Vector{Vector}(undef, 0)
     for (i, cidx) in enumerate(idxs)
-        variable_subset = s:(s + cidx - 1)
+        variable_subset = s:(s+cidx-1)
         s += cidx
         y = @views joint_bins[:, variable_subset]
         for j in size(y, 2)
@@ -113,7 +113,7 @@ end
 
 # A version of `cartesian_bin_index` that directly returns the joint bin encoding
 # instead of converting it to a cartesian index.
-function encode_as_tuple(e::RectangularBinEncoding, point::SVector{D, T}) where {D, T}
+function encode_as_tuple(e::RectangularBinEncoding, point::SVector{D,T}) where {D,T}
     ranges = e.ranges
     if e.precise
         # Don't know how to make this faster unfurtunately...
diff --git a/src/methods/information/estimators/conditional_mutual_info_estimators/FPVP.jl b/src/methods/information/estimators/conditional_mutual_info_estimators/FPVP.jl
index a90b87d6..b19291ef 100644
--- a/src/methods/information/estimators/conditional_mutual_info_estimators/FPVP.jl
+++ b/src/methods/information/estimators/conditional_mutual_info_estimators/FPVP.jl
@@ -12,7 +12,7 @@ export FPVP
 The Frenzel-Pompe-Vejmelka-Paluš (or `FPVP` for short)
 [`ConditionalMutualInformationEstimator`](@ref) is used to estimate the
 conditional mutual information using a `k`-th nearest neighbor approach that is
-analogous to that of the [`KraskovStögbauerGrassberger1`](@ref) mutual information
+analogous to that of the [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) mutual information
 estimator from [Frenzel2007](@citet) and [Vejmelka2008](@citet).
 
 `k` is the number of nearest neighbors. `w` is the Theiler window, which controls the
@@ -33,7 +33,7 @@ number of temporal neighbors that are excluded during neighbor searches.
 - [Example 1](@ref example_CMIShannon_FPVP): Estimating [`CMIShannon`](@ref)
 
 """
-struct FPVP{M <: ConditionalMutualInformation, MJ, MM} <: ConditionalMutualInformationEstimator{M}
+struct FPVP{M<:ConditionalMutualInformation,MJ,MM} <: ConditionalMutualInformationEstimator{M}
     definition::M
     k::Int
     w::Int
@@ -41,7 +41,7 @@ struct FPVP{M <: ConditionalMutualInformation, MJ, MM} <: ConditionalMutualInfor
     metric_marginals::MM
 end
 
-function FPVP(definition = CMIShannon(); k = 1, w = 0)
+function FPVP(definition=CMIShannon(); k=1, w=0)
     # Metrics shouldn't be modified by the user.
     metric_joint = Chebyshev()
     metric_marginals = Chebyshev()
diff --git a/src/methods/information/estimators/conditional_mutual_info_estimators/Rahimzamani.jl b/src/methods/information/estimators/conditional_mutual_info_estimators/Rahimzamani.jl
index a86268aa..88552e2f 100644
--- a/src/methods/information/estimators/conditional_mutual_info_estimators/Rahimzamani.jl
+++ b/src/methods/information/estimators/conditional_mutual_info_estimators/Rahimzamani.jl
@@ -18,7 +18,7 @@ for data that can be mixtures of discrete and continuous data [Rahimzamani2018](
 
 ## Description
 
-This estimator is very similar to the [`GaoKannanOhViswanath`](@ref) mutual information
+This estimator is very similar to the [`GaoKannanOhViswanath`](@extref ComplexityMeasures) mutual information
 estimator, but has been expanded to the conditional mutual information case.
 
 `k` is the number of nearest neighbors. `w` is the Theiler window, which controls the
@@ -36,14 +36,14 @@ association(Rahimzamani(; k = 10), x, z, y) # should be near 0 (and can be negat
 ```
 
 """
-struct Rahimzamani{M <: ConditionalMutualInformation, ME} <: ConditionalMutualInformationEstimator{M}
+struct Rahimzamani{M<:ConditionalMutualInformation,ME} <: ConditionalMutualInformationEstimator{M}
     definition::M
     k::Int
     w::Int
     metric::ME
 end
 
-function Rahimzamani(definition = CMIShannon(); k = 1, w = 0)
+function Rahimzamani(definition=CMIShannon(); k=1, w=0)
     # Metric shouldn't be modified by the user.
     metric = Chebyshev()
     return Rahimzamani(definition, k, w, metric)
@@ -75,7 +75,7 @@ function association(est::Rahimzamani{<:CMIShannon}, x, y, z)
         # I assume ρ_{i, xy} is the distance in the *joint* space.
         # ... but isn't this just the FPVP estimator?
         dmax = ds_joint[i]
-        k̂ = dmax == 0 ? inrangecount(tree_joint, joint[i], 0.0) - 1  : k
+        k̂ = dmax == 0 ? inrangecount(tree_joint, joint[i], 0.0) - 1 : k
         condmi += digamma(k̂)
         condmi -= log(inrangecount(tree_xz, XZ[i], dmax))
         condmi -= log(inrangecount(tree_yz, YZ[i], dmax))
diff --git a/src/methods/information/estimators/decomposition/EntropyDecomposition.jl b/src/methods/information/estimators/decomposition/EntropyDecomposition.jl
index 5b6a5055..17f11dcc 100644
--- a/src/methods/information/estimators/decomposition/EntropyDecomposition.jl
+++ b/src/methods/information/estimators/decomposition/EntropyDecomposition.jl
@@ -25,14 +25,14 @@ per variable/column and each column is encoded into integers using [`codify`](@r
 
 The entropy terms are estimated using `est`, and then combined to form the final 
 estimate of `definition`. No bias correction is applied.
-If `est` is a [`DifferentialInfoEstimator`](@ref), then `discretization` and `pest` 
-are ignored. If `est` is a [`DiscreteInfoEstimator`](@ref), then `discretization` and a
+If `est` is a [`DifferentialInfoEstimator`](@extref ComplexityMeasures), then `discretization` and `pest` 
+are ignored. If `est` is a [`DiscreteInfoEstimator`](@extref ComplexityMeasures), then `discretization` and a
 probabilities estimator `pest` must also be provided (default to `RelativeAmount`, 
 which uses naive plug-in probabilities).
 
 ## Compatible differential information estimators
 
-If using the first signature, any compatible [`DifferentialInfoEstimator`](@ref) can be 
+If using the first signature, any compatible [`DifferentialInfoEstimator`](@extref ComplexityMeasures) can be 
 used.
 
 ## Compatible outcome spaces for discrete estimation
@@ -42,10 +42,10 @@ Note that not all outcome spaces will work with all measures.
 
 | Estimator                         | Principle                     |
 | :-------------------------------- | :---------------------------- |
-| [`UniqueElements`](@ref)          | Count of unique elements      |
-| [`ValueBinning`](@ref)            | Binning (histogram)           |
-| [`OrdinalPatterns`](@ref)         | Ordinal patterns              |
-| [`Dispersion`](@ref)              | Dispersion patterns           |
+| [`UniqueElements`](@extref ComplexityMeasures)          | Count of unique elements      |
+| [`ValueBinning`](@extref ComplexityMeasures)            | Binning (histogram)           |
+| [`OrdinalPatterns`](@extref ComplexityMeasures)         | Ordinal patterns              |
+| [`Dispersion`](@extref ComplexityMeasures)              | Dispersion patterns           |
 | [`BubbleSortSwaps`](@ref)         | Sorting complexity            |
 | [`CosineSimilarityBinning`](@ref) | Cosine similarities histogram |
 
@@ -77,48 +77,48 @@ of entropies using the `Kraskov(Shannon(base = ℯ))` Shannon entropy estimator,
 
 ## Discrete entropy decomposition 
 
-The second signature is for discrete estimation using [`DiscreteInfoEstimator`](@ref)s,
+The second signature is for discrete estimation using [`DiscreteInfoEstimator`](@extref ComplexityMeasures)s,
 for example [`PlugIn`](@ref). The given `discretization` scheme (typically an 
 [`OutcomeSpace`](@ref)) controls how the joint/marginals are discretized, and the
 probabilities estimator `pest` controls how probabilities are estimated from counts.
 
 !!! note "Bias"
-    Like for [`DifferentialInfoEstimator`](@ref), using a dedicated estimator 
+    Like for [`DifferentialInfoEstimator`](@extref ComplexityMeasures), using a dedicated estimator 
     for the measure in question will be more reliable than using a decomposition
     estimate. Here's how different `discretization`s are applied:
 
-    - [`ValueBinning`](@ref). Bin visitation frequencies are counted in the joint space
+    - [`ValueBinning`](@extref ComplexityMeasures). Bin visitation frequencies are counted in the joint space
         `XY`, then marginal visitations are obtained from the joint bin visits.
         This behaviour is the same for both [`FixedRectangularBinning`](@ref) and
         [`RectangularBinning`](@ref) (which adapts the grid to the data).
         When using [`FixedRectangularBinning`](@ref), the range along the first dimension
         is used as a template for all other dimensions. This is a bit slower than naively 
         binning each marginal, but lessens bias.
-    - [`OrdinalPatterns`](@ref). Each timeseries is separately [`codify`](@ref)-ed
+    - [`OrdinalPatterns`](@extref ComplexityMeasures). Each timeseries is separately [`codify`](@ref)-ed
         according to its ordinal pattern (no bias correction).
-    - [`Dispersion`](@ref). Each timeseries is separately [`codify`](@ref)-ed according
+    - [`Dispersion`](@extref ComplexityMeasures). Each timeseries is separately [`codify`](@ref)-ed according
         to its dispersion pattern  (no bias correction).
 
 ## Examples
 
 - [Example 1](@ref example_MIShannon_EntropyDecomposition_Jackknife_ValueBinning):
     [`MIShannon`](@ref) estimation using decomposition into discrete [`Shannon`](@ref)
-    entropy estimated using [`CodifyVariables`](@ref) with [`ValueBinning`](@ref).
+    entropy estimated using [`CodifyVariables`](@ref) with [`ValueBinning`](@extref ComplexityMeasures).
 - [Example 2](@ref example_MIShannon_EntropyDecomposition_BubbleSortSwaps):
     [`MIShannon`](@ref) estimation using decomposition into discrete [`Shannon`](@ref)
     entropy estimated using [`CodifyVariables`](@ref) with [`BubbleSortSwaps`](@ref).
 - [Example 3](@ref example_MIShannon_EntropyDecomposition_Kraskov):
     [`MIShannon`](@ref) estimation using decomposition into differental [`Shannon`](@ref)
-    entropy estimated using the [`Kraskov`](@ref) estimator.
+    entropy estimated using the [`Kraskov`](@extref ComplexityMeasures) estimator.
 
 See also: [`MutualInformationEstimator`](@ref), [`MultivariateInformationMeasure`](@ref).
 """
 struct EntropyDecomposition{
-        M <: MultivariateInformationMeasure, 
-        E <: InformationMeasureEstimator, 
-        D <: Union{Discretization, Nothing}, 
-        P <: Union{ProbabilitiesEstimator, Nothing}
-        } <: DecompositionEstimator{M}
+    M<:MultivariateInformationMeasure,
+    E<:InformationMeasureEstimator,
+    D<:Union{Discretization,Nothing},
+    P<:Union{ProbabilitiesEstimator,Nothing}
+} <: DecompositionEstimator{M}
     definition::M # extend API from complexity measures: definition must be the first field of the info estimator.
     est::E # The estimator + measure which `definition` is decomposed into.
     discretization::D # `Nothing` if `est` is a `DifferentialInfoEstimator`.
@@ -126,26 +126,26 @@ struct EntropyDecomposition{
 
 
     function EntropyDecomposition(
-        definition::MultivariateInformationMeasure, 
+        definition::MultivariateInformationMeasure,
         est::DifferentialInfoEstimator)
         M = typeof(definition)
         E = typeof(est)
         verify_decomposition_entropy_type(definition, est)
-        return new{M, E, Nothing, Nothing}(definition, est, nothing, nothing)
+        return new{M,E,Nothing,Nothing}(definition, est, nothing, nothing)
     end
 
     function EntropyDecomposition(
-            definition::MultivariateInformationMeasure, 
-            est::DiscreteInfoEstimator, 
-            discretization::D,
-            pest::ProbabilitiesEstimator = RelativeAmount(),
-        ) where {D}
+        definition::MultivariateInformationMeasure,
+        est::DiscreteInfoEstimator,
+        discretization::D,
+        pest::ProbabilitiesEstimator=RelativeAmount(),
+    ) where {D}
         M = typeof(definition)
         E = typeof(est)
         P = typeof(pest)
         verify_decomposition_entropy_type(definition, est)
 
-        return new{M, E, D, P}(definition, est, discretization, pest)
+        return new{M,E,D,P}(definition, est, discretization, pest)
     end
 end
 
@@ -160,15 +160,15 @@ Check that we can actually decompose the `definition` into `est.definition`. The
 default is to do nothing. Certain definitions  may override (e.g. `CMIRenyiJizba` does so).
 """
 function verify_decomposition_entropy_type(
-        definition::MultivariateInformationMeasure, 
-        est::Union{DiscreteInfoEstimator, DifferentialInfoEstimator})
+    definition::MultivariateInformationMeasure,
+    est::Union{DiscreteInfoEstimator,DifferentialInfoEstimator})
 end
 
 
 # ----------------------------------------------------------------------------------------
 # Custom pretty printing for discrete entropy estimators, since it has more field.
 # ----------------------------------------------------------------------------------------
-function summary_strings(est::EntropyDecomposition{<:M, <:DiscreteInfoEstimator}) where M
+function summary_strings(est::EntropyDecomposition{<:M,<:DiscreteInfoEstimator}) where M
     return [
         "Measure to be decomposed",
         "Estimator for decomposed components",
@@ -177,7 +177,7 @@ function summary_strings(est::EntropyDecomposition{<:M, <:DiscreteInfoEstimator}
     ]
 end
 
-function summary_types(est::EntropyDecomposition{<:M, <:DiscreteInfoEstimator}) where M
+function summary_types(est::EntropyDecomposition{<:M,<:DiscreteInfoEstimator}) where M
     return [
         typeof(est.definition),
         typeof(est.est),
@@ -186,7 +186,7 @@ function summary_types(est::EntropyDecomposition{<:M, <:DiscreteInfoEstimator})
     ]
 end
 
-function measure_colors(est::EntropyDecomposition{<:M, <:DiscreteInfoEstimator}) where M
+function measure_colors(est::EntropyDecomposition{<:M,<:DiscreteInfoEstimator}) where M
     return [
         :light_red,
         :light_green,
@@ -195,7 +195,7 @@ function measure_colors(est::EntropyDecomposition{<:M, <:DiscreteInfoEstimator})
     ]
 end
 
-function info_colors(est::EntropyDecomposition{<:M, <:DiscreteInfoEstimator}) where M
+function info_colors(est::EntropyDecomposition{<:M,<:DiscreteInfoEstimator}) where M
     return [
         :red,
         :green,
diff --git a/src/methods/information/estimators/decomposition/MIDecomposition.jl b/src/methods/information/estimators/decomposition/MIDecomposition.jl
index 294cdfe4..a7c384bf 100644
--- a/src/methods/information/estimators/decomposition/MIDecomposition.jl
+++ b/src/methods/information/estimators/decomposition/MIDecomposition.jl
@@ -21,11 +21,11 @@ value of the measure.
 
 - [Example 1](@ref example_CMIShannon_MIDecomposition): Estimating [`CMIShannon`](@ref)
     using a decomposition into [`MIShannon`](@ref) terms using 
-    the [`KraskovStögbauerGrassberger1`](@ref) mutual information estimator.
+    the [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) mutual information estimator.
 
 See also: [`MultivariateInformationMeasureEstimator`](@ref).
 """
-struct MIDecomposition{M <: MultivariateInformationMeasure, E} <: DecompositionEstimator{M}
+struct MIDecomposition{M<:MultivariateInformationMeasure,E} <: DecompositionEstimator{M}
     definition::M # extend API from complexity measures: definition must be the first field of the info estimator.
     est::E # The MI estimator + measure which `definition` is decomposed into.
 end
diff --git a/src/methods/information/estimators/mutual_info_estimators/GaoKannanOhViswanath.jl b/src/methods/information/estimators/mutual_info_estimators/GaoKannanOhViswanath.jl
index fe56ca9f..9ee81101 100644
--- a/src/methods/information/estimators/mutual_info_estimators/GaoKannanOhViswanath.jl
+++ b/src/methods/information/estimators/mutual_info_estimators/GaoKannanOhViswanath.jl
@@ -40,8 +40,8 @@ variables (by quantization) or making it continuous by adding a small Gaussian n
 
 !!! warn "Implementation note"
     In [GaoKannanOhViswanath2017](@citet), they claim (roughly speaking) that the estimator
-    reduces to the [`KraskovStögbauerGrassberger1`](@ref) estimator for continuous-valued data.
-    However, [`KraskovStögbauerGrassberger1`](@ref) uses the digamma function, while `GaoKannanOhViswanath`
+    reduces to the [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator for continuous-valued data.
+    However, [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) uses the digamma function, while `GaoKannanOhViswanath`
     uses the logarithm instead, so the estimators are not exactly equivalent
     for continuous data.
 
@@ -51,7 +51,7 @@ variables (by quantization) or making it continuous by adding a small Gaussian n
     `k`-th nearest distances among the two marginal spaces, which are in general not the
     same as the `k`-th neighbor distance in the joint space (unless both marginals are
     univariate). Therefore, our implementation here differs slightly from algorithm 1 in
-    `GaoKannanOhViswanath`. We have modified it in a way that mimics [`KraskovStögbauerGrassberger1`](@ref) for
+    `GaoKannanOhViswanath`. We have modified it in a way that mimics [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) for
     continous data. Note that because of using the `log` function instead of `digamma`,
     there will be slight differences between the methods. See the source code for more
     details.
@@ -72,13 +72,13 @@ x = rand(rng, 10000); y = rand(rng, 10000)
 association(GaoKannanOhViswanath(; k = 10), x, y) # should be near 0 (and can be negative)
 ```
 """
-struct GaoKannanOhViswanath{M <: MutualInformation} <: MutualInformationEstimator{M}
+struct GaoKannanOhViswanath{M<:MutualInformation} <: MutualInformationEstimator{M}
     definition::M
     k::Int
-    w::Int 
+    w::Int
 end
 
-function GaoKannanOhViswanath(definition = MIShannon(); k = 1, w = 0)
+function GaoKannanOhViswanath(definition=MIShannon(); k=1, w=0)
     return GaoKannanOhViswanath(definition, k, w)
 end
 # TODO: We here extend the estimator to multiple variables (i.e. the multi-information),
diff --git a/src/methods/information/estimators/transfer_entropy_estimators/Hilbert.jl b/src/methods/information/estimators/transfer_entropy_estimators/Hilbert.jl
index 99424a34..19dc5fb4 100644
--- a/src/methods/information/estimators/transfer_entropy_estimators/Hilbert.jl
+++ b/src/methods/information/estimators/transfer_entropy_estimators/Hilbert.jl
@@ -30,7 +30,7 @@ obtained by first applying the Hilbert transform to each signal, then extracting
 phases/amplitudes of the resulting complex numbers [Palus2014](@cite). Original time series are
 thus transformed to instantaneous phase/amplitude time series. Transfer
 entropy is then estimated using the provided `est` on those phases/amplitudes (use e.g.
-[`ValueBinning`](@ref), or [`OrdinalPatterns`](@ref)).
+[`ValueBinning`](@extref ComplexityMeasures), or [`OrdinalPatterns`](@extref ComplexityMeasures)).
 
 !!! info
     Details on estimation of the transfer entropy (conditional mutual information)
@@ -47,9 +47,9 @@ struct Hilbert{M} <: TransferEntropyEstimator{M}
     cond::InstantaneousSignalProperty
 
     function Hilbert(est::M;
-            source::InstantaneousSignalProperty = Phase(),
-            target::InstantaneousSignalProperty = Phase(),
-            cond::InstantaneousSignalProperty = Phase()) where M
+        source::InstantaneousSignalProperty=Phase(),
+        target::InstantaneousSignalProperty=Phase(),
+        cond::InstantaneousSignalProperty=Phase()) where M
         new{M}(est, source, target, cond)
     end
 end
@@ -105,6 +105,6 @@ function association(est::Hilbert, source, target, cond)
     else
         throw(ArgumentError("est.cond must be either Phase or Amplitude instance"))
     end
-    
+
     association(est.est, s, t, c)
 end
diff --git a/src/methods/information/estimators/transfer_entropy_estimators/SymbolicTransferEntropy.jl b/src/methods/information/estimators/transfer_entropy_estimators/SymbolicTransferEntropy.jl
index 9437ed18..888f1dc0 100644
--- a/src/methods/information/estimators/transfer_entropy_estimators/SymbolicTransferEntropy.jl
+++ b/src/methods/information/estimators/transfer_entropy_estimators/SymbolicTransferEntropy.jl
@@ -16,7 +16,7 @@ A convenience estimator for symbolic transfer entropy [Staniek2008](@cite).
 
 [Symbolic transfer entropy](https://journals.aps.org/prl/abstract/10.1103/PhysRevLett.100.158101)
 consists of two simple steps. First, the input time series are encoded using [`codify`](@ref) with
-the [`CodifyVariables`](@ref) discretization and the [`OrdinalPatterns`](@ref) outcome space. This 
+the [`CodifyVariables`](@ref) discretization and the [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space. This 
 transforms the input time series into integer time series. Transfer entropy entropy is then 
 estimated from the encoded time series by applying  
 
@@ -34,8 +34,8 @@ struct SymbolicTransferEntropy{M} <: TransferEntropyEstimator{M}
     lt::Function
 end
 
-function SymbolicTransferEntropy(definition::M = TEShannon(); 
-        m = 3, τ = 1, lt = ComplexityMeasures.isless_rand) where M
+function SymbolicTransferEntropy(definition::M=TEShannon();
+    m=3, τ=1, lt=ComplexityMeasures.isless_rand) where M
     return SymbolicTransferEntropy{M}(definition, m, τ, lt)
 end
 
@@ -43,7 +43,7 @@ function association(est::SymbolicTransferEntropy{<:TEShannon}, x::AbstractVecto
     (; m, τ, lt) = est
     discretization = CodifyVariables(OrdinalPatterns(; m, τ, lt))
 
-    x̂ = (codify(discretization, xᵢ) for xᵢ in x) 
+    x̂ = (codify(discretization, xᵢ) for xᵢ in x)
 
     te_definition = est.definition
     embedding = te_definition.embedding
@@ -55,9 +55,9 @@ function association(est::SymbolicTransferEntropy{<:TEShannon}, x::AbstractVecto
 
     # We have already encoded the marginals, so when computing CMI, we can 
     # simply use `UniqueElements`.
-    cmi_def = CMIShannon(; base = est.definition.base)
+    cmi_def = CMIShannon(; base=est.definition.base)
     disc = CodifyVariables(UniqueElements())
-    
+
     est_unique = JointProbabilities(cmi_def, disc)
-    return association(est_unique, T⁺, S,  StateSpaceSet(T, C))
+    return association(est_unique, T⁺, S, StateSpaceSet(T, C))
 end

From 0cafac81f44f80b5d07e6417bd9c74090bed8d97 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 10:01:41 +0200
Subject: [PATCH 03/24] update style

---
 docs/style.jl | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/docs/style.jl b/docs/style.jl
index 168f16ee..691fffa7 100644
--- a/docs/style.jl
+++ b/docs/style.jl
@@ -18,11 +18,11 @@ Base.iterate(c::CyclicContainer, i = 1) = iterate(c.c, i)
 
 COLORSCHEME = [
     "#7143E0",
-    "#0A9A84",
     "#191E44",
+    "#0A9A84",
     "#AF9327",
-    "#701B80",
-    "#2E6137",
+    "#791457",
+    "#6C768C",
 ]
 
 COLORS = CyclicContainer(COLORSCHEME)

From d4e463fc6df61bd4b7930cb53a8fb4f0b81ce05d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 10:07:41 +0200
Subject: [PATCH 04/24] formatting

---
 docs/build_docs_with_style.jl | 134 +++++++++++++++++-----------------
 1 file changed, 68 insertions(+), 66 deletions(-)

diff --git a/docs/build_docs_with_style.jl b/docs/build_docs_with_style.jl
index 33827955..288d5843 100644
--- a/docs/build_docs_with_style.jl
+++ b/docs/build_docs_with_style.jl
@@ -1,40 +1,40 @@
 CI = get(ENV, "CI", nothing) == "true" || get(ENV, "GITHUB_TOKEN", nothing) !== nothing
 
- import Pkg
- Pkg.pkg"add Documenter@1"
+import Pkg
+Pkg.pkg"add Documenter@1"
 
- # Load documenter
- using Documenter
- using DocumenterTools: Themes
- ENV["JULIA_DEBUG"] = "Documenter"
+# Load documenter
+using Documenter
+using DocumenterTools: Themes
+ENV["JULIA_DEBUG"] = "Documenter"
 
- # For easier debugging when downloading from a specific branch.
- github_user = "JuliaDynamics"
- branch = "master"
- download_path = "https://raw.githubusercontent.com/$github_user/doctheme/$branch"
+# For easier debugging when downloading from a specific branch.
+github_user = "JuliaDynamics"
+branch = "master"
+download_path = "https://raw.githubusercontent.com/$github_user/doctheme/$branch"
 
- import Downloads
- for file in ("juliadynamics-lightdefs.scss", "juliadynamics-darkdefs.scss", "juliadynamics-style.scss")
-     Downloads.download("$download_path/$file", joinpath(@__DIR__, file))
- end
+import Downloads
+for file in ("juliadynamics-lightdefs.scss", "juliadynamics-darkdefs.scss", "juliadynamics-style.scss")
+    Downloads.download("$download_path/$file", joinpath(@__DIR__, file))
+end
 
- # create the themes
- for w in ("light", "dark")
-     header = read(joinpath(@__DIR__, "juliadynamics-style.scss"), String)
-     theme = read(joinpath(@__DIR__, "juliadynamics-$(w)defs.scss"), String)
-     write(joinpath(@__DIR__, "juliadynamics-$(w).scss"), header*"\n"*theme)
- end
+# create the themes
+for w in ("light", "dark")
+    header = read(joinpath(@__DIR__, "juliadynamics-style.scss"), String)
+    theme = read(joinpath(@__DIR__, "juliadynamics-$(w)defs.scss"), String)
+    write(joinpath(@__DIR__, "juliadynamics-$(w).scss"), header * "\n" * theme)
+end
 
- # compile the themes
- Themes.compile(joinpath(@__DIR__, "juliadynamics-light.scss"), joinpath(@__DIR__, "src/assets/themes/documenter-light.css"))
- Themes.compile(joinpath(@__DIR__, "juliadynamics-dark.scss"), joinpath(@__DIR__, "src/assets/themes/documenter-dark.css"))
+# compile the themes
+Themes.compile(joinpath(@__DIR__, "juliadynamics-light.scss"), joinpath(@__DIR__, "src/assets/themes/documenter-light.css"))
+Themes.compile(joinpath(@__DIR__, "juliadynamics-dark.scss"), joinpath(@__DIR__, "src/assets/themes/documenter-dark.css"))
 
- # Download and apply CairoMakie plotting style
- using CairoMakie
- Downloads.download("$download_path/style.jl", joinpath(@__DIR__, "style.jl"))
- include("style.jl")
+# Download and apply CairoMakie plotting style
+using CairoMakie
+Downloads.download("$download_path/style.jl", joinpath(@__DIR__, "style.jl"))
+include("style.jl")
 
- using DocumenterInterLinks
+using DocumenterInterLinks
 
 links = InterLinks(
     "ComplexityMeasures" => (
@@ -49,46 +49,48 @@ links = InterLinks(
     ),
 );
 
- function build_docs_with_style(pages, modules...; bib = nothing, authors = "George Datseris", draft = false, kwargs...)
-     settings = (
-         modules = [modules...],
-         format = Documenter.HTML(
-             prettyurls = CI,
-             assets = [
-                 asset("https://fonts.googleapis.com/css?family=Montserrat|Source+Code+Pro&display=swap", class=:css),
-             ],
-             collapselevel = 3,
-             size_threshold = 1250 * 2^10, 
-             size_threshold_warn = 750 * 2^10,
-             example_size_threshold = 100 * 2^10,
-             size_threshold_ignore = [
-                "examples/examples_associations.md", 
+function build_docs_with_style(pages, modules...; bib=nothing,
+    authors="Kristian Haaga, George Datseris and others", draft=false, kwargs...)
+    settings = (
+        modules=[modules...],
+        format=Documenter.HTML(
+            prettyurls=CI,
+            assets=[
+                asset("https://fonts.googleapis.com/css?family=Montserrat|Source+Code+Pro&display=swap", class=:css),
+            ],
+            collapselevel=3,
+            size_threshold=1250 * 2^10,
+            size_threshold_warn=750 * 2^10,
+            example_size_threshold=100 * 2^10,
+            size_threshold_ignore=[
+                "examples/examples_associations.md",
                 "examples/examples_independence.md",
                 "examples/examples_infer_graphs.md",
-             ]
-         ),
-         sitename = "$(modules[1]).jl",
-         authors,
-         pages,
-         draft,
-         doctest = false,
-         warnonly = false,
-         checkdocs = :exported,
-         kwargs...
-     )
+            ]
+        ),
+        sitename="$(modules[1]).jl",
+        authors,
+        pages,
+        draft,
+        doctest=false,
+        checkdocs=:exported,
+        # The following Documenter fails will NOT ERROR the docbuild!
+        warnonly=[:doctest, :missing_docs],
+        kwargs...
+    )
 
-     if isnothing(bib)
-         makedocs(; settings...)
-     else
-         makedocs(; plugins=[bib, links], settings...)
-     end
+    if isnothing(bib)
+        makedocs(; settings...)
+    else
+        makedocs(; plugins=[bib, links], settings...)
+    end
 
-     if CI
-         deploydocs(
-             repo = "github.com/JuliaDynamics/$(modules[1]).jl.git",
-             target = "build",
-             push_preview = true
-         )
-     end
+    if CI
+        deploydocs(
+            repo="github.com/JuliaDynamics/$(modules[1]).jl.git",
+            target="build",
+            push_preview=true
+        )
+    end
 
- end 
\ No newline at end of file
+end
\ No newline at end of file

From 2242495278ffd20d777f8257797ed8d345c64f37 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 10:08:17 +0200
Subject: [PATCH 05/24] formatting and extref

---
 src/core.jl | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/src/core.jl b/src/core.jl
index 85f03896..2f9664d3 100644
--- a/src/core.jl
+++ b/src/core.jl
@@ -5,10 +5,10 @@ export AssociationMeasure
 export AssociationMeasureEstimator
 export association
 
-const VectorOr1DDataset{T} = Union{AbstractVector{T}, AbstractStateSpaceSet{1, T}} where T
-const VectorOrStateSpaceSet{D, T} = Union{AbstractVector{T}, AbstractStateSpaceSet{D, T}} where {D, T}
-const ArrayOrStateSpaceSet{D, T, N} = Union{AbstractArray{T, N}, AbstractStateSpaceSet{D, T}} where {D, T, N}
-const INFO_ESTS = Union{DifferentialInfoEstimator, DiscreteInfoEstimator}
+const VectorOr1DDataset{T} = Union{AbstractVector{T},AbstractStateSpaceSet{1,T}} where T
+const VectorOrStateSpaceSet{D,T} = Union{AbstractVector{T},AbstractStateSpaceSet{D,T}} where {D,T}
+const ArrayOrStateSpaceSet{D,T,N} = Union{AbstractArray{T,N},AbstractStateSpaceSet{D,T}} where {D,T,N}
+const INFO_ESTS = Union{DifferentialInfoEstimator,DiscreteInfoEstimator}
 
 """
     AssociationMeasure
@@ -105,7 +105,7 @@ Concrete subtypes are given as input to [`association`](@ref).
 | [`ConvergentCrossMapping`](@ref)                     | [`RandomVectors`](@ref), [`RandomSegment`](@ref)                                                                                                                                                                             |
 | [`MCR`](@ref)                                        | Not required                                                                                                                                                                                                                 |
 | [`RMCD`](@ref)                                       | Not required                                                                                                                                                                                                                 |
-| [`MIShannon`](@ref)                                  | [`JointProbabilities`](@ref), [`EntropyDecomposition`](@ref), [`KraskovStögbauerGrassberger1`](@ref), [`KraskovStögbauerGrassberger2`](@ref), [`GaoOhViswanath`](@ref), [`GaoKannanOhViswanath`](@ref), [`GaussianMI`](@ref) |
+| [`MIShannon`](@ref)                                  | [`JointProbabilities`](@ref), [`EntropyDecomposition`](@ref), [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures), [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures), [`GaoOhViswanath`](@ref), [`GaoKannanOhViswanath`](@extref ComplexityMeasures), [`GaussianMI`](@ref) |
 | [`MIRenyiJizba`](@ref)                               | [`JointProbabilities`](@ref), [`EntropyDecomposition`](@ref)                                                                                                                                                                 |
 | [`MIRenyiSarbu`](@ref)                               | [`JointProbabilities`](@ref)                                                                                                                                                                                                 |
 | [`MITsallisFuruichi`](@ref)                          | [`JointProbabilities`](@ref), [`EntropyDecomposition`](@ref)                                                                                                                                                                 |

From 482c103f44ee40726668a777e2f7cbd58c1cf91f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 10:08:23 +0200
Subject: [PATCH 06/24] extref

---
 docs/src/api/information_multivariate_api.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/docs/src/api/information_multivariate_api.md b/docs/src/api/information_multivariate_api.md
index 5674b650..5bbc9317 100644
--- a/docs/src/api/information_multivariate_api.md
+++ b/docs/src/api/information_multivariate_api.md
@@ -207,8 +207,8 @@ est_diff = EntropyDecomposition(MIShannon(base = 2), Kraskov(Shannon(), k=10))
 association(est_diff, x, y)
 ```
 
-We can also construct a discrete entropy based estimator based on e.g. [`PlugIn`](@ref)
-estimator of [`Shannon`](@ref) entropy.
+We can also construct a discrete entropy based estimator based on e.g. [`PlugIn`](@extref ComplexityMeasures)
+estimator of [`Shannon`](@extref ComplexityMeasures) entropy.
 
 ```@example INFO_TUTORIAL
 # We know that `x` and `y` were generated from a uniform distribution above,

From 3aa1f7d549f51655e5a265783f37a3e579894013 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 10:08:36 +0200
Subject: [PATCH 07/24] extref

---
 .../conditional_entropies/ConditionalEntropyShannon.jl    | 8 ++++----
 .../conditional_mutual_informations/CMIShannon.jl         | 2 +-
 .../definitions/divergences_and_distances/KLDivergence.jl | 2 +-
 .../divergences_and_distances/RenyiDivergence.jl          | 2 +-
 src/methods/information/estimators/JointProbabilities.jl  | 4 ++--
 .../estimators/decomposition/EntropyDecomposition.jl      | 8 ++++----
 6 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/src/methods/information/definitions/conditional_entropies/ConditionalEntropyShannon.jl b/src/methods/information/definitions/conditional_entropies/ConditionalEntropyShannon.jl
index 51afae9b..3cbab77e 100644
--- a/src/methods/information/definitions/conditional_entropies/ConditionalEntropyShannon.jl
+++ b/src/methods/information/definitions/conditional_entropies/ConditionalEntropyShannon.jl
@@ -7,7 +7,7 @@ export ConditionalEntropyShannon
     ConditionalEntropyShannon <: ConditionalEntropy
     ConditionalEntropyShannon(; base = 2)
 
-The [`Shannon`](@ref) conditional entropy measure.
+The [`Shannon`](@extref ComplexityMeasures) conditional entropy measure.
 
 ## Usage 
 
@@ -40,9 +40,9 @@ Equivalently, the following differenConditionalEntropy of entropies hold
 H^S(X | Y) = H^S(X, Y) - H^S(Y),
 ```
 
-where ``H^S(\\cdot)`` and ``H^S(\\cdot | \\cdot)`` are the [`Shannon`](@ref) entropy and
+where ``H^S(\\cdot)`` and ``H^S(\\cdot | \\cdot)`` are the [`Shannon`](@extref ComplexityMeasures) entropy and
 Shannon joint entropy, respectively. This is the definition used when calling
-[`association`](@ref) with a [`ProbabilitiesEstimator`](@ref).
+[`association`](@ref) with a [`ProbabilitiesEstimator`](@extref ComplexityMeasures).
 
 ## Differential definition
 
@@ -52,7 +52,7 @@ The differential conditional Shannon entropy is analogously defined as
 H^S(X | Y) = h^S(X, Y) - h^S(Y),
 ```
 
-where ``h^S(\\cdot)`` and ``h^S(\\cdot | \\cdot)`` are the [`Shannon`](@ref)
+where ``h^S(\\cdot)`` and ``h^S(\\cdot | \\cdot)`` are the [`Shannon`](@extref ComplexityMeasures)
 differential entropy and Shannon joint differential entropy, respectively. This is the
 definition used when calling [`association`](@ref) with a
 [`DifferentialInfoEstimator`](@extref ComplexityMeasures).
diff --git a/src/methods/information/definitions/conditional_mutual_informations/CMIShannon.jl b/src/methods/information/definitions/conditional_mutual_informations/CMIShannon.jl
index 0c0f886c..0924cef1 100644
--- a/src/methods/information/definitions/conditional_mutual_informations/CMIShannon.jl
+++ b/src/methods/information/definitions/conditional_mutual_informations/CMIShannon.jl
@@ -42,7 +42,7 @@ I(X; Y | Z)
 ```
 
 where ``I^S(\\cdot; \\cdot)`` is the Shannon mutual information [`MIShannon`](@ref),
-and ``H^S(\\cdot)`` is the [`Shannon`](@ref) entropy.
+and ``H^S(\\cdot)`` is the [`Shannon`](@extref ComplexityMeasures) entropy.
 
 Differential Shannon CMI is obtained by replacing the entropies by
 differential entropies.
diff --git a/src/methods/information/definitions/divergences_and_distances/KLDivergence.jl b/src/methods/information/definitions/divergences_and_distances/KLDivergence.jl
index 04288925..8337208c 100644
--- a/src/methods/information/definitions/divergences_and_distances/KLDivergence.jl
+++ b/src/methods/information/definitions/divergences_and_distances/KLDivergence.jl
@@ -36,7 +36,7 @@ D_{KL}(P_Y(\\Omega) || P_Y(\\Omega)) =
 - [`association`](@ref). Used to compute the KL-divergence between two pre-computed
     probability distributions. If used with [`RelativeAmount`](@ref), the KL divergence may
     be undefined to due some outcomes having zero counts. Use some other
-    [`ProbabilitiesEstimator`](@ref) like [`BayesianRegularization`](@ref) to ensure
+    [`ProbabilitiesEstimator`](@extref ComplexityMeasures) like [`BayesianRegularization`](@ref) to ensure
     all estimated probabilities are nonzero.
 
 !!! note 
diff --git a/src/methods/information/definitions/divergences_and_distances/RenyiDivergence.jl b/src/methods/information/definitions/divergences_and_distances/RenyiDivergence.jl
index f5e127db..5a35ec67 100644
--- a/src/methods/information/definitions/divergences_and_distances/RenyiDivergence.jl
+++ b/src/methods/information/definitions/divergences_and_distances/RenyiDivergence.jl
@@ -34,7 +34,7 @@ D_{q}(P_Y(\\Omega) || P_Y(\\Omega)) =
 - [`information`](@ref). Used to compute the Rényi divergence between two pre-computed
     probability distributions. If used with [`RelativeAmount`](@ref), the KL divergence may
     be undefined to due some outcomes having zero counts. Use some other
-    [`ProbabilitiesEstimator`](@ref) like [`BayesianRegularization`](@ref) to ensure
+    [`ProbabilitiesEstimator`](@extref ComplexityMeasures) like [`BayesianRegularization`](@ref) to ensure
     all estimated probabilities are nonzero.
 
 !!! note 
diff --git a/src/methods/information/estimators/JointProbabilities.jl b/src/methods/information/estimators/JointProbabilities.jl
index b28846c9..453f33a9 100644
--- a/src/methods/information/estimators/JointProbabilities.jl
+++ b/src/methods/information/estimators/JointProbabilities.jl
@@ -18,7 +18,7 @@ export JointProbabilities
 
 It first encodes the input data according to the given `discretization`, then constructs 
 `probs`, a multidimensional [`Probabilities`](@ref) instance. Finally, `probs` are 
-forwarded to a [`PlugIn`](@ref) estimator, which computes the measure according to 
+forwarded to a [`PlugIn`](@extref ComplexityMeasures) estimator, which computes the measure according to 
 `definition`.
 
 # Compatible encoding schemes
@@ -41,7 +41,7 @@ Works for any [`OutcomeSpace`](@ref) that implements [`codify`](@ref).
     because it fails to fully take into consideration the joint relationships between the variables.
     Pick your estimator according to your needs.
 
-See also: [`Counts`](@ref), [`Probabilities`](@ref), [`ProbabilitiesEstimator`](@ref),
+See also: [`Counts`](@ref), [`Probabilities`](@ref), [`ProbabilitiesEstimator`](@extref ComplexityMeasures),
 [`OutcomeSpace`](@ref), [`DiscreteInfoEstimator`](@extref ComplexityMeasures).
 """
 struct JointProbabilities{M<:MultivariateInformationMeasure,O,P} <: MultivariateInformationMeasureEstimator{M}
diff --git a/src/methods/information/estimators/decomposition/EntropyDecomposition.jl b/src/methods/information/estimators/decomposition/EntropyDecomposition.jl
index 17f11dcc..cd1ff24e 100644
--- a/src/methods/information/estimators/decomposition/EntropyDecomposition.jl
+++ b/src/methods/information/estimators/decomposition/EntropyDecomposition.jl
@@ -78,7 +78,7 @@ of entropies using the `Kraskov(Shannon(base = ℯ))` Shannon entropy estimator,
 ## Discrete entropy decomposition 
 
 The second signature is for discrete estimation using [`DiscreteInfoEstimator`](@extref ComplexityMeasures)s,
-for example [`PlugIn`](@ref). The given `discretization` scheme (typically an 
+for example [`PlugIn`](@extref ComplexityMeasures). The given `discretization` scheme (typically an 
 [`OutcomeSpace`](@ref)) controls how the joint/marginals are discretized, and the
 probabilities estimator `pest` controls how probabilities are estimated from counts.
 
@@ -102,13 +102,13 @@ probabilities estimator `pest` controls how probabilities are estimated from cou
 ## Examples
 
 - [Example 1](@ref example_MIShannon_EntropyDecomposition_Jackknife_ValueBinning):
-    [`MIShannon`](@ref) estimation using decomposition into discrete [`Shannon`](@ref)
+    [`MIShannon`](@ref) estimation using decomposition into discrete [`Shannon`](@extref ComplexityMeasures)
     entropy estimated using [`CodifyVariables`](@ref) with [`ValueBinning`](@extref ComplexityMeasures).
 - [Example 2](@ref example_MIShannon_EntropyDecomposition_BubbleSortSwaps):
-    [`MIShannon`](@ref) estimation using decomposition into discrete [`Shannon`](@ref)
+    [`MIShannon`](@ref) estimation using decomposition into discrete [`Shannon`](@extref ComplexityMeasures)
     entropy estimated using [`CodifyVariables`](@ref) with [`BubbleSortSwaps`](@ref).
 - [Example 3](@ref example_MIShannon_EntropyDecomposition_Kraskov):
-    [`MIShannon`](@ref) estimation using decomposition into differental [`Shannon`](@ref)
+    [`MIShannon`](@ref) estimation using decomposition into differental [`Shannon`](@extref ComplexityMeasures)
     entropy estimated using the [`Kraskov`](@extref ComplexityMeasures) estimator.
 
 See also: [`MutualInformationEstimator`](@ref), [`MultivariateInformationMeasure`](@ref).

From 635117c5c5d3135c446caa57a8c739b5fa5f9e52 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 11:00:20 +0200
Subject: [PATCH 08/24] always use links

---
 docs/build_docs_with_style.jl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/build_docs_with_style.jl b/docs/build_docs_with_style.jl
index 288d5843..d386bb3e 100644
--- a/docs/build_docs_with_style.jl
+++ b/docs/build_docs_with_style.jl
@@ -80,7 +80,7 @@ function build_docs_with_style(pages, modules...; bib=nothing,
     )
 
     if isnothing(bib)
-        makedocs(; settings...)
+        makedocs(; plugins=[links], settings...)
     else
         makedocs(; plugins=[bib, links], settings...)
     end

From 031dd994886f07af0be0009e17cba7c949f13293 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 11:00:50 +0200
Subject: [PATCH 09/24] formatting

---
 docs/make.jl | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/docs/make.jl b/docs/make.jl
index 37f471c1..47a5f21b 100644
--- a/docs/make.jl
+++ b/docs/make.jl
@@ -25,7 +25,7 @@ pages = [
         "api/cross_map_api.md",
     ],
     "Examples" => [
-        "Associations" => "examples/examples_associations.md", 
+        "Associations" => "examples/examples_associations.md",
         "Independence testing" => "examples/examples_independence.md",
         "Causal graph inference" => "examples/examples_infer_graphs.md",
     ],
@@ -44,8 +44,8 @@ bibliography = CitationBibliography(
 )
 
 build_docs_with_style(pages, Associations, ComplexityMeasures, StateSpaceSets;
-    expandfirst = ["index.md"],
-    bib = bibliography,
-    pages = pages,
-    authors = "Kristian Agasøster Haaga, David Diego, Tor Einar Møller, George Datseris",
+    expandfirst=["index.md"],
+    bib=bibliography,
+    pages=pages,
+    authors="Kristian Agasøster Haaga, David Diego, Tor Einar Møller, George Datseris",
 )

From f9ab796b51e82b2542eadd72a2556c26991c3579 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 11:01:05 +0200
Subject: [PATCH 10/24] up to julia long term release version

---
 docs/Project.toml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/docs/Project.toml b/docs/Project.toml
index 614195e8..3d76c263 100644
--- a/docs/Project.toml
+++ b/docs/Project.toml
@@ -1,4 +1,5 @@
 [deps]
+Associations = "614afb3a-e278-4863-8805-9959372b9ec2"
 CairoMakie = "13f3f980-e62b-5c42-98c6-ff1f3baf88f0"
 ComplexityMeasures = "ab4b797d-85ee-42ba-b621-05d793b346a2"
 DelayEmbeddings = "5732040d-69e3-5649-938a-b6b4f237613f"
@@ -27,4 +28,4 @@ TimeseriesSurrogates = "c804724b-8c18-5caa-8579-6025a0767c70"
 [compat]
 ComplexityMeasures = "^3.8"
 DynamicalSystemsBase = "3"
-julia = "^1.10.6"
+julia = "^1.10.10"

From f7cfdb6b92169ccfeac44d3dbac6c927c28e09ab Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 11:41:28 +0200
Subject: [PATCH 11/24] reintroduce references

---
 .../api/information_single_variable_api.md    | 44 ++++++++++++++++++-
 1 file changed, 43 insertions(+), 1 deletion(-)

diff --git a/docs/src/api/information_single_variable_api.md b/docs/src/api/information_single_variable_api.md
index 6f987d01..35ce51be 100644
--- a/docs/src/api/information_single_variable_api.md
+++ b/docs/src/api/information_single_variable_api.md
@@ -8,4 +8,46 @@ Below we list some relevant functions types from
 [ComplexityMeasures.jl](https://github.com/JuliaDynamics/ComplexityMeasures.jl) that 
 are used for the [`EntropyDecomposition`](@ref) estimator.
 
-- [`information`](@extref ComplexityMeasures)
+```@docs
+information
+```
+
+## Single-variable information measures
+
+```@docs
+Shannon
+Renyi
+Tsallis
+Kaniadakis
+```
+
+## Discrete information estimators
+
+```@docs
+DiscreteInfoEstimator
+PlugIn
+MillerMadow
+Schuermann
+GeneralizedSchuermann
+Jackknife
+HorvitzThompson
+ChaoShen
+```
+
+## Differential information estimators
+
+```@docs
+DifferentialInfoEstimator
+Kraskov
+KozachenkoLeonenko
+Zhu
+ZhuSingh
+Gao
+Goria
+Lord
+LeonenkoProzantoSavani
+Vasicek
+AlizadehArghami
+Ebrahimi
+Correa
+```
\ No newline at end of file

From 60de9f74616c2bcea0fe61fcc8546ed5ee6bc24a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 12:37:32 +0200
Subject: [PATCH 12/24] Properly use extrefs

---
 docs/build_docs_with_style.jl                 |  18 ++-
 docs/make.jl                                  |   2 +-
 docs/src/api/counts_and_probabilities_api.md  |   8 +-
 .../api/discretization_counts_probs_api.md    |  67 +++++----
 docs/src/api/information_multivariate_api.md  |  16 +--
 .../api/information_single_variable_api.md    |  58 ++++----
 docs/src/examples/examples_associations.md    | 130 +++++++++---------
 docs/src/examples/examples_independence.md    |   4 +-
 src/core.jl                                   |   2 +-
 src/methods/information/core.jl               |  12 +-
 .../information/counts_and_probs/counts.jl    |   6 +-
 .../encoding/codify_points.jl                 |  40 +++---
 .../encoding/codify_variables.jl              |  14 +-
 .../counts_and_probs/probabilities.jl         |   8 +-
 .../ConditionalEntropyShannon.jl              |  14 +-
 .../ConditionalEntropyTsallisAbe.jl           |   6 +-
 .../ConditionalEntropyTsallisFuruichi.jl      |   4 +-
 .../CMIRenyiJizba.jl                          |   6 +-
 .../CMIShannon.jl                             |   8 +-
 .../HellingerDistance.jl                      |   4 +-
 .../divergences_and_distances/KLDivergence.jl |   8 +-
 .../RenyiDivergence.jl                        |   8 +-
 .../VariationDistance.jl                      |   4 +-
 .../joint_entropies/JointEntropyRenyi.jl      |   2 +-
 .../joint_entropies/JointEntropyShannon.jl    |   2 +-
 .../joint_entropies/JointEntropyTsallis.jl    |   2 +-
 .../mutual_informations/MIRenyiJizba.jl       |   8 +-
 .../mutual_informations/MIRenyiSarbu.jl       |   4 +-
 .../mutual_informations/MIShannon.jl          |  24 ++--
 .../mutual_informations/MITsallisFuruichi.jl  |   8 +-
 .../mutual_informations/MITsallisMartin.jl    |   8 +-
 ...xpansion_conditional_mutual_information.jl |   2 +-
 .../transferentropy/TERenyiJizba.jl           |  14 +-
 .../definitions/transferentropy/TEShannon.jl  |   2 +-
 .../estimators/JointProbabilities.jl          |  10 +-
 .../estimators/codify_marginals.jl            |  16 +--
 .../FPVP.jl                                   |   2 +-
 .../Rahimzamani.jl                            |   2 +-
 .../decomposition/EntropyDecomposition.jl     |  50 +++----
 .../decomposition/MIDecomposition.jl          |   2 +-
 .../GaoKannanOhViswanath.jl                   |   6 +-
 .../transfer_entropy_estimators/Hilbert.jl    |   2 +-
 .../SymbolicTransferEntropy.jl                |   2 +-
 43 files changed, 309 insertions(+), 306 deletions(-)

diff --git a/docs/build_docs_with_style.jl b/docs/build_docs_with_style.jl
index d386bb3e..1f5c5460 100644
--- a/docs/build_docs_with_style.jl
+++ b/docs/build_docs_with_style.jl
@@ -42,12 +42,22 @@ links = InterLinks(
         "https://juliadynamics.github.io/DynamicalSystemsDocs.jl/complexitymeasures/stable/objects.inv",
         joinpath(@__DIR__, "inventories", "Documenter.toml")
     ),
-    "StateSpaceSets" => (
-        "https://juliadynamics.github.io/DynamicalSystemsDocs.jl/statespacesets/stable/",
-        "https://juliadynamics.github.io/DynamicalSystemsDocs.jl/statespacesets/stable/objects.inv",
+    "Documenter" => (
+        "https://documenter.juliadocs.org/stable/",
+        "https://documenter.juliadocs.org/stable/objects.inv",
         joinpath(@__DIR__, "inventories", "Documenter.toml")
     ),
+    # "StateSpaceSets" => (
+    #     "https://juliadynamics.github.io/DynamicalSystemsDocs.jl/statespacesets/stable/",
+    #     "https://juliadynamics.github.io/DynamicalSystemsDocs.jl/statespacesets/stable/objects.inv",
+    #     joinpath(@__DIR__, "inventories", "Documenter.toml")
+    # ),
 );
+@show links["ComplexityMeasures"]
+@show links["Documenter"]
+for item in links["ComplexityMeasures"]
+    @show item
+end
 
 function build_docs_with_style(pages, modules...; bib=nothing,
     authors="Kristian Haaga, George Datseris and others", draft=false, kwargs...)
@@ -82,7 +92,7 @@ function build_docs_with_style(pages, modules...; bib=nothing,
     if isnothing(bib)
         makedocs(; plugins=[links], settings...)
     else
-        makedocs(; plugins=[bib, links], settings...)
+        makedocs(; plugins=[links, bib], settings...)
     end
 
     if CI
diff --git a/docs/make.jl b/docs/make.jl
index 47a5f21b..480c8430 100644
--- a/docs/make.jl
+++ b/docs/make.jl
@@ -43,7 +43,7 @@ bibliography = CitationBibliography(
     style=:authoryear
 )
 
-build_docs_with_style(pages, Associations, ComplexityMeasures, StateSpaceSets;
+build_docs_with_style(pages, Associations, StateSpaceSets;
     expandfirst=["index.md"],
     bib=bibliography,
     pages=pages,
diff --git a/docs/src/api/counts_and_probabilities_api.md b/docs/src/api/counts_and_probabilities_api.md
index 042b20ac..480e9c72 100644
--- a/docs/src/api/counts_and_probabilities_api.md
+++ b/docs/src/api/counts_and_probabilities_api.md
@@ -24,10 +24,10 @@ The utility function [`marginal`](@ref) is also useful.
 marginal
 ```
 
-## [Example: estimating [`Counts`](@ref) and [`Probabilities`](@ref)](@id tutorial_probabilities)
+## [Example: estimating [`Counts`](@extref ComplexityMeasures.Counts) and [`Probabilities`](@extref ComplexityMeasures.Probabilities)](@id tutorial_probabilities)
 
 Estimating multivariate counts (contingency matrices) and PMFs is simple. If the data are pre-discretized, then
-we can use [`UniqueElements`](@extref ComplexityMeasures) to simply count the number of occurrences.
+we can use [`UniqueElements`](@extref ComplexityMeasures.UniqueElements) to simply count the number of occurrences.
 
 ```@example counts_probs_tutorial
 using Associations
@@ -47,7 +47,7 @@ probabilities(discretization, x, y, z)
 ```
 
 For numerical data, we can estimate both counts and probabilities using [`CodifyVariables`](@ref)
-with any count-based [`OutcomeSpace`](@ref).
+with any count-based [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace).
 
 ```@example counts_probs_tutorial
 using Associations
@@ -56,7 +56,7 @@ discretization = CodifyVariables(BubbleSortSwaps(m = 4))
 probabilities(discretization, x, y)
 ```
 
-For more fine-grained control, we can use [`CodifyPoints`](@ref) with one or several [`Encoding`](@ref)s.
+For more fine-grained control, we can use [`CodifyPoints`](@ref) with one or several [`Encoding`](@extref ComplexityMeasures.Encoding)s.
 
 ```@example counts_probs_tutorial
 using Associations
diff --git a/docs/src/api/discretization_counts_probs_api.md b/docs/src/api/discretization_counts_probs_api.md
index 8fe28698..85047d2a 100644
--- a/docs/src/api/discretization_counts_probs_api.md
+++ b/docs/src/api/discretization_counts_probs_api.md
@@ -9,7 +9,7 @@ CollapsedDocStrings = true
 A fundamental operation when computing multivariate information measures from data is *discretization*. 
 When discretizing, what happens is that we "encode" input data into an intermediate representation indexed by the positive integers. This intermediate representation is called an "encoding". This is useful in several ways:
 
-- Once a dataset has been encoded into integers, we can estimate [`Counts`](@ref) or [`Probabilities`](@ref) ([tutorial](@ref tutorial_probabilities)).
+- Once a dataset has been encoded into integers, we can estimate [`Counts`](@extref ComplexityMeasures.Counts) or [`Probabilities`](@extref ComplexityMeasures.Probabilities) ([tutorial](@ref tutorial_probabilities)).
 - Once probabilities have been estimated, one can use these to estimate [`MultivariateInformationMeasure`](@ref) ([tutorial](@ref tutorial_infomeasures)).
 
  The following functions and types are used by Associations.jl to perform discretization of input data.
@@ -24,12 +24,12 @@ codify
 In summary, the two main ways of discretizing data in Associations are as follows.
 
 - The [`CodifyPoints`](@ref) discretization scheme encodes input data on a point-by-point 
-    basis by applying some [`Encoding`](@ref) to each point.
+    basis by applying some [`Encoding`](@extref ComplexityMeasures.Encoding) to each point.
 - The [`CodifyVariables`](@ref) discretization scheme encodes input data on a column-by-column
-    basis by applying a sliding window to each column, and encoding the data within the sliding window according to some [`OutcomeSpace`](@ref) (*Internally, this uses [`codify`](@ref)*).
+    basis by applying a sliding window to each column, and encoding the data within the sliding window according to some [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace) (*Internally, this uses [`codify`](@ref)*).
 
 !!! note 
-    [`Encoding`](@ref), [`OutcomeSpace`](@ref) and [`codify`](@ref) are all from
+    [`Encoding`](@extref ComplexityMeasures.Encoding), [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace) and [`codify`](@ref) are all from
     [ComplexityMeasures.jl](https://github.com/JuliaDynamics/ComplexityMeasures.jl).
     In this package, they are used to discretize multiple input variables instead of just one input
     variable.
@@ -41,28 +41,26 @@ In some cases, it may be desireable to encode data on a row-wise basis. This
 typically happens when working with pre-embedded time series or [`StateSpaceSet`](@ref)s 
 (respecting the fact that time ordering is already taken care of by the 
 embedding procedure). 
-If we want to apply something like [`OrdinalPatternEncoding`](@ref) to such data, then 
+If we want to apply something like [`OrdinalPatternEncoding`](@extref ComplexityMeasures.OrdinalPatternEncoding) to such data, then 
 we must encode each *point* individually, such that vectors like `[1.2, 2.4, 4.5]` or 
 `["howdy", "partner"]` gets mapped to an integer. The [`CodifyPoints`](@ref) discretization 
 intstruction ensures input data are encoded on a point-by-point basis.
 
-A point-by-point discretization using [`CodifyPoints`](@ref) is formally done by applying some [`Encoding`](@ref) to each input data point. You can pick between the following encodings, or combine 
-them in arbitrary ways using [`CombinationEncoding`](@ref).
+A point-by-point discretization using [`CodifyPoints`](@ref) is formally done by applying some [`Encoding`](@extref ComplexityMeasures.Encoding) to each input data point. You can pick between the following encodings, or combine 
+them in arbitrary ways using [`CombinationEncoding`](@extref ComplexityMeasures.CombinationEncoding).
 
-```@docs
-Encoding
-GaussianCDFEncoding
-OrdinalPatternEncoding
-RelativeMeanEncoding
-RelativeFirstDifferenceEncoding
-UniqueElementsEncoding
-RectangularBinEncoding
-CombinationEncoding
-```
+- [`Encoding`](@extref ComplexityMeasures.Encoding)
+- [`GaussianCDFEncoding`](@extref ComplexityMeasures.GaussianCDFEncoding)
+- [`OrdinalPatternEncoding`](@extref ComplexityMeasures.OrdinalPatternEncoding)
+- [`RelativeMeanEncoding`](@extref ComplexityMeasures.RelativeMeanEncoding)
+- [`RelativeFirstDifferenceEncoding`](@extref ComplexityMeasures.RelativeFirstDifferenceEncoding)
+- [`UniqueElementsEncoding`](@extref ComplexityMeasures.UniqueElementsEncoding)
+- [`RectangularBinEncoding`](@extref ComplexityMeasures.RectangularBinEncoding)
+- [`CombinationEncoding`](@extref ComplexityMeasures.CombinationEncoding)
 
 #### [Examples: encoding *rows* (one *point* at a time)](@id tutorial_codify_points)
 
-We'll here use the [`OrdinalPatternEncoding`](@ref) with differing parameter `m` to encode 
+We'll here use the [`OrdinalPatternEncoding`](@extref ComplexityMeasures.OrdinalPatternEncoding) with differing parameter `m` to encode 
 multiple [`StateSpaceSet`](@ref) of differing dimensions.
 
 ```@example example_encode_points
@@ -105,27 +103,26 @@ This typically happens when the input are either a single or multiple timeseries
 To encode columns, we move a sliding window across each input variable/column and 
 encode points within that window. Formally, such a sliding-window discretization 
 is done by using the [`CodifyVariables`](@ref) discretization scheme, which takes
-as input some [`OutcomeSpace`](@ref) that dictates how each window is encoded, and 
+as input some [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace) that dictates how each window is encoded, and 
 also dictates the width of the encoding windows. 
 
 For column/variable-wise encoding, you can pick between the following outcome spaces.
+- [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace)
+- [`UniqueElements`](@extref ComplexityMeasures.UniqueElements)
+- [`CosineSimilarityBinning`](@extref ComplexityMeasures.CosineSimilarityBinning)
+- [`Dispersion`](@extref ComplexityMeasures.Dispersion)
+- [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)
+- [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)
+- [`BubbleSortSwaps`](@extref ComplexityMeasures.BubbleSortSwaps)
+- [`ValueBinning`](@extref ComplexityMeasures.ValueBinning)
+- [`RectangularBinning`](@extref ComplexityMeasures.RectangularBinning)
+- [`FixedRectangularBinning`](@extref ComplexityMeasures.FixedRectangularBinning)
 
-```@docs
-OutcomeSpace
-UniqueElements
-CosineSimilarityBinning
-Dispersion
-OrdinalPatterns
-BubbleSortSwaps
-ValueBinning
-RectangularBinning
-FixedRectangularBinning
-```
 
 #### Example: encoding *columns* (one variable at a time)
 
-Some [`OutcomeSpace`](@ref)s dictate a sliding window which has the width of one element
-when used with [`CodifyVariables`](@ref). [`ValueBinning`](@extref ComplexityMeasures) is such an outcome space.
+Some [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace)s dictate a sliding window which has the width of one element
+when used with [`CodifyVariables`](@ref). [`ValueBinning`](@extref ComplexityMeasures.ValueBinning) is such an outcome space.
 
 ```@example example_encode_vars
 using Associations
@@ -136,17 +133,17 @@ o = ValueBinning(3)
 cx = codify(CodifyVariables(o), x)
 ```
 
-We can verify that [`ValueBinning`](@extref ComplexityMeasures) preserves the cardinality of the input dataset.
+We can verify that [`ValueBinning`](@extref ComplexityMeasures.ValueBinning) preserves the cardinality of the input dataset.
 
 ```@example example_encode_vars
 length(x) == length(cx)
 ```
 
-Other outcome spaces such as [`Dispersion`](@extref ComplexityMeasures) or [`OrdinalPatterns`](@extref ComplexityMeasures) do not 
+Other outcome spaces such as [`Dispersion`](@extref ComplexityMeasures.Dispersion) or [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns) do not 
 preserve the cardinality of the input dataset when used with [`CodifyVariables`](@ref). This is 
 because when they are applied in a sliding window, they compress sliding windows consisting of 
 potentially multiple points into single integers. This means that some points at the 
-end of each input variable are lost. For example, with [`OrdinalPatterns`](@extref ComplexityMeasures), the number 
+end of each input variable are lost. For example, with [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns), the number 
 of encoded points decrease with the embedding parameter `m`.
 
 ```@example example_encode_vars
diff --git a/docs/src/api/information_multivariate_api.md b/docs/src/api/information_multivariate_api.md
index 5bbc9317..89736235 100644
--- a/docs/src/api/information_multivariate_api.md
+++ b/docs/src/api/information_multivariate_api.md
@@ -110,7 +110,7 @@ find those that we implement [here](@ref divergences_and_distances).
 
 As an example, let's quantify the [`KLDivergence`](@ref) between two probability 
 mass functions estimated by symbolizing two input vectors `x` and `y` using 
-[`OrdinalPatterns`](@extref ComplexityMeasures). Since the discrete [`KLDivergence`](@ref) can be 
+[`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns). Since the discrete [`KLDivergence`](@ref) can be 
 expressed as a function of a joint pmf, we can use the [`JointProbabilities`](@ref)
 estimator.
 
@@ -157,7 +157,7 @@ association(est, x, y)
 
 [Joint entropies](@ref joint_entropies), on the other hand, are *symmetric*. Joint
 entropies are functionals of a joint pmf, so we can still use the
-[`JointProbabilities`](@ref) estimator. This time, we use a [`Dispersion`](@extref ComplexityMeasures)
+[`JointProbabilities`](@ref) estimator. This time, we use a [`Dispersion`](@extref ComplexityMeasures.Dispersion)
 based discretization.
 
 ```@example INFO_TUTORIAL
@@ -176,7 +176,7 @@ Mutual informations, in particular [`MIShannon`](@ref) is an often-used symmetri
 measure for quantifing the (possibly nonlinear) association between variables. It appears
 in both  discrete and differential form, and can be estimated in a multitude of ways. For 
 example, one can use dedicated [`MutualInformationEstimator`](@ref)s such as 
-[`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) or [`GaussianMI`](@ref):
+[`KraskovStögbauerGrassberger2`](@ref) or [`GaussianMI`](@ref):
 
 ```@example INFO_TUTORIAL
 using Associations
@@ -196,7 +196,7 @@ association(est, x, y) ≈ association(est, y, x) # should be true
 
 One can also estimate mutual information using the [`EntropyDecomposition`](@ref) 
 estimator, or (like above) using the [`JointProbabilities`](@ref) estimator.
-Let's construct a differential entropy based estimator based on the [`Kraskov`](@extref ComplexityMeasures)
+Let's construct a differential entropy based estimator based on the [`Kraskov`](@extref ComplexityMeasures.Kraskov)
 estimator.
 
 ```@example INFO_TUTORIAL
@@ -207,8 +207,8 @@ est_diff = EntropyDecomposition(MIShannon(base = 2), Kraskov(Shannon(), k=10))
 association(est_diff, x, y)
 ```
 
-We can also construct a discrete entropy based estimator based on e.g. [`PlugIn`](@extref ComplexityMeasures)
-estimator of [`Shannon`](@extref ComplexityMeasures) entropy.
+We can also construct a discrete entropy based estimator based on e.g. [`PlugIn`](@extref ComplexityMeasures.PlugIn)
+estimator of [`Shannon`](@extref ComplexityMeasures.Shannon) entropy.
 
 ```@example INFO_TUTORIAL
 # We know that `x` and `y` were generated from a uniform distribution above,
@@ -224,7 +224,7 @@ association(est_disc, x, y)
 
 
 For numerical data, we can estimate both counts and probabilities using [`CodifyVariables`](@ref)
-with any count-based [`OutcomeSpace`](@ref). Here, we'll estimate [`MIShannon`](@ref) using 
+with any count-based [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace). Here, we'll estimate [`MIShannon`](@ref) using 
 one type of encoding for the first variable, and another type of encoding for the second variable.
 
 ```@example counts_probs_tutorial
@@ -244,7 +244,7 @@ est = JointProbabilities(MIShannon(), discretization)
 association(est, x, y)
 ```
 
-For more fine-grained control than [`CodifyVariables`](@ref) can offer, we can use [`CodifyPoints`](@ref) with one or several [`Encoding`](@ref)s. Here's how we can estimate [`MIShannon`](@ref) one multivariate input 
+For more fine-grained control than [`CodifyVariables`](@ref) can offer, we can use [`CodifyPoints`](@ref) with one or several [`Encoding`](@extref ComplexityMeasures.Encoding)s. Here's how we can estimate [`MIShannon`](@ref) one multivariate input 
 data by discretizing each input variable in arbitrary ways.
 
 ```@example counts_probs_tutorial
diff --git a/docs/src/api/information_single_variable_api.md b/docs/src/api/information_single_variable_api.md
index 35ce51be..7eace43f 100644
--- a/docs/src/api/information_single_variable_api.md
+++ b/docs/src/api/information_single_variable_api.md
@@ -14,40 +14,36 @@ information
 
 ## Single-variable information measures
 
-```@docs
-Shannon
-Renyi
-Tsallis
-Kaniadakis
-```
+- [`Shannon`](@extref ComplexityMeasures.Shannon)
+- [`Renyi`](@extref ComplexityMeasures.Renyi)
+- [`Tsallis`](@extref ComplexityMeasures.Tsallis)
+- [`Kaniadakis`](@extref ComplexityMeasures.Kaniadakis)
 
 ## Discrete information estimators
 
-```@docs
-DiscreteInfoEstimator
-PlugIn
-MillerMadow
-Schuermann
-GeneralizedSchuermann
-Jackknife
-HorvitzThompson
-ChaoShen
-```
+
+- [`DiscreteInfoEstimator`](@extref ComplexityMeasures.DiscreteInfoEstimator)
+- [`PlugIn`](@extref ComplexityMeasures.PlugIn)
+- [`MillerMadow`](@extref ComplexityMeasures.MillerMadow)
+- [`Schuermann`](@extref ComplexityMeasures.Schuermann)
+- [`GeneralizedSchuermann`](@extref ComplexityMeasures.GeneralizedSchuermann)
+- [`Jackknife`](@extref ComplexityMeasures.Jackknife)
+- [`HorvitzThompson`](@extref ComplexityMeasures.HorvitzThompson)
+- [`ChaoShen`](@extref ComplexityMeasures.ChaoShen)
+
 
 ## Differential information estimators
 
-```@docs
-DifferentialInfoEstimator
-Kraskov
-KozachenkoLeonenko
-Zhu
-ZhuSingh
-Gao
-Goria
-Lord
-LeonenkoProzantoSavani
-Vasicek
-AlizadehArghami
-Ebrahimi
-Correa
-```
\ No newline at end of file
+- [`DifferentialInfoEstimator`](@extref ComplexityMeasures.DifferentialInfoEstimator)
+- [`Kraskov`](@extref ComplexityMeasures.Kraskov)
+- [`KozachenkoLeonenko`](@extref ComplexityMeasures.KozachenkoLeonenko)
+- [`Zhu`](@extref ComplexityMeasures.Zhu)
+- [`ZhuSingh`](@extref ComplexityMeasures.ZhuSingh)
+- [`Gao`](@extref ComplexityMeasures.Gao)
+- [`Goria`](@extref ComplexityMeasures.Goria)
+- [`Lord`](@extref ComplexityMeasures.Lord)
+- [`LeonenkoProzantoSavani`](@extref ComplexityMeasures.LeonenkoProzantoSavani)
+- [`Vasicek`](@extref ComplexityMeasures.Vasicek)
+- [`AlizadehArghami`](@extref ComplexityMeasures.AlizadehArghami)
+- [`Ebrahimi`](@extref ComplexityMeasures.Ebrahimi)
+- [`Correa`](@extref ComplexityMeasures.Correa)
diff --git a/docs/src/examples/examples_associations.md b/docs/src/examples/examples_associations.md
index d1c1fb7f..3ca96c68 100644
--- a/docs/src/examples/examples_associations.md
+++ b/docs/src/examples/examples_associations.md
@@ -12,7 +12,7 @@ p2 = Probabilities([0.3, 0.3, 0.2, 0.2])
 association(HellingerDistance(), p1, p2)
 ```
 
-### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_HellingerDistance_JointProbabilities_OrdinalPatterns)
+### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)](@id example_HellingerDistance_JointProbabilities_OrdinalPatterns)
 
 We expect the Hellinger distance between two uncorrelated variables to be close to zero.
 
@@ -37,7 +37,7 @@ p2 = Probabilities([0.3, 0.3, 0.2, 0.2])
 association(KLDivergence(), p1, p2)
 ```
 
-### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_KLDivergence_JointProbabilities_OrdinalPatterns)
+### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)](@id example_KLDivergence_JointProbabilities_OrdinalPatterns)
 
 We expect the [`KLDivergence`](@ref) between two uncorrelated variables to be close to zero.
 
@@ -63,7 +63,7 @@ p2 = Probabilities([0.3, 0.3, 0.2, 0.2])
 association(RenyiDivergence(), p1, p2)
 ```
 
-### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_RenyiDivergence_JointProbabilities_OrdinalPatterns)
+### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)](@id example_RenyiDivergence_JointProbabilities_OrdinalPatterns)
 
 We expect the [`RenyiDivergence`](@ref) between two uncorrelated variables to be close to zero.
 
@@ -89,7 +89,7 @@ p2 = Probabilities([0.3, 0.3, 0.2, 0.2])
 association(VariationDistance(), p1, p2)
 ```
 
-### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_VariationDistance_JointProbabilities_OrdinalPatterns)
+### [[`JointProbabilities`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)](@id example_VariationDistance_JointProbabilities_OrdinalPatterns)
 
 We expect the [`VariationDistance`](@ref) between two uncorrelated variables to be close to zero.
 
@@ -104,7 +104,7 @@ div_hd = association(est, x, y) # pretty close to zero
 
 ## [`JointEntropyShannon`](@ref)
 
-### [[`JointProbabilities`](@ref) with [`Dispersion`](@extref ComplexityMeasures)](@id example_JointEntropyShannon_Dispersion)
+### [[`JointProbabilities`](@ref) with [`Dispersion`](@extref ComplexityMeasures.Dispersion)](@id example_JointEntropyShannon_Dispersion)
 
 ```@example example_JointEntropyShannon
 using Associations
@@ -118,7 +118,7 @@ association(est, x, y)
 
 ## [`JointEntropyTsallis`](@ref)
 
-### [[`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_JointEntropyTsallis_OrdinalPatterns)
+### [[`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)](@id example_JointEntropyTsallis_OrdinalPatterns)
 
 ```@example example_JointEntropyTsallis
 using Associations
@@ -133,7 +133,7 @@ association(est, x, y)
 
 ## [`JointEntropyRenyi`](@ref)
 
-### [[`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_JointEntropyRenyi_ValueBinning)
+### [[`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)](@id example_JointEntropyRenyi_ValueBinning)
 
 ```@example example_JointEntropyRenyi
 using Associations
@@ -190,7 +190,7 @@ pyx = Probabilities(transpose(freqs_yx))
 ce_y_given_x = association(ConditionalEntropyShannon(), pyx) |> Rational
 ```
 
-### [[`JointProbabilities`](@ref) + [`CodifyVariables`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_ConditionalEntropyShannon_JointProbabilities_CodifyVariables_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`CodifyVariables`](@ref) + [`UniqueElements`](@extref ComplexityMeasures.UniqueElements)](@id example_ConditionalEntropyShannon_JointProbabilities_CodifyVariables_UniqueElements)
 
 We can of course also estimate conditional entropy from data. To do so, we'll use the 
 [`JointProbabilities`](@ref) estimator, which constructs a multivariate PMF for us.
@@ -198,7 +198,7 @@ Thus, we don't explicitly need a set of counts, like in the example above, becau
 are estimated under the hood for us. 
 
 Let's first demonstrate on some categorical data. For that, we must use
-[`UniqueElements`](@extref ComplexityMeasures) as the discretization (i.e. just count unique elements).
+[`UniqueElements`](@extref ComplexityMeasures.UniqueElements) as the discretization (i.e. just count unique elements).
 
 ```@example example_ConditionalEntropyShannon_JointProbabilities_CodifyVariables_UniqueElements
 using Associations
@@ -212,7 +212,7 @@ est = JointProbabilities(ConditionalEntropyShannon(), disc)
 association(est, rating, movie)
 ```
 
-### [[`JointProbabilities`](@ref) + [`CodifyPoints`](@ref) + [`UniqueElementsEncoding`](@ref)](@id example_ConditionalEntropyShannon_JointProbabilities_CodifyPoints_UniqueElementsEncoding)
+### [[`JointProbabilities`](@ref) + [`CodifyPoints`](@ref) + [`UniqueElementsEncoding`](@extref ComplexityMeasures.UniqueElementsEncoding)](@id example_ConditionalEntropyShannon_JointProbabilities_CodifyPoints_UniqueElementsEncoding)
 
 ```@example example_ConditionalEntropyShannon_JointProbabilities_CodifyPoints_UniqueElementsEncoding
 using Associations
@@ -227,7 +227,7 @@ association(est, X, Y)
 
 ## [`ConditionalEntropyTsallisAbe`](@ref)
 
-### [[`JointProbabilities`](@ref) + [`CodifyVariables`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_ConditionalEntropyTsallisAbe_JointProbabilities_CodifyVariables_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`CodifyVariables`](@ref) + [`UniqueElements`](@extref ComplexityMeasures.UniqueElements)](@id example_ConditionalEntropyTsallisAbe_JointProbabilities_CodifyVariables_UniqueElements)
 
 We'll here repeat the analysis we did for [`ConditionalEntropyShannon`](@ref) above.
 
@@ -243,7 +243,7 @@ est = JointProbabilities(ConditionalEntropyTsallisAbe(q =1.5), disc)
 association(est, rating, movie)
 ```
 
-### [[`JointProbabilities`](@ref) + [`CodifyPoints`](@ref) + [`UniqueElementsEncoding`](@ref)](@id example_ConditionalEntropyTsallisAbe_JointProbabilities_CodifyPoints_UniqueElementsEncoding)
+### [[`JointProbabilities`](@ref) + [`CodifyPoints`](@ref) + [`UniqueElementsEncoding`](@extref ComplexityMeasures.UniqueElementsEncoding)](@id example_ConditionalEntropyTsallisAbe_JointProbabilities_CodifyPoints_UniqueElementsEncoding)
 
 ```@example example_ConditionalEntropyTsallisAbe_JointProbabilities_CodifyPoints_UniqueElementsEncoding
 using Associations
@@ -259,7 +259,7 @@ association(est, X, Y)
 
 ## [`ConditionalEntropyTsallisFuruichi`](@ref)
 
-### [[`JointProbabilities`](@ref) + [`CodifyVariables`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_ConditionalEntropyTsallisFuruichi_JointProbabilities_CodifyVariables_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`CodifyVariables`](@ref) + [`UniqueElements`](@extref ComplexityMeasures.UniqueElements)](@id example_ConditionalEntropyTsallisFuruichi_JointProbabilities_CodifyVariables_UniqueElements)
 
 We'll here repeat the analysis we did for [`ConditionalEntropyShannon`](@ref) and [`ConditionalEntropyTsallisAbe`](@ref) above.
 
@@ -275,7 +275,7 @@ est = JointProbabilities(ConditionalEntropyTsallisFuruichi(q =0.5), disc)
 association(est, rating, movie)
 ```
 
-### [[`JointProbabilities`](@ref) + [`CodifyPoints`](@ref) + [`UniqueElementsEncoding`](@ref)](@id example_ConditionalEntropyTsallisFuruichi_JointProbabilities_CodifyPoints_UniqueElementsEncoding)
+### [[`JointProbabilities`](@ref) + [`CodifyPoints`](@ref) + [`UniqueElementsEncoding`](@extref ComplexityMeasures.UniqueElementsEncoding)](@id example_ConditionalEntropyTsallisFuruichi_JointProbabilities_CodifyPoints_UniqueElementsEncoding)
 
 ```@example example_ConditionalEntropyTsallisFuruichi_JointProbabilities_CodifyPoints_UniqueElementsEncoding
 using Associations
@@ -291,7 +291,7 @@ association(est, X, Y)
 
 ## [`MIShannon`](@ref)
 
-### [[`JointProbabilities`](@ref) + [`ValueBinning`](@extref ComplexityMeasures)](@id example_MIShannon_JointProbabilities_ValueBinning)
+### [[`JointProbabilities`](@ref) + [`ValueBinning`](@extref ComplexityMeasures.ValueBinning)](@id example_MIShannon_JointProbabilities_ValueBinning)
 
 ```@example mi_demonstration
 using Associations
@@ -304,7 +304,7 @@ association(est, x, y)
 ```
 
 
-### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_MIShannon_JointProbabilities_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures.UniqueElements)](@id example_MIShannon_JointProbabilities_UniqueElements)
 
 The [`JointProbabilities`](@ref) estimator can also be used with categorical data.
 For example, let's compare the Shannon mutual information between the preferences
@@ -343,7 +343,7 @@ y = rand(1000) .+ x
 association(GaussianMI(MIShannon()), x, y) # defaults to `MIShannon()`
 ```
 
-### [Dedicated [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator](@id example_MIShannon_KSG1)
+### [Dedicated [`KraskovStögbauerGrassberger2`](@ref) estimator](@id example_MIShannon_KSG1)
 
 ```@example mi_demonstration
 using Associations
@@ -351,7 +351,7 @@ x, y = rand(1000), rand(1000)
 association(KSG1(MIShannon(); k = 5), x, y)
 ```
 
-### [Dedicated [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator](@id example_MIShannon_KSG2)
+### [Dedicated [`KraskovStögbauerGrassberger2`](@ref) estimator](@id example_MIShannon_KSG2)
 
 ```@example mi_demonstration
 using Associations
@@ -359,7 +359,7 @@ x, y = rand(1000), rand(1000)
 association(KSG2(MIShannon(); k = 5), x, y)
 ```
 
-### [Dedicated [`GaoKannanOhViswanath`](@extref ComplexityMeasures) estimator](@id example_MIShannon_GaoKannanOhViswanath)
+### [Dedicated [`GaoKannanOhViswanath`](@ref) estimator](@id example_MIShannon_GaoKannanOhViswanath)
 
 ```@example mi_demonstration
 using Associations
@@ -367,9 +367,9 @@ x, y = rand(1000), rand(1000)
 association(GaoKannanOhViswanath(MIShannon(); k = 10), x, y)
 ```
 
-### [[`EntropyDecomposition`](@ref) + [`Kraskov`](@extref ComplexityMeasures)](@id example_MIShannon_EntropyDecomposition_Kraskov)
+### [[`EntropyDecomposition`](@ref) + [`Kraskov`](@extref ComplexityMeasures.Kraskov)](@id example_MIShannon_EntropyDecomposition_Kraskov)
 
-We can compute [`MIShannon`](@ref) by naively applying a [`DifferentialInfoEstimator`](@extref ComplexityMeasures).
+We can compute [`MIShannon`](@ref) by naively applying a [`DifferentialInfoEstimator`](@extref ComplexityMeasures.DifferentialInfoEstimator).
 Note that this doesn't apply any bias correction.
 
 ```@example mi_demonstration
@@ -379,9 +379,9 @@ association(EntropyDecomposition(MIShannon(), Kraskov(k = 3)), x, y)
 ```
 
 
-### [[`EntropyDecomposition`](@ref) + [`BubbleSortSwaps`](@ref)](@id example_MIShannon_EntropyDecomposition_BubbleSortSwaps)
+### [[`EntropyDecomposition`](@ref) + [`BubbleSortSwaps`](@extref ComplexityMeasures.BubbleSortSwaps)](@id example_MIShannon_EntropyDecomposition_BubbleSortSwaps)
 
-We can also compute [`MIShannon`](@ref) by naively applying a [`DiscreteInfoEstimator`](@extref ComplexityMeasures).
+We can also compute [`MIShannon`](@ref) by naively applying a [`DiscreteInfoEstimator`](@extref ComplexityMeasures.DiscreteInfoEstimator).
 Note that this doesn't apply any bias correction.
 
 ```@example mi_demonstration
@@ -393,10 +393,10 @@ association(EntropyDecomposition(MIShannon(), hest, disc), x, y)
 ```
 
 
-### [[`EntropyDecomposition`](@ref) + [`Jackknife`](@extref ComplexityMeasures) + [`ValueBinning`](@extref ComplexityMeasures)](@id example_MIShannon_EntropyDecomposition_Jackknife_ValueBinning)
+### [[`EntropyDecomposition`](@ref) + [`Jackknife`](@extref ComplexityMeasures.Jackknife) + [`ValueBinning`](@extref ComplexityMeasures.ValueBinning)](@id example_MIShannon_EntropyDecomposition_Jackknife_ValueBinning)
 
 Shannon mutual information can be written as a sum of marginal entropy terms.
-Here, we use [`CodifyVariables`](@ref) with [`ValueBinning`](@extref ComplexityMeasures) bin the data 
+Here, we use [`CodifyVariables`](@ref) with [`ValueBinning`](@extref ComplexityMeasures.ValueBinning) bin the data 
 and compute discrete Shannon mutual information.
 
 ```@example mi_demonstration
@@ -421,7 +421,7 @@ Here, we'll reproduce Figure 4 from [Kraskov2004](@citet)'s seminal paper on the
 between marginals of a bivariate Gaussian for a fixed time series length of 1000,
 varying the number of neighbors. *Note: in the original paper, they show multiple
 curves corresponding to different time series length. We only show two single curves:
-one for the [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator and one for the [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator*.
+one for the [`KraskovStögbauerGrassberger2`](@ref) estimator and one for the [`KraskovStögbauerGrassberger2`](@ref) estimator*.
 
 ```@example ex_mutualinfo
 using Associations
@@ -468,10 +468,10 @@ Most estimators suffer from significant bias when applied to discrete, finite da
 
 But instead of adding noise to your data, you can also consider using an
 estimator that is specifically designed to deal with continuous-discrete mixture data. 
-One example is the [`GaoKannanOhViswanath`](@extref ComplexityMeasures) estimator. Below, we compare its
-performance to [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) on uniformly distributed discrete multivariate data.
-The true mutual information is zero. While the "naive" [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator 
-diverges from the true value for these data, the [`GaoKannanOhViswanath`](@extref ComplexityMeasures)
+One example is the [`GaoKannanOhViswanath`](@ref) estimator. Below, we compare its
+performance to [`KraskovStögbauerGrassberger2`](@ref) on uniformly distributed discrete multivariate data.
+The true mutual information is zero. While the "naive" [`KraskovStögbauerGrassberger2`](@ref) estimator 
+diverges from the true value for these data, the [`GaoKannanOhViswanath`](@ref)
 converges to the true value.
 
 ```@example ex_mutualinfo
@@ -548,7 +548,7 @@ axislegend(position = :rb)
 fig
 ```
 
-### Estimation using [`DifferentialInfoEstimator`](@extref ComplexityMeasures)s: a comparison
+### Estimation using [`DifferentialInfoEstimator`](@extref ComplexityMeasures.DifferentialInfoEstimator)s: a comparison
 
 Let's compare the performance of a subset of the implemented mutual information estimators. We'll use example data from Lord et al., where the analytical mutual information is known.
 
@@ -775,15 +775,15 @@ fig = plot_results(family3, ifamily3;
     estimators = estimators, base = base)
 ```
 
-We see that the [`Lord`](@extref ComplexityMeasures) estimator, which estimates local volume elements using a singular-value decomposition (SVD) of local neighborhoods, outperforms the other estimators by a large margin.
+We see that the [`Lord`](@extref ComplexityMeasures.Lord) estimator, which estimates local volume elements using a singular-value decomposition (SVD) of local neighborhoods, outperforms the other estimators by a large margin.
 
 
 ## [`MIRenyiJizba`](@ref)
 
-### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_MIRenyiJizba_JointProbabilities_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures.UniqueElements)](@id example_MIRenyiJizba_JointProbabilities_UniqueElements)
 
 [`MIRenyiJizba`](@ref) can be estimated for categorical data using [`JointProbabilities`](@ref) estimator
-with the [`UniqueElements`](@extref ComplexityMeasures) outcome space.
+with the [`UniqueElements`](@extref ComplexityMeasures.UniqueElements) outcome space.
 
 ```@example example_mirenyijizba
 using Associations
@@ -794,11 +794,11 @@ est = JointProbabilities(MIRenyiJizba(), UniqueElements())
 association(est, x, y)
 ```
 
-### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures)](@id example_MIRenyiJizba_JointProbabilities_LeonenkoProzantoSavani)
+### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures.LeonenkoProzantoSavani)](@id example_MIRenyiJizba_JointProbabilities_LeonenkoProzantoSavani)
 
 [`MIRenyiJizba`](@ref) can also estimated for numerical data using [`EntropyDecomposition`](@ref)
-in combination with any [`DifferentialInfoEstimator`](@extref ComplexityMeasures) capable of estimating differential 
-[`Renyi`](@extref ComplexityMeasures) entropy.
+in combination with any [`DifferentialInfoEstimator`](@extref ComplexityMeasures.DifferentialInfoEstimator) capable of estimating differential 
+[`Renyi`](@extref ComplexityMeasures.Renyi) entropy.
 
 ```@example example_MIRenyiJizba
 using Associations
@@ -809,11 +809,11 @@ est_diff = EntropyDecomposition(def, LeonenkoProzantoSavani(Renyi(), k=3))
 association(est_diff, x, y) 
 ```
 
-### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures)](@id example_MIRenyiJizba_EntropyDecomposition_ValueBinning)
+### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures.LeonenkoProzantoSavani)](@id example_MIRenyiJizba_EntropyDecomposition_ValueBinning)
 
 [`MIRenyiJizba`](@ref) can also estimated for numerical data using [`EntropyDecomposition`](@ref)
-in combination with any [`DiscreteInfoEstimator`](@extref ComplexityMeasures) capable of estimating differential 
-[`Renyi`](@extref ComplexityMeasures) entropy over some [`OutcomeSpace`](@ref), e.g. [`ValueBinning`](@extref ComplexityMeasures).
+in combination with any [`DiscreteInfoEstimator`](@extref ComplexityMeasures.DiscreteInfoEstimator) capable of estimating differential 
+[`Renyi`](@extref ComplexityMeasures.Renyi) entropy over some [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace), e.g. [`ValueBinning`](@extref ComplexityMeasures.ValueBinning).
 
 
 ```@example example_MIRenyiJizba
@@ -832,7 +832,7 @@ association(est_disc, x, y)
 [`MIRenyiSarbu`](@ref) can be estimated using the [`JointProbabilities`](@ref) estimator 
 in combination with any [`CodifyVariables`](@ref) or [`CodifyPoints`](@ref) discretization scheme.
 
-### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_MIRenyiSarbu_JointProbabilities_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures.UniqueElements)](@id example_MIRenyiSarbu_JointProbabilities_UniqueElements)
 
 ```@example example_MIRenyiSarbu
 using Associations
@@ -844,7 +844,7 @@ est = JointProbabilities(MIRenyiSarbu(), CodifyVariables(UniqueElements()))
 association(est, x, y)
 ```
 
-### [[`JointProbabilities`](@ref) + [`CosineSimilarityBinning`](@ref)](@id example_MIRenyiSarbu_JointProbabilities_CosineSimilarityBinning)
+### [[`JointProbabilities`](@ref) + [`CosineSimilarityBinning`](@extref ComplexityMeasures.CosineSimilarityBinning)](@id example_MIRenyiSarbu_JointProbabilities_CosineSimilarityBinning)
 
 ```@example example_MIRenyiSarbu
 using Associations
@@ -858,7 +858,7 @@ association(est, x, y)
 
 ## [`MITsallisFuruichi`](@ref)
 
-### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_MITsallisFuruichi_JointProbabilities_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures.UniqueElements)](@id example_MITsallisFuruichi_JointProbabilities_UniqueElements)
 
 [`MITsallisFuruichi`](@ref) can be estimated using the [`JointProbabilities`](@ref) estimator 
 in combination with any [`CodifyVariables`](@ref) or [`CodifyPoints`](@ref) discretization scheme.
@@ -873,7 +873,7 @@ est = JointProbabilities(MITsallisFuruichi(q = 0.3), UniqueElements())
 association(est, x, y) 
 ```
 
-### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures)](@id example_MITsallisFuruichi_EntropyDecomposition_LeonenkoProzantoSavani)
+### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures.LeonenkoProzantoSavani)](@id example_MITsallisFuruichi_EntropyDecomposition_LeonenkoProzantoSavani)
 
 ```@example example_MITsallisFuruichi
 using Associations
@@ -886,7 +886,7 @@ association(est_diff, x, y)
 ```
 
 
-### [[`EntropyDecomposition`](@ref) + [`Dispersion`](@extref ComplexityMeasures)](@id example_MITsallisFuruichi_EntropyDecomposition_Dispersion)
+### [[`EntropyDecomposition`](@ref) + [`Dispersion`](@extref ComplexityMeasures.Dispersion)](@id example_MITsallisFuruichi_EntropyDecomposition_Dispersion)
 
 ```@example example_MITsallisFuruichi
 using Associations
@@ -902,7 +902,7 @@ association(est_disc, x, y)
 
 ## [`MITsallisMartin`](@ref)
 
-### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures)](@id example_MITsallisMartin_JointProbabilities_UniqueElements)
+### [[`JointProbabilities`](@ref) + [`UniqueElements`](@extref ComplexityMeasures.UniqueElements)](@id example_MITsallisMartin_JointProbabilities_UniqueElements)
 
 ```@example example_MITsallisMartin
 using Associations
@@ -914,11 +914,11 @@ est = JointProbabilities(MITsallisMartin(q = 1.5), UniqueElements())
 association(est, x, y) 
 ```
 
-### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures)](@id example_MITsallisMartin_EntropyDecomposition_LeonenkoProzantoSavani)
+### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures.LeonenkoProzantoSavani)](@id example_MITsallisMartin_EntropyDecomposition_LeonenkoProzantoSavani)
 
 [`MITsallisMartin`](@ref) can be estimated using a decomposition into entropy 
 terms using [`EntropyDecomposition`](@ref) with any compatible estimator 
-that can estimate differential [`Tsallis`](@extref ComplexityMeasures) entropy. 
+that can estimate differential [`Tsallis`](@extref ComplexityMeasures.Tsallis) entropy. 
 
 
 ```@example example_MITsallisMartin
@@ -931,7 +931,7 @@ est_diff = EntropyDecomposition(MITsallisMartin(), LeonenkoProzantoSavani(Tsalli
 association(est_diff, x, y)
 ```
 
-### [[`EntropyDecomposition`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_MITsallisMartin_EntropyDecomposition_OrdinalPatterns)
+### [[`EntropyDecomposition`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)](@id example_MITsallisMartin_EntropyDecomposition_OrdinalPatterns)
 
 
 ```@example 
@@ -1072,7 +1072,7 @@ taking the difference of mutual information terms.
 
 ## [`CMIShannon`](@ref)
 
-### [[`MIDecomposition`](@ref) + [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures)](@id example_CMIShannon_MIDecomposition_KSG1)
+### [[`MIDecomposition`](@ref) + [`KraskovStögbauerGrassberger2`](@ref)](@id example_CMIShannon_MIDecomposition_KSG1)
 
 ```@example mi_demonstration
 using Associations
@@ -1095,7 +1095,7 @@ association(est, x, z, y)
 
 ## [`ShortExpansionConditionalMutualInformation`](@ref)
 
-### [[`JointProbabilities`](@ref) with [`CodifyVariables`](@ref) and [`ValueBinning`](@extref ComplexityMeasures)](@id example_ShortExpansionConditionalMutualInformation_JointProbabilities_CodifyVariables_ValueBinning)
+### [[`JointProbabilities`](@ref) with [`CodifyVariables`](@ref) and [`ValueBinning`](@extref ComplexityMeasures.ValueBinning)](@id example_ShortExpansionConditionalMutualInformation_JointProbabilities_CodifyVariables_ValueBinning)
 
 ```@example
 using Associations
@@ -1111,9 +1111,9 @@ est = JointProbabilities(SECMI(base = 2), CodifyVariables(ValueBinning(3)))
 association(est, x, z, y)
 ```
 
-### [[`EntropyDecomposition`](@ref) + [`Kraskov`](@extref ComplexityMeasures)](@id example_CMIShannon_EntropyDecomposition_Kraskov)
+### [[`EntropyDecomposition`](@ref) + [`Kraskov`](@extref ComplexityMeasures.Kraskov)](@id example_CMIShannon_EntropyDecomposition_Kraskov)
 
-Any [`DifferentialInfoEstimator`](@extref ComplexityMeasures) can also be used to compute conditional
+Any [`DifferentialInfoEstimator`](@extref ComplexityMeasures.DifferentialInfoEstimator) can also be used to compute conditional
 mutual information using a sum of entropies. For that, we 
 usethe [`EntropyDecomposition`](@ref) estimator. No bias correction is applied for 
 [`EntropyDecomposition`](@ref) either.
@@ -1131,12 +1131,12 @@ est = EntropyDecomposition(CMIShannon(), Kraskov(k = 5))
 association(est, x, z, y)
 ```
 
-Any [`DiscreteInfoEstimator`](@extref ComplexityMeasures) that computes entropy can also be used to compute
+Any [`DiscreteInfoEstimator`](@extref ComplexityMeasures.DiscreteInfoEstimator) that computes entropy can also be used to compute
 conditional mutual information using a sum of entropies. For that, we also
 use [`EntropyDecomposition`](@ref). In the discrete case, we also have to specify a
-discretization (an [`OutcomeSpace`](@ref)).
+discretization (an [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace)).
 
-### [[`EntropyDecomposition`](@ref) + [`ValueBinning`](@extref ComplexityMeasures)](@id example_CMIShannon_EntropyDecomposition_ValueBinning)
+### [[`EntropyDecomposition`](@ref) + [`ValueBinning`](@extref ComplexityMeasures.ValueBinning)](@id example_CMIShannon_EntropyDecomposition_ValueBinning)
 
 ```@example
 using Associations
@@ -1155,7 +1155,7 @@ association(est, x, y, z)
 
 ## [`CMIRenyiJizba`](@ref)
 
-### [[`JointProbabilities`](@ref) + [`BubbleSortSwaps`](@ref)](@id example_CMIRenyiJizba_JointProbabilities_BubbleSortSwaps)
+### [[`JointProbabilities`](@ref) + [`BubbleSortSwaps`](@extref ComplexityMeasures.BubbleSortSwaps)](@id example_CMIRenyiJizba_JointProbabilities_BubbleSortSwaps)
 
 ```@example example_CMIRenyiJizba
 using Associations
@@ -1169,7 +1169,7 @@ association(est, x, z, y)
 ```
 
 
-### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures)](@id example_CMIRenyiJizba_EntropyDecomposition_LeonenkoProzantoSavani)
+### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures.LeonenkoProzantoSavani)](@id example_CMIRenyiJizba_EntropyDecomposition_LeonenkoProzantoSavani)
 
 ```@example example_CMIRenyiJizba
 using Associations
@@ -1183,7 +1183,7 @@ association(est, x, y, z)
 ```
 
 
-### [[`EntropyDecomposition`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures)](@id example_CMIRenyiJizba_EntropyDecomposition_OrdinalPatterns)
+### [[`EntropyDecomposition`](@ref) + [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)](@id example_CMIRenyiJizba_EntropyDecomposition_OrdinalPatterns)
 
 ```@example example_CMIRenyiJizba
 using Associations
@@ -1198,7 +1198,7 @@ association(est, x, y, z)
 
 ## [`TEShannon`](@ref)
 
-### [[`EntropyDecomposition`](@extref ComplexityMeasures) + [`TransferOperator`](@extref ComplexityMeasures)](@id example_TEShannon_EntropyDecomposition_TransferOperator)
+### [[`EntropyDecomposition`](@ref) + [`TransferOperator`](@extref ComplexityMeasures.TransferOperator)](@id example_TEShannon_EntropyDecomposition_TransferOperator)
 
 For transfer entropy examples, we'll construct some time series for which 
 there is time-delayed forcing between variables.
@@ -1280,7 +1280,7 @@ association(est, x, z, y) # should be near 0 (and can be negative)
 ### [[`SymbolicTransferEntropy`](@ref) estimator](@id example_TEShannon_SymbolicTransferEntropy)
 
 The [`SymbolicTransferEntropy`](@ref) estimator is just a convenience wrapper which utilizes
-[`CodifyVariables`](@ref)with the [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space to 
+[`CodifyVariables`](@ref)with the [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns) outcome space to 
 discretize the input time series before computing transfer entropy.
 
 We'll use coupled time series from the `logistic4` system above, where `x → y → z → w`.
@@ -1306,9 +1306,9 @@ We will test
 
 - The [`Lindner`](@ref) and [`Zhu1`](@ref) dedicated transfer entropy estimators,
     which try to eliminate bias.
-- The [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator, which computes TE naively as a sum of mutual information
+- The [`KraskovStögbauerGrassberger2`](@ref) estimator, which computes TE naively as a sum of mutual information
     terms (without guaranteed cancellation of biases for the total sum).
-- The [`Kraskov`](@extref ComplexityMeasures) estimator, which computes TE naively as a sum of entropy 
+- The [`Kraskov`](@extref ComplexityMeasures.Kraskov) estimator, which computes TE naively as a sum of entropy 
     terms (without guaranteed cancellation of biases for the total sum).
 
 ```@example
@@ -1383,7 +1383,7 @@ fig
 Let's try to reproduce the results from Schreiber's original paper [Schreiber2000](@cite) where
 he introduced the transfer entropy. We'll here use the [`JointProbabilities`](@ref) estimator,
 discretizing per column of the input data using the [`CodifyVariables`](@ref) discretization
-scheme with the [`ValueBinning`](@extref ComplexityMeasures) outcome space.
+scheme with the [`ValueBinning`](@extref ComplexityMeasures.ValueBinning) outcome space.
 
 ```@example example_te_schreiber
 using Associations
@@ -1484,7 +1484,7 @@ The plot above shows the original transfer entropies (solid lines) and the 95th
 
 ## [`TERenyiJizba`](@ref)
 
-### [[`EntropyDecomposition`](@extref ComplexityMeasures) + [`TransferOperator`](@extref ComplexityMeasures)](@id example_TERenyiJizba_EntropyDecomposition_TransferOperator)
+### [[`EntropyDecomposition`](@ref) + [`TransferOperator`](@extref ComplexityMeasures.TransferOperator)](@id example_TERenyiJizba_EntropyDecomposition_TransferOperator)
 
 We can perform the same type of analysis as above using [`TERenyiJizba`](@ref)
 instead of [`TEShannon`](@ref).
diff --git a/docs/src/examples/examples_independence.md b/docs/src/examples/examples_independence.md
index 0ccad560..faff15ac 100644
--- a/docs/src/examples/examples_independence.md
+++ b/docs/src/examples/examples_independence.md
@@ -387,7 +387,7 @@ end
 
 ### [[`CMIShannon`](@ref)](@id example_LocalPermutationTest_CMIShannon)
 
-To estimate CMI, we'll use the [`Kraskov`](@extref ComplexityMeasures) differential
+To estimate CMI, we'll use the [`Kraskov`](@extref ComplexityMeasures.Kraskov) differential
 entropy estimator, which naively computes CMI as a sum of entropy terms without guaranteed
 bias cancellation.
 
@@ -504,7 +504,7 @@ independence(test, x, z, y)
 
 ## [[`JointProbabilities`](@ref) estimation on categorical data](@id example_SECMITEST_JointProbabilities_CodifyVariables_UniqueElements)
 
-Note that this also works for categorical variables. Just use [`UniqueElements`](@extref ComplexityMeasures) to 
+Note that this also works for categorical variables. Just use [`UniqueElements`](@extref ComplexityMeasures.UniqueElements) to 
 discretize!
 
 ```@example example_SECMITest_categorical
diff --git a/src/core.jl b/src/core.jl
index 2f9664d3..6cca5ccd 100644
--- a/src/core.jl
+++ b/src/core.jl
@@ -105,7 +105,7 @@ Concrete subtypes are given as input to [`association`](@ref).
 | [`ConvergentCrossMapping`](@ref)                     | [`RandomVectors`](@ref), [`RandomSegment`](@ref)                                                                                                                                                                             |
 | [`MCR`](@ref)                                        | Not required                                                                                                                                                                                                                 |
 | [`RMCD`](@ref)                                       | Not required                                                                                                                                                                                                                 |
-| [`MIShannon`](@ref)                                  | [`JointProbabilities`](@ref), [`EntropyDecomposition`](@ref), [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures), [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures), [`GaoOhViswanath`](@ref), [`GaoKannanOhViswanath`](@extref ComplexityMeasures), [`GaussianMI`](@ref) |
+| [`MIShannon`](@ref)                                  | [`JointProbabilities`](@ref), [`EntropyDecomposition`](@ref), [`KraskovStögbauerGrassberger2`](@ref), [`KraskovStögbauerGrassberger2`](@ref), [`GaoOhViswanath`](@ref), [`GaoKannanOhViswanath`](@ref), [`GaussianMI`](@ref) |
 | [`MIRenyiJizba`](@ref)                               | [`JointProbabilities`](@ref), [`EntropyDecomposition`](@ref)                                                                                                                                                                 |
 | [`MIRenyiSarbu`](@ref)                               | [`JointProbabilities`](@ref)                                                                                                                                                                                                 |
 | [`MITsallisFuruichi`](@ref)                          | [`JointProbabilities`](@ref), [`EntropyDecomposition`](@ref)                                                                                                                                                                 |
diff --git a/src/methods/information/core.jl b/src/methods/information/core.jl
index b1a95008..8859feda 100644
--- a/src/methods/information/core.jl
+++ b/src/methods/information/core.jl
@@ -27,10 +27,10 @@ The supertype for all estimators of multivariate information measures.
 
 [`MutualInformationEstimator`](@ref)s:
 
-- [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures)
-- [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures)
+- [`KraskovStögbauerGrassberger2`](@ref)
+- [`KraskovStögbauerGrassberger2`](@ref)
 - [`GaoOhViswanath`](@ref)
-- [`GaoKannanOhViswanath`](@extref ComplexityMeasures)
+- [`GaoKannanOhViswanath`](@ref)
 - [`GaussianMI`](@ref)
 
 [`ConditionalMutualInformationEstimator`](@ref)s:
@@ -56,10 +56,10 @@ The supertype for dedicated [`MutualInformation`](@ref) estimators.
 
 ## Concrete implementations
 
-- [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures)
-- [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures)
+- [`KraskovStögbauerGrassberger2`](@ref)
+- [`KraskovStögbauerGrassberger2`](@ref)
 - [`GaoOhViswanath`](@ref)
-- [`GaoKannanOhViswanath`](@extref ComplexityMeasures)
+- [`GaoKannanOhViswanath`](@ref)
 - [`GaussianMI`](@ref)
 """
 abstract type MutualInformationEstimator{M} <: BivariateInformationMeasureEstimator{M} end
diff --git a/src/methods/information/counts_and_probs/counts.jl b/src/methods/information/counts_and_probs/counts.jl
index dd6dc996..36263c03 100644
--- a/src/methods/information/counts_and_probs/counts.jl
+++ b/src/methods/information/counts_and_probs/counts.jl
@@ -20,13 +20,13 @@ Construct an `N`-dimensional contingency table from the input iterables
 `x₁, x₂, ..., xₙ` which are such that 
 `length(x₁) == length(x₂) == ⋯ == length(xₙ)`.
 
-If `x₁, x₂, ..., xₙ` are already discrete, then use [`UniqueElements`](@extref ComplexityMeasures) as 
+If `x₁, x₂, ..., xₙ` are already discrete, then use [`UniqueElements`](@extref ComplexityMeasures.UniqueElements) as 
 the first argument to directly construct the joint contingency table.
 
 If `x₁, x₂, ..., xₙ` need to be discretized, provide as the first argument
 - [`CodifyPoints`](@ref) (encodes every *point* in each of the input variables `xᵢ`s individually)
 - [`CodifyVariables`](@ref) (encodes every `xᵢ` individually using a sliding window encoding). NB: If 
-    using different [`OutcomeSpace`](@ref)s for the different `xᵢ`, then [`total_outcomes`](@ref) must 
+    using different [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace)s for the different `xᵢ`, then [`total_outcomes`](@extref ComplexityMeasures.total_outcomes) must 
     be the same for every outcome space.
 
 ## Examples
@@ -52,7 +52,7 @@ z = rand([(1, 2), (2, 1)], n)
 counts(UniqueElements(), x, y, z)
 ```
 
-See also: [`CodifyPoints`](@ref), [`CodifyVariables`](@ref), [`UniqueElements`](@extref ComplexityMeasures), [`OutcomeSpace`](@ref),
+See also: [`CodifyPoints`](@ref), [`CodifyVariables`](@ref), [`UniqueElements`](@extref ComplexityMeasures.UniqueElements), [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace),
 [`probabilities`](@ref).
 """
 function counts(o::UniqueElements, x::Vararg{VectorOrStateSpaceSet,N}) where N # this extends ComplexityMeasures.jl definition
diff --git a/src/methods/information/counts_and_probs/encoding/codify_points.jl b/src/methods/information/counts_and_probs/encoding/codify_points.jl
index 0a53ce8e..a4fc2d04 100644
--- a/src/methods/information/counts_and_probs/encoding/codify_points.jl
+++ b/src/methods/information/counts_and_probs/encoding/codify_points.jl
@@ -19,24 +19,24 @@ export codify
 
 ## Compatible encodings
 
-- [`GaussianCDFEncoding`](@ref)
-- [`OrdinalPatternEncoding`](@ref)
-- [`RelativeMeanEncoding`](@ref)
-- [`RelativeFirstDifferenceEncoding`](@ref)
-- [`UniqueElementsEncoding`](@ref)
-- [`RectangularBinEncoding`](@ref)
-- [`CombinationEncoding`](@ref)
+- [`GaussianCDFEncoding`](@extref ComplexityMeasures.GaussianCDFEncoding)
+- [`OrdinalPatternEncoding`](@extref ComplexityMeasures.OrdinalPatternEncoding)
+- [`RelativeMeanEncoding`](@extref ComplexityMeasures.RelativeMeanEncoding)
+- [`RelativeFirstDifferenceEncoding`](@extref ComplexityMeasures.RelativeFirstDifferenceEncoding)
+- [`UniqueElementsEncoding`](@extref ComplexityMeasures.UniqueElementsEncoding)
+- [`RectangularBinEncoding`](@extref ComplexityMeasures.RectangularBinEncoding)
+- [`CombinationEncoding`](@extref ComplexityMeasures.CombinationEncoding)
 
 ## Description
 
 Given `x::AbstractStateSpaceSet...`, where the `i`-th dataset is assumed to represent
 a single series of measurements, `CodifyPoints` encodes each point `pₖ ∈ x[i]` 
-using some [`Encoding`](@ref)(s), *without* applying any (sequential) transformation to
+using some [`Encoding`](@extref ComplexityMeasures.Encoding)(s), *without* applying any (sequential) transformation to
 the `x[i]` first. This behaviour is different to [`CodifyVariables`](@ref), which
 *does* apply a transformation to `x[i]` before encoding.
 
 If `length(x) == N` (i.e. there are `N` input dataset), then `encodings` must be a tuple
-of `N` [`Encoding`](@ref). Alternatively, if `encodings` is a single [`Encoding`](@ref),
+of `N` [`Encoding`](@extref ComplexityMeasures.Encoding). Alternatively, if `encodings` is a single [`Encoding`](@extref ComplexityMeasures.Encoding),
 then that same encoding is applied to every `x[i]`.
 
 ## Examples
@@ -58,8 +58,8 @@ cx, cy, cz = codify(d, x, y, z)
 ```
 """
 struct CodifyPoints{N} <: Discretization{N}
-    encodings::NTuple{N, Encoding}
-    function CodifyPoints(encodings::NTuple{N, Encoding}) where N
+    encodings::NTuple{N,Encoding}
+    function CodifyPoints(encodings::NTuple{N,Encoding}) where N
         if !(N ≥ 1)
             throw(ArgumentError("CodifyPoints requires at least 1 dimensions"))
         end
@@ -68,7 +68,7 @@ struct CodifyPoints{N} <: Discretization{N}
 end
 Base.getindex(e::CodifyPoints, i) = getindex(e.encodings, i)
 
-function CodifyPoints(encodings::Vararg{Encoding, N}) where N
+function CodifyPoints(encodings::Vararg{Encoding,N}) where N
     return CodifyPoints(tuple(encodings...))
 end
 
@@ -103,27 +103,27 @@ codify(CodifyPoints(ex, ey, ez), x, y, z)
 """
 function codify(encoding::CodifyPoints, x) end
 
-function codify(encoding::CodifyPoints{1}, x::Vararg{Any, 1})
+function codify(encoding::CodifyPoints{1}, x::Vararg{Any,1})
     e = first(encoding.encodings)
     x̂ = codify_individual_dataset(e, first(x))
     return x̂::Vector{<:Integer}
 end
 
 # Apply the same encoding to all input datasets.
-function codify(encoding::CodifyPoints{1}, x::Vararg{Any, M}) where {M}
+function codify(encoding::CodifyPoints{1}, x::Vararg{Any,M}) where {M}
     verify_input(encoding, x...)
     e = first(encoding.encodings)
     x̂ = map(k -> codify_individual_dataset(e, x[k]), tuple(1:M...))
 
-    return x̂::NTuple{M, Vector{<:Integer}}
+    return x̂::NTuple{M,Vector{<:Integer}}
 end
 
 
-function codify(encoding::CodifyPoints{N}, x::Vararg{Any, M}) where {N, M}
+function codify(encoding::CodifyPoints{N}, x::Vararg{Any,M}) where {N,M}
     verify_input(encoding, x...)
     x̂ = map(k -> codify_individual_dataset(encoding[k], x[k]), tuple(1:M...))
 
-    return x̂::NTuple{M, Vector{<:Integer}}
+    return x̂::NTuple{M,Vector{<:Integer}}
 end
 
 function verify_input(encoding::CodifyPoints{N}, x...) where N
@@ -153,9 +153,9 @@ function codify_individual_dataset(encoding::Encoding, x)
     return x̂
 end
 
- # The decoding step on the second-to-last line is not possible without actually providing
- # the encodings. Therefore, we need to override the Generic implementation of
- # `counts`.
+# The decoding step on the second-to-last line is not possible without actually providing
+# the encodings. Therefore, we need to override the Generic implementation of
+# `counts`.
 function counts(encoding::CodifyPoints, x...)
     # This converts each dataset `x[i]::StateSpaceSet` into `x̂[i]::Vector{Int}`,
     # where `length(x[i]) == length(x̂[i])`.
diff --git a/src/methods/information/counts_and_probs/encoding/codify_variables.jl b/src/methods/information/counts_and_probs/encoding/codify_variables.jl
index f5dbde6d..0281d437 100644
--- a/src/methods/information/counts_and_probs/encoding/codify_variables.jl
+++ b/src/methods/information/counts_and_probs/encoding/codify_variables.jl
@@ -18,16 +18,16 @@ using the given `outcome_space`.
 
 ## Compatible outcome spaces
 
-- [`UniqueElements`](@extref ComplexityMeasures) (for when data are pre-discretized)
-- [`BubbleSortSwaps`](@ref)
-- [`CosineSimilarityBinning`](@ref)
-- [`OrdinalPatterns`](@extref ComplexityMeasures)
-- [`Dispersion`](@extref ComplexityMeasures)
+- [`UniqueElements`](@extref ComplexityMeasures.UniqueElements) (for when data are pre-discretized)
+- [`BubbleSortSwaps`](@extref ComplexityMeasures.BubbleSortSwaps)
+- [`CosineSimilarityBinning`](@extref ComplexityMeasures.CosineSimilarityBinning)
+- [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)
+- [`Dispersion`](@extref ComplexityMeasures.Dispersion)
 
 # Description
 
 The main difference between `CodifyVariables` and [`CodifyPoints`] is that the former
-uses [`OutcomeSpace`](@ref)s for discretization. This usually means that some
+uses [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace)s for discretization. This usually means that some
 transformation is applied to the data before discretizing. For example, some outcome
 constructs a delay embedding from the input (and thus encodes sequential information)
 before encoding the data.
@@ -35,7 +35,7 @@ before encoding the data.
 Specifically, given `x::AbstractStateSpaceSet...`, where the `i`-th dataset `x[i]` 
 is assumed to represent a single series of measurements, `CodifyVariables` encodes
  `x[i]` by [`codify`](@ref)-ing into a series of integers 
-using an appropriate  [`OutcomeSpace`](@ref). This is typically done by first 
+using an appropriate  [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace). This is typically done by first 
 sequentially transforming the data and then running sliding window (the width of 
 the window is controlled by `outcome_space`) across the data, and then encoding the 
 values within each window to an integer.
diff --git a/src/methods/information/counts_and_probs/probabilities.jl b/src/methods/information/counts_and_probs/probabilities.jl
index 3751c3d4..2c192bde 100644
--- a/src/methods/information/counts_and_probs/probabilities.jl
+++ b/src/methods/information/counts_and_probs/probabilities.jl
@@ -12,16 +12,16 @@ export marginal
     probabilities(encoding::CodifyPoints, x₁, x₂, ..., xₙ) → Counts{N}
     probabilities(encoding::CodifyVariables, x₁, x₂, ..., xₙ) → Counts{N}
 
-Construct an `N`-dimensional [`Probabilities`](@ref) array from the input iterables
+Construct an `N`-dimensional [`Probabilities`](@extref ComplexityMeasures.Probabilities) array from the input iterables
 `x₁, x₂, ..., xₙ` which are such that 
 `length(x₁) == length(x₂) == ⋯ == length(xₙ)`.
 
 ## Description
 
 Probabilities are computed by first constructing a joint contingency matrix in the form 
-of a [`Counts`](@ref) instance. 
+of a [`Counts`](@extref ComplexityMeasures.Counts) instance. 
 
-If `x₁, x₂, ..., xₙ` are already discrete, then use [`UniqueElements`](@extref ComplexityMeasures) as 
+If `x₁, x₂, ..., xₙ` are already discrete, then use [`UniqueElements`](@extref ComplexityMeasures.UniqueElements) as 
 the first argument to directly construct the joint contingency table.
 
 If `x₁, x₂, ..., xₙ` need to be discretized, provide as the first argument
@@ -51,7 +51,7 @@ z = rand([(1, 2), (2, 1)], n)
 probabilities(UniqueElements(), x, y, z)
 ```
 
-See also: [`CodifyPoints`](@ref), [`CodifyVariables`](@ref), [`UniqueElements`](@extref ComplexityMeasures), [`OutcomeSpace`](@ref).
+See also: [`CodifyPoints`](@ref), [`CodifyVariables`](@ref), [`UniqueElements`](@extref ComplexityMeasures.UniqueElements), [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace).
 """
 function probabilities(o::OutcomeSpace) end
 
diff --git a/src/methods/information/definitions/conditional_entropies/ConditionalEntropyShannon.jl b/src/methods/information/definitions/conditional_entropies/ConditionalEntropyShannon.jl
index 3cbab77e..ef1ee635 100644
--- a/src/methods/information/definitions/conditional_entropies/ConditionalEntropyShannon.jl
+++ b/src/methods/information/definitions/conditional_entropies/ConditionalEntropyShannon.jl
@@ -7,7 +7,7 @@ export ConditionalEntropyShannon
     ConditionalEntropyShannon <: ConditionalEntropy
     ConditionalEntropyShannon(; base = 2)
 
-The [`Shannon`](@extref ComplexityMeasures) conditional entropy measure.
+The [`Shannon`](@extref ComplexityMeasures.Shannon) conditional entropy measure.
 
 ## Usage 
 
@@ -40,9 +40,9 @@ Equivalently, the following differenConditionalEntropy of entropies hold
 H^S(X | Y) = H^S(X, Y) - H^S(Y),
 ```
 
-where ``H^S(\\cdot)`` and ``H^S(\\cdot | \\cdot)`` are the [`Shannon`](@extref ComplexityMeasures) entropy and
+where ``H^S(\\cdot)`` and ``H^S(\\cdot | \\cdot)`` are the [`Shannon`](@extref ComplexityMeasures.Shannon) entropy and
 Shannon joint entropy, respectively. This is the definition used when calling
-[`association`](@ref) with a [`ProbabilitiesEstimator`](@extref ComplexityMeasures).
+[`association`](@ref) with a [`ProbabilitiesEstimator`](@extref ComplexityMeasures.ProbabilitiesEstimator).
 
 ## Differential definition
 
@@ -52,19 +52,19 @@ The differential conditional Shannon entropy is analogously defined as
 H^S(X | Y) = h^S(X, Y) - h^S(Y),
 ```
 
-where ``h^S(\\cdot)`` and ``h^S(\\cdot | \\cdot)`` are the [`Shannon`](@extref ComplexityMeasures)
+where ``h^S(\\cdot)`` and ``h^S(\\cdot | \\cdot)`` are the [`Shannon`](@extref ComplexityMeasures.Shannon)
 differential entropy and Shannon joint differential entropy, respectively. This is the
 definition used when calling [`association`](@ref) with a
-[`DifferentialInfoEstimator`](@extref ComplexityMeasures).
+[`DifferentialInfoEstimator`](@extref ComplexityMeasures.DifferentialInfoEstimator).
 
 ## Estimation
 
 - [Example 1](@ref example_ConditionalEntropyShannon_analytical): Analytical example from Cover & Thomas's book.
 - [Example 2](@ref example_ConditionalEntropyShannon_JointProbabilities_CodifyVariables_UniqueElements): 
     [`JointProbabilities`](@ref) estimator with[`CodifyVariables`](@ref) discretization and 
-    [`UniqueElements`](@extref ComplexityMeasures) outcome space on categorical data.
+    [`UniqueElements`](@extref ComplexityMeasures.UniqueElements) outcome space on categorical data.
 - [Example 3](@ref example_ConditionalEntropyShannon_JointProbabilities_CodifyPoints_UniqueElementsEncoding): 
-    [`JointProbabilities`](@ref) estimator with [`CodifyPoints`](@ref) discretization and [`UniqueElementsEncoding`](@ref)
+    [`JointProbabilities`](@ref) estimator with [`CodifyPoints`](@ref) discretization and [`UniqueElementsEncoding`](@extref ComplexityMeasures.UniqueElementsEncoding)
     encoding of points on numerical data.
 """
 Base.@kwdef struct ConditionalEntropyShannon{B} <: ConditionalEntropy
diff --git a/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisAbe.jl b/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisAbe.jl
index 7f4205d8..20b378c2 100644
--- a/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisAbe.jl
+++ b/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisAbe.jl
@@ -26,16 +26,16 @@ Abe & Rajagopal's Tsallis conditional entropy between discrete random variables
 H_q^{T_A}(X | Y) = \\dfrac{H_q^T(X, Y) - H_q^T(Y)}{1 + (1-q)H_q^T(Y)},
 ```
 
-where ``H_q^T(\\cdot)`` and ``H_q^T(\\cdot, \\cdot)`` is the [`Tsallis`](@extref ComplexityMeasures)
+where ``H_q^T(\\cdot)`` and ``H_q^T(\\cdot, \\cdot)`` is the [`Tsallis`](@extref ComplexityMeasures.Tsallis)
 entropy and the joint Tsallis entropy.
 
 ## Estimation
 
 - [Example 1](@ref example_ConditionalEntropyTsallisAbe_JointProbabilities_CodifyVariables_UniqueElements): 
     [`JointProbabilities`](@ref) estimator with[`CodifyVariables`](@ref) discretization and 
-    [`UniqueElements`](@extref ComplexityMeasures) outcome space on categorical data.
+    [`UniqueElements`](@extref ComplexityMeasures.UniqueElements) outcome space on categorical data.
 - [Example 2](@ref example_ConditionalEntropyTsallisAbe_JointProbabilities_CodifyPoints_UniqueElementsEncoding): 
-    [`JointProbabilities`](@ref) estimator with [`CodifyPoints`](@ref) discretization and [`UniqueElementsEncoding`](@ref)
+    [`JointProbabilities`](@ref) estimator with [`CodifyPoints`](@ref) discretization and [`UniqueElementsEncoding`](@extref ComplexityMeasures.UniqueElementsEncoding)
     encoding of points on numerical data.
 """
 Base.@kwdef struct ConditionalEntropyTsallisAbe{B,Q} <: ConditionalEntropy
diff --git a/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisFuruichi.jl b/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisFuruichi.jl
index 98d81879..a941a0dc 100644
--- a/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisFuruichi.jl
+++ b/src/methods/information/definitions/conditional_entropies/ConditionalEntropyTsallisFuruichi.jl
@@ -40,9 +40,9 @@ is undefined for a particular value, then the measure is undefined and `NaN` is
 
 - [Example 1](@ref example_ConditionalEntropyTsallisFuruichi_JointProbabilities_CodifyVariables_UniqueElements): 
     [`JointProbabilities`](@ref) estimator with[`CodifyVariables`](@ref) discretization and 
-    [`UniqueElements`](@extref ComplexityMeasures) outcome space on categorical data.
+    [`UniqueElements`](@extref ComplexityMeasures.UniqueElements) outcome space on categorical data.
 - [Example 2](@ref example_ConditionalEntropyTsallisFuruichi_JointProbabilities_CodifyPoints_UniqueElementsEncoding): 
-    [`JointProbabilities`](@ref) estimator with [`CodifyPoints`](@ref) discretization and [`UniqueElementsEncoding`](@ref)
+    [`JointProbabilities`](@ref) estimator with [`CodifyPoints`](@ref) discretization and [`UniqueElementsEncoding`](@extref ComplexityMeasures.UniqueElementsEncoding)
     encoding of points on numerical data.
 """
 Base.@kwdef struct ConditionalEntropyTsallisFuruichi{B,Q} <: ConditionalEntropy
diff --git a/src/methods/information/definitions/conditional_mutual_informations/CMIRenyiJizba.jl b/src/methods/information/definitions/conditional_mutual_informations/CMIRenyiJizba.jl
index 65a9ad5b..5c3ab043 100644
--- a/src/methods/information/definitions/conditional_mutual_informations/CMIRenyiJizba.jl
+++ b/src/methods/information/definitions/conditional_mutual_informations/CMIRenyiJizba.jl
@@ -32,11 +32,11 @@ where ``I_q^{R_{J}}(X; Z)`` is the [`MIRenyiJizba`](@ref) mutual information.
 ## Estimation
 
 - [Example 1](@ref example_CMIRenyiJizba_JointProbabilities_BubbleSortSwaps): 
-    [`JointProbabilities`](@ref) with [`BubbleSortSwaps`](@ref) outcome space.
+    [`JointProbabilities`](@ref) with [`BubbleSortSwaps`](@extref ComplexityMeasures.BubbleSortSwaps) outcome space.
 - [Example 2](@ref example_CMIRenyiJizba_EntropyDecomposition_OrdinalPatterns): 
-    [`EntropyDecomposition`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space.
+    [`EntropyDecomposition`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns) outcome space.
 - [Example 3](@ref example_CMIRenyiJizba_EntropyDecomposition_LeonenkoProzantoSavani): 
-    [`EntropyDecomposition`](@ref) with differential entropy estimator [`LeonenkoProzantoSavani`](@extref ComplexityMeasures).
+    [`EntropyDecomposition`](@ref) with differential entropy estimator [`LeonenkoProzantoSavani`](@extref ComplexityMeasures.LeonenkoProzantoSavani).
 """
 Base.@kwdef struct CMIRenyiJizba{B,Q} <: ConditionalMutualInformation
     base::B = 2
diff --git a/src/methods/information/definitions/conditional_mutual_informations/CMIShannon.jl b/src/methods/information/definitions/conditional_mutual_informations/CMIShannon.jl
index 0924cef1..86270172 100644
--- a/src/methods/information/definitions/conditional_mutual_informations/CMIShannon.jl
+++ b/src/methods/information/definitions/conditional_mutual_informations/CMIShannon.jl
@@ -42,7 +42,7 @@ I(X; Y | Z)
 ```
 
 where ``I^S(\\cdot; \\cdot)`` is the Shannon mutual information [`MIShannon`](@ref),
-and ``H^S(\\cdot)`` is the [`Shannon`](@extref ComplexityMeasures) entropy.
+and ``H^S(\\cdot)`` is the [`Shannon`](@extref ComplexityMeasures.Shannon) entropy.
 
 Differential Shannon CMI is obtained by replacing the entropies by
 differential entropies.
@@ -50,11 +50,11 @@ differential entropies.
 ## Estimation
 
 - [Example 1](@ref example_CMIShannon_EntropyDecomposition_Kraskov): 
-    [`EntropyDecomposition`](@ref) with [`Kraskov`](@extref ComplexityMeasures) estimator.
+    [`EntropyDecomposition`](@ref) with [`Kraskov`](@extref ComplexityMeasures.Kraskov) estimator.
 - [Example 2](@ref example_CMIShannon_EntropyDecomposition_ValueBinning):
-    [`EntropyDecomposition`](@ref) with [`ValueBinning`](@extref ComplexityMeasures) estimator.
+    [`EntropyDecomposition`](@ref) with [`ValueBinning`](@extref ComplexityMeasures.ValueBinning) estimator.
 - [Example 3](@ref example_CMIShannon_MIDecomposition_KSG1): 
-    [`MIDecomposition`](@ref) with [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator.
+    [`MIDecomposition`](@ref) with [`KraskovStögbauerGrassberger2`](@ref) estimator.
 """
 Base.@kwdef struct CMIShannon{B} <: ConditionalMutualInformation
     base::B = 2
diff --git a/src/methods/information/definitions/divergences_and_distances/HellingerDistance.jl b/src/methods/information/definitions/divergences_and_distances/HellingerDistance.jl
index 1f2a7fb0..f0071578 100644
--- a/src/methods/information/definitions/divergences_and_distances/HellingerDistance.jl
+++ b/src/methods/information/definitions/divergences_and_distances/HellingerDistance.jl
@@ -19,7 +19,7 @@ The Hellinger distance.
 The Hellinger distance between two probability distributions
 ``P_X = (p_x(\\omega_1), \\ldots, p_x(\\omega_n))`` and
 ``P_Y = (p_y(\\omega_1), \\ldots, p_y(\\omega_m))``, both defined over the same
-[`OutcomeSpace`](@ref) ``\\Omega = \\{\\omega_1, \\ldots, \\omega_n \\}``, is
+[`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace) ``\\Omega = \\{\\omega_1, \\ldots, \\omega_n \\}``, is
 [defined](https://en.wikipedia.org/wiki/Hellinger_distance) as
 
 ```math
@@ -31,7 +31,7 @@ D_{H}(P_Y(\\Omega) || P_Y(\\Omega)) =
 
 - [Example 1](@ref example_HellingerDistance_precomputed_probabilities): From precomputed probabilities
 - [Example 2](@ref example_HellingerDistance_JointProbabilities_OrdinalPatterns): 
-    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space
+    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns) outcome space
 """
 struct HellingerDistance <: DivergenceOrDistance end
 
diff --git a/src/methods/information/definitions/divergences_and_distances/KLDivergence.jl b/src/methods/information/definitions/divergences_and_distances/KLDivergence.jl
index 8337208c..b534ff9b 100644
--- a/src/methods/information/definitions/divergences_and_distances/KLDivergence.jl
+++ b/src/methods/information/definitions/divergences_and_distances/KLDivergence.jl
@@ -24,7 +24,7 @@ The Kullback-Leibler (KL) divergence.
 The KL-divergence between two probability distributions
 ``P_X = (p_x(\\omega_1), \\ldots, p_x(\\omega_n))`` and
 ``P_Y = (p_y(\\omega_1), \\ldots, p_y(\\omega_m))``, both defined over the same
-[`OutcomeSpace`](@ref) ``\\Omega = \\{\\omega_1, \\ldots, \\omega_n \\}``, is defined as
+[`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace) ``\\Omega = \\{\\omega_1, \\ldots, \\omega_n \\}``, is defined as
 
 ```math
 D_{KL}(P_Y(\\Omega) || P_Y(\\Omega)) =
@@ -34,9 +34,9 @@ D_{KL}(P_Y(\\Omega) || P_Y(\\Omega)) =
 ## Implements
 
 - [`association`](@ref). Used to compute the KL-divergence between two pre-computed
-    probability distributions. If used with [`RelativeAmount`](@ref), the KL divergence may
+    probability distributions. If used with [`RelativeAmount`](@extref ComplexityMeasures.RelativeAmount), the KL divergence may
     be undefined to due some outcomes having zero counts. Use some other
-    [`ProbabilitiesEstimator`](@extref ComplexityMeasures) like [`BayesianRegularization`](@ref) to ensure
+    [`ProbabilitiesEstimator`](@extref ComplexityMeasures.ProbabilitiesEstimator) like [`BayesianRegularization`](@extref ComplexityMeasures.BayesianRegularization) to ensure
     all estimated probabilities are nonzero.
 
 !!! note 
@@ -47,7 +47,7 @@ D_{KL}(P_Y(\\Omega) || P_Y(\\Omega)) =
 
 - [Example 1](@ref example_KLDivergence_precomputed_probabilities): From precomputed probabilities
 - [Example 2](@ref example_KLDivergence_JointProbabilities_OrdinalPatterns): 
-    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space
+    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns) outcome space
 """
 struct KLDivergence{B} <: DivergenceOrDistance
     base::B
diff --git a/src/methods/information/definitions/divergences_and_distances/RenyiDivergence.jl b/src/methods/information/definitions/divergences_and_distances/RenyiDivergence.jl
index 5a35ec67..99c3e696 100644
--- a/src/methods/information/definitions/divergences_and_distances/RenyiDivergence.jl
+++ b/src/methods/information/definitions/divergences_and_distances/RenyiDivergence.jl
@@ -21,7 +21,7 @@ The Rényi divergence of positive order `q`.
 The Rényi divergence between two probability distributions
 ``P_X = (p_x(\\omega_1), \\ldots, p_x(\\omega_n))`` and
 ``P_Y = (p_y(\\omega_1), \\ldots, p_y(\\omega_m))``, both defined over the same
-[`OutcomeSpace`](@ref) ``\\Omega = \\{\\omega_1, \\ldots, \\omega_n \\}``, is defined as
+[`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace) ``\\Omega = \\{\\omega_1, \\ldots, \\omega_n \\}``, is defined as
 [vanErven2014](@citet).
 
 ```math
@@ -32,9 +32,9 @@ D_{q}(P_Y(\\Omega) || P_Y(\\Omega)) =
 ## Implements
 
 - [`information`](@ref). Used to compute the Rényi divergence between two pre-computed
-    probability distributions. If used with [`RelativeAmount`](@ref), the KL divergence may
+    probability distributions. If used with [`RelativeAmount`](@extref ComplexityMeasures.RelativeAmount), the KL divergence may
     be undefined to due some outcomes having zero counts. Use some other
-    [`ProbabilitiesEstimator`](@extref ComplexityMeasures) like [`BayesianRegularization`](@ref) to ensure
+    [`ProbabilitiesEstimator`](@extref ComplexityMeasures.ProbabilitiesEstimator) like [`BayesianRegularization`](@extref ComplexityMeasures.BayesianRegularization) to ensure
     all estimated probabilities are nonzero.
 
 !!! note 
@@ -46,7 +46,7 @@ D_{q}(P_Y(\\Omega) || P_Y(\\Omega)) =
 
 - [Example 1](@ref example_RenyiDivergence_precomputed_probabilities): From precomputed probabilities
 - [Example 2](@ref example_RenyiDivergence_JointProbabilities_OrdinalPatterns): 
-    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space
+    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns) outcome space
 """
 struct RenyiDivergence{Q,B} <: DivergenceOrDistance
     q::Q
diff --git a/src/methods/information/definitions/divergences_and_distances/VariationDistance.jl b/src/methods/information/definitions/divergences_and_distances/VariationDistance.jl
index 1a0d2283..d5b45aa2 100644
--- a/src/methods/information/definitions/divergences_and_distances/VariationDistance.jl
+++ b/src/methods/information/definitions/divergences_and_distances/VariationDistance.jl
@@ -20,7 +20,7 @@ The variation distance.
 The variation distance between two probability distributions
 ``P_X = (p_x(\\omega_1), \\ldots, p_x(\\omega_n))`` and
 ``P_Y = (p_y(\\omega_1), \\ldots, p_y(\\omega_m))``, both defined over the same
-[`OutcomeSpace`](@ref) ``\\Omega = \\{\\omega_1, \\ldots, \\omega_n \\}``, is
+[`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace) ``\\Omega = \\{\\omega_1, \\ldots, \\omega_n \\}``, is
 [defined](https://en.wikipedia.org/wiki/Variation_distance) as
 
 ```math
@@ -32,7 +32,7 @@ D_{V}(P_Y(\\Omega) || P_Y(\\Omega)) =
 
 - [Example 1](@ref example_VariationDistance_precomputed_probabilities): From precomputed probabilities
 - [Example 2](@ref example_VariationDistance_JointProbabilities_OrdinalPatterns): 
-    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space
+    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns) outcome space
 """
 struct VariationDistance <: DivergenceOrDistance end
 
diff --git a/src/methods/information/definitions/joint_entropies/JointEntropyRenyi.jl b/src/methods/information/definitions/joint_entropies/JointEntropyRenyi.jl
index c119ae63..9e3945b3 100644
--- a/src/methods/information/definitions/joint_entropies/JointEntropyRenyi.jl
+++ b/src/methods/information/definitions/joint_entropies/JointEntropyRenyi.jl
@@ -31,7 +31,7 @@ where ``q > 0`` and ``q != 1``.
 ## Estimation
 
 - [Example 1](@ref example_JointEntropyRenyi_ValueBinning): 
-    [`JointProbabilities`](@ref) with [`ValueBinning`](@extref ComplexityMeasures) outcome space
+    [`JointProbabilities`](@ref) with [`ValueBinning`](@extref ComplexityMeasures.ValueBinning) outcome space
 """
 Base.@kwdef struct JointEntropyRenyi{B,Q} <: JointEntropy
     base::B = 2
diff --git a/src/methods/information/definitions/joint_entropies/JointEntropyShannon.jl b/src/methods/information/definitions/joint_entropies/JointEntropyShannon.jl
index 321d6f72..94bb8161 100644
--- a/src/methods/information/definitions/joint_entropies/JointEntropyShannon.jl
+++ b/src/methods/information/definitions/joint_entropies/JointEntropyShannon.jl
@@ -31,7 +31,7 @@ where we define ``log(p(x, y)) := 0`` if ``p(x, y) = 0``.
 ## Estimation
 
 - [Example 1](@ref example_JointEntropyShannon_Dispersion): 
-    [`JointProbabilities`](@ref) with [`Dispersion`](@extref ComplexityMeasures) outcome space
+    [`JointProbabilities`](@ref) with [`Dispersion`](@extref ComplexityMeasures.Dispersion) outcome space
 """
 Base.@kwdef struct JointEntropyShannon{B} <: JointEntropy
     base::B = 2
diff --git a/src/methods/information/definitions/joint_entropies/JointEntropyTsallis.jl b/src/methods/information/definitions/joint_entropies/JointEntropyTsallis.jl
index 090505ae..c1f70341 100644
--- a/src/methods/information/definitions/joint_entropies/JointEntropyTsallis.jl
+++ b/src/methods/information/definitions/joint_entropies/JointEntropyTsallis.jl
@@ -32,7 +32,7 @@ we define ``log_q(x, q) := 0`` if ``q = 0``.
 ## Estimation
 
 - [Example 1](@ref example_JointEntropyTsallis_OrdinalPatterns): 
-    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space
+    [`JointProbabilities`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns) outcome space
 """
 Base.@kwdef struct JointEntropyTsallis{B,Q} <: JointEntropy
     base::B = 2
diff --git a/src/methods/information/definitions/mutual_informations/MIRenyiJizba.jl b/src/methods/information/definitions/mutual_informations/MIRenyiJizba.jl
index da13ffbe..5898be2c 100644
--- a/src/methods/information/definitions/mutual_informations/MIRenyiJizba.jl
+++ b/src/methods/information/definitions/mutual_informations/MIRenyiJizba.jl
@@ -26,14 +26,14 @@ The Rényi mutual information ``I_q^{R_{J}}(X; Y)`` defined in [Jizba2012](@cite
 I_q^{R_{J}}(X; Y) = H_q^{R}(X) + H_q^{R}(Y) - H_q^{R}(X, Y),
 ```
 
-where ``H_q^{R}(\\cdot)`` is the [`Rényi`](@ref) entropy.
+where ``H_q^{R}(\\cdot)`` is the [`Renyi`](@extref ComplexityMeasures.Renyi) entropy.
 
 
 ## Estimation
 
-- [Example 1](@ref example_MIRenyiJizba_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures) outcome space.
-- [Example 2](@ref example_MIRenyiJizba_JointProbabilities_LeonenkoProzantoSavani): [`EntropyDecomposition`](@ref) with [`LeonenkoProzantoSavani`](@extref ComplexityMeasures).
-- [Example 3](@ref example_MIRenyiJizba_EntropyDecomposition_ValueBinning): [`EntropyDecomposition`](@ref) with [`ValueBinning`](@extref ComplexityMeasures).
+- [Example 1](@ref example_MIRenyiJizba_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures.UniqueElements) outcome space.
+- [Example 2](@ref example_MIRenyiJizba_JointProbabilities_LeonenkoProzantoSavani): [`EntropyDecomposition`](@ref) with [`LeonenkoProzantoSavani`](@extref ComplexityMeasures.LeonenkoProzantoSavani).
+- [Example 3](@ref example_MIRenyiJizba_EntropyDecomposition_ValueBinning): [`EntropyDecomposition`](@ref) with [`ValueBinning`](@extref ComplexityMeasures.ValueBinning).
 """
 Base.@kwdef struct MIRenyiJizba{B,Q} <: MutualInformation
     base::B = 2
diff --git a/src/methods/information/definitions/mutual_informations/MIRenyiSarbu.jl b/src/methods/information/definitions/mutual_informations/MIRenyiSarbu.jl
index 0c608f5c..90fbd80a 100644
--- a/src/methods/information/definitions/mutual_informations/MIRenyiSarbu.jl
+++ b/src/methods/information/definitions/mutual_informations/MIRenyiSarbu.jl
@@ -36,8 +36,8 @@ I(X, Y)^R_q =
 
 ## Estimation
 
-- [Example 1](@ref example_MIRenyiSarbu_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures) for categorical data.
-- [Example 2](@ref example_MIRenyiSarbu_JointProbabilities_CosineSimilarityBinning): [`JointProbabilities`](@ref) with [`CosineSimilarityBinning`](@ref) for numerical data.
+- [Example 1](@ref example_MIRenyiSarbu_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures.UniqueElements) for categorical data.
+- [Example 2](@ref example_MIRenyiSarbu_JointProbabilities_CosineSimilarityBinning): [`JointProbabilities`](@ref) with [`CosineSimilarityBinning`](@extref ComplexityMeasures.CosineSimilarityBinning) for numerical data.
 """
 Base.@kwdef struct MIRenyiSarbu{B,Q} <: MutualInformation
     base::B = 2
diff --git a/src/methods/information/definitions/mutual_informations/MIShannon.jl b/src/methods/information/definitions/mutual_informations/MIShannon.jl
index a036858a..592541e1 100644
--- a/src/methods/information/definitions/mutual_informations/MIShannon.jl
+++ b/src/methods/information/definitions/mutual_informations/MIShannon.jl
@@ -19,10 +19,10 @@ The Shannon mutual information ``I_S(X; Y)``.
 
 - [`JointProbabilities`](@ref) (generic)
 - [`EntropyDecomposition`](@ref) (generic)
-- [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures)
-- [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures)
+- [`KraskovStögbauerGrassberger2`](@ref)
+- [`KraskovStögbauerGrassberger2`](@ref)
 - [`GaoOhViswanath`](@ref)
-- [`GaoKannanOhViswanath`](@extref ComplexityMeasures)
+- [`GaoKannanOhViswanath`](@ref)
 - [`GaussianMI`](@ref)
 
 ## Discrete definition
@@ -73,19 +73,19 @@ I^S(X; Y) = h^S(X) + h_q^S(Y) - h^S(X, Y),
 
 where ``h^S(\\cdot)`` and ``h^S(\\cdot, \\cdot)`` are the marginal and joint
 differential Shannon entropies. This definition is used by [`association`](@ref) when
-called with [`EntropyDecomposition`](@ref) estimator and a [`DifferentialInfoEstimator`](@extref ComplexityMeasures).
+called with [`EntropyDecomposition`](@ref) estimator and a [`DifferentialInfoEstimator`](@extref ComplexityMeasures.DifferentialInfoEstimator).
 
 ## Estimation
 
-- [Example 1](@ref example_MIShannon_JointProbabilities_ValueBinning): [`JointProbabilities`](@ref) with [`ValueBinning`](@extref ComplexityMeasures) outcome space.
-- [Example 2](@ref example_MIShannon_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures) outcome space on string data.
+- [Example 1](@ref example_MIShannon_JointProbabilities_ValueBinning): [`JointProbabilities`](@ref) with [`ValueBinning`](@extref ComplexityMeasures.ValueBinning) outcome space.
+- [Example 2](@ref example_MIShannon_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures.UniqueElements) outcome space on string data.
 - [Example 3](@ref example_MIShannon_GaussianMI): Dedicated [`GaussianMI`](@ref) estimator.
-- [Example 4](@ref example_MIShannon_KSG1): Dedicated [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator.
-- [Example 5](@ref example_MIShannon_KSG2): Dedicated [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator.
-- [Example 6](@ref example_MIShannon_GaoKannanOhViswanath): Dedicated [`GaoKannanOhViswanath`](@extref ComplexityMeasures) estimator.
-- [Example 7](@ref example_MIShannon_EntropyDecomposition_Kraskov): [`EntropyDecomposition`](@ref) with [`Kraskov`](@extref ComplexityMeasures) estimator.
-- [Example 8](@ref example_MIShannon_EntropyDecomposition_BubbleSortSwaps): [`EntropyDecomposition`](@ref) with [`BubbleSortSwaps`](@ref).
-- [Example 9](@ref example_MIShannon_EntropyDecomposition_Jackknife_ValueBinning): [`EntropyDecomposition`](@ref) with [`Jackknife`](@extref ComplexityMeasures) estimator and [`ValueBinning`](@extref ComplexityMeasures) outcome space.
+- [Example 4](@ref example_MIShannon_KSG1): Dedicated [`KraskovStögbauerGrassberger2`](@ref) estimator.
+- [Example 5](@ref example_MIShannon_KSG2): Dedicated [`KraskovStögbauerGrassberger2`](@ref) estimator.
+- [Example 6](@ref example_MIShannon_GaoKannanOhViswanath): Dedicated [`GaoKannanOhViswanath`](@ref) estimator.
+- [Example 7](@ref example_MIShannon_EntropyDecomposition_Kraskov): [`EntropyDecomposition`](@ref) with [`Kraskov`](@extref ComplexityMeasures.Kraskov) estimator.
+- [Example 8](@ref example_MIShannon_EntropyDecomposition_BubbleSortSwaps): [`EntropyDecomposition`](@ref) with [`BubbleSortSwaps`](@extref ComplexityMeasures.BubbleSortSwaps).
+- [Example 9](@ref example_MIShannon_EntropyDecomposition_Jackknife_ValueBinning): [`EntropyDecomposition`](@ref) with [`Jackknife`](@extref ComplexityMeasures.Jackknife) estimator and [`ValueBinning`](@extref ComplexityMeasures.ValueBinning) outcome space.
 - [Example 10](@ref example_MIShannon_reproducing_Kraskov): Reproducing Kraskov et al. (2004).
 """
 Base.@kwdef struct MIShannon{B} <: MutualInformation
diff --git a/src/methods/information/definitions/mutual_informations/MITsallisFuruichi.jl b/src/methods/information/definitions/mutual_informations/MITsallisFuruichi.jl
index 057b8fd0..1f2b2d37 100644
--- a/src/methods/information/definitions/mutual_informations/MITsallisFuruichi.jl
+++ b/src/methods/information/definitions/mutual_informations/MITsallisFuruichi.jl
@@ -30,13 +30,13 @@ I_q^T(X; Y) = H_q^T(X) - H_q^T(X | Y) = H_q^T(X) + H_q^T(Y) - H_q^T(X, Y),
 ```
 
 where ``H^T(\\cdot)`` and ``H^T(\\cdot, \\cdot)`` are the marginal and joint Tsallis
-entropies, and `q` is the [`Tsallis`](@extref ComplexityMeasures)-parameter.
+entropies, and `q` is the [`Tsallis`](@extref ComplexityMeasures.Tsallis)-parameter.
 
 ## Estimation
 
-- [Example 1](@ref example_MITsallisFuruichi_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures) outcome space.
-- [Example 2](@ref example_MITsallisFuruichi_EntropyDecomposition_LeonenkoProzantoSavani): [`EntropyDecomposition`](@ref) with [`LeonenkoProzantoSavani`](@extref ComplexityMeasures) estimator.
-- [Example 3](@ref example_MITsallisFuruichi_EntropyDecomposition_Dispersion): [`EntropyDecomposition`](@ref) with [`Dispersion`](@extref ComplexityMeasures)
+- [Example 1](@ref example_MITsallisFuruichi_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures.UniqueElements) outcome space.
+- [Example 2](@ref example_MITsallisFuruichi_EntropyDecomposition_LeonenkoProzantoSavani): [`EntropyDecomposition`](@ref) with [`LeonenkoProzantoSavani`](@extref ComplexityMeasures.LeonenkoProzantoSavani) estimator.
+- [Example 3](@ref example_MITsallisFuruichi_EntropyDecomposition_Dispersion): [`EntropyDecomposition`](@ref) with [`Dispersion`](@extref ComplexityMeasures.Dispersion)
 """
 Base.@kwdef struct MITsallisFuruichi{B,Q} <: MutualInformation
     base::B = 2
diff --git a/src/methods/information/definitions/mutual_informations/MITsallisMartin.jl b/src/methods/information/definitions/mutual_informations/MITsallisMartin.jl
index f8d3c790..6937d0ee 100644
--- a/src/methods/information/definitions/mutual_informations/MITsallisMartin.jl
+++ b/src/methods/information/definitions/mutual_informations/MITsallisMartin.jl
@@ -30,13 +30,13 @@ I_{\\text{Martin}}^T(X, Y, q) := H_q^T(X) + H_q^T(Y) - (1 - q) H_q^T(X) H_q^T(Y)
 ```
 
 where ``H^S(\\cdot)`` and ``H^S(\\cdot, \\cdot)`` are the marginal and joint Shannon
-entropies, and `q` is the [`Tsallis`](@extref ComplexityMeasures)-parameter.
+entropies, and `q` is the [`Tsallis`](@extref ComplexityMeasures.Tsallis)-parameter.
 
 ## Estimation
 
-- [Example 1](@ref example_MITsallisMartin_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures) outcome space.
-- [Example 2](@ref example_MITsallisMartin_EntropyDecomposition_LeonenkoProzantoSavani): [`EntropyDecomposition`](@ref) with [`LeonenkoProzantoSavani`](@extref ComplexityMeasures) estimator.
-- [Example 3](@ref example_MITsallisMartin_EntropyDecomposition_OrdinalPatterns): [`EntropyDecomposition`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space.
+- [Example 1](@ref example_MITsallisMartin_JointProbabilities_UniqueElements): [`JointProbabilities`](@ref) with [`UniqueElements`](@extref ComplexityMeasures.UniqueElements) outcome space.
+- [Example 2](@ref example_MITsallisMartin_EntropyDecomposition_LeonenkoProzantoSavani): [`EntropyDecomposition`](@ref) with [`LeonenkoProzantoSavani`](@extref ComplexityMeasures.LeonenkoProzantoSavani) estimator.
+- [Example 3](@ref example_MITsallisMartin_EntropyDecomposition_OrdinalPatterns): [`EntropyDecomposition`](@ref) with [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns) outcome space.
 """
 Base.@kwdef struct MITsallisMartin{B,Q} <: MutualInformation
     base::B = 2
diff --git a/src/methods/information/definitions/short_expansion_conditional_mutual_information/short_expansion_conditional_mutual_information.jl b/src/methods/information/definitions/short_expansion_conditional_mutual_information/short_expansion_conditional_mutual_information.jl
index 77337c2b..41cf946f 100644
--- a/src/methods/information/definitions/short_expansion_conditional_mutual_information/short_expansion_conditional_mutual_information.jl
+++ b/src/methods/information/definitions/short_expansion_conditional_mutual_information/short_expansion_conditional_mutual_information.jl
@@ -35,7 +35,7 @@ This quantity is estimated from data using one of the estimators below from the
 
 - [Example 1](@ref example_ShortExpansionConditionalMutualInformation_JointProbabilities_CodifyVariables_ValueBinning):
     Estimating [`ShortExpansionConditionalMutualInformation`](@ref) using the [`JointProbabilities`](@ref) estimator using a
-    [`CodifyVariables`](@ref) with [`ValueBinning`](@extref ComplexityMeasures) discretization.
+    [`CodifyVariables`](@ref) with [`ValueBinning`](@extref ComplexityMeasures.ValueBinning) discretization.
 """
 Base.@kwdef struct ShortExpansionConditionalMutualInformation{B} <: MultivariateInformationMeasure
     base::B = 2
diff --git a/src/methods/information/definitions/transferentropy/TERenyiJizba.jl b/src/methods/information/definitions/transferentropy/TERenyiJizba.jl
index 7d48cc02..c2af8624 100644
--- a/src/methods/information/definitions/transferentropy/TERenyiJizba.jl
+++ b/src/methods/information/definitions/transferentropy/TERenyiJizba.jl
@@ -38,18 +38,18 @@ estimator from the list below as its input.
 
 | Estimator                      | Sub-estimator                    | Principle                    |
 | :----------------------------- | :------------------------------- | :--------------------------- |
-| [`EntropyDecomposition`](@ref) | [`LeonenkoProzantoSavani`](@extref ComplexityMeasures) | Four-entropies decomposition |
-| [`EntropyDecomposition`](@ref) | [`ValueBinning`](@extref ComplexityMeasures)           | Four-entropies decomposition |
-| [`EntropyDecomposition`](@ref) | [`Dispersion`](@extref ComplexityMeasures)             | Four-entropies decomposition |
-| [`EntropyDecomposition`](@ref) | [`OrdinalPatterns`](@extref ComplexityMeasures)        | Four-entropies decomposition |
-| [`EntropyDecomposition`](@ref) | [`UniqueElements`](@extref ComplexityMeasures)         | Four-entropies decomposition |
-| [`EntropyDecomposition`](@ref) | [`TransferOperator`](@extref ComplexityMeasures)       | Four-entropies decomposition |
+| [`EntropyDecomposition`](@ref) | [`LeonenkoProzantoSavani`](@extref ComplexityMeasures.LeonenkoProzantoSavani) | Four-entropies decomposition |
+| [`EntropyDecomposition`](@ref) | [`ValueBinning`](@extref ComplexityMeasures.ValueBinning)           | Four-entropies decomposition |
+| [`EntropyDecomposition`](@ref) | [`Dispersion`](@extref ComplexityMeasures.Dispersion)             | Four-entropies decomposition |
+| [`EntropyDecomposition`](@ref) | [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)        | Four-entropies decomposition |
+| [`EntropyDecomposition`](@ref) | [`UniqueElements`](@extref ComplexityMeasures.UniqueElements)         | Four-entropies decomposition |
+| [`EntropyDecomposition`](@ref) | [`TransferOperator`](@extref ComplexityMeasures.TransferOperator)       | Four-entropies decomposition |
 
 Any of these estimators must be given as input to a [`CMIDecomposition](@ref) estimator.
 
 ## Estimation
 
-- [Example 1](@ref example_TERenyiJizba_EntropyDecomposition_TransferOperator): [`EntropyDecomposition`](@ref) with [`TransferOperator`](@extref ComplexityMeasures) outcome space.
+- [Example 1](@ref example_TERenyiJizba_EntropyDecomposition_TransferOperator): [`EntropyDecomposition`](@ref) with [`TransferOperator`](@extref ComplexityMeasures.TransferOperator) outcome space.
 
 """
 struct TERenyiJizba{B,Q,EMB} <: TransferEntropy
diff --git a/src/methods/information/definitions/transferentropy/TEShannon.jl b/src/methods/information/definitions/transferentropy/TEShannon.jl
index 7a12d20b..07205c18 100644
--- a/src/methods/information/definitions/transferentropy/TEShannon.jl
+++ b/src/methods/information/definitions/transferentropy/TEShannon.jl
@@ -32,7 +32,7 @@ are constructed using present/past values and future values, respectively.
 ## Estimation
 
 - [Example 1](@ref example_TEShannon_EntropyDecomposition_TransferOperator): 
-    [`EntropyDecomposition`](@ref) with [`TransferOperator`](@extref ComplexityMeasures) outcome space.
+    [`EntropyDecomposition`](@ref) with [`TransferOperator`](@extref ComplexityMeasures.TransferOperator) outcome space.
 - [Example 2](@ref example_TEShannon_SymbolicTransferEntropy): Estimation using the
     [`SymbolicTransferEntropy`](@ref) estimator.
 """
diff --git a/src/methods/information/estimators/JointProbabilities.jl b/src/methods/information/estimators/JointProbabilities.jl
index 453f33a9..64d2c4d7 100644
--- a/src/methods/information/estimators/JointProbabilities.jl
+++ b/src/methods/information/estimators/JointProbabilities.jl
@@ -17,8 +17,8 @@ export JointProbabilities
 ## Description
 
 It first encodes the input data according to the given `discretization`, then constructs 
-`probs`, a multidimensional [`Probabilities`](@ref) instance. Finally, `probs` are 
-forwarded to a [`PlugIn`](@extref ComplexityMeasures) estimator, which computes the measure according to 
+`probs`, a multidimensional [`Probabilities`](@extref ComplexityMeasures.Probabilities) instance. Finally, `probs` are 
+forwarded to a [`PlugIn`](@extref ComplexityMeasures.PlugIn) estimator, which computes the measure according to 
 `definition`.
 
 # Compatible encoding schemes
@@ -27,7 +27,7 @@ forwarded to a [`PlugIn`](@extref ComplexityMeasures) estimator, which computes
     applying an encoding in a sliding window over each input variable).  
 - [`CodifyPoints`](@ref) (encode each *point*/column of the input data)
 
-Works for any [`OutcomeSpace`](@ref) that implements [`codify`](@ref).
+Works for any [`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace) that implements [`codify`](@ref).
 
 !!! note "Joint probabilities vs decomposition methods"
 
@@ -41,8 +41,8 @@ Works for any [`OutcomeSpace`](@ref) that implements [`codify`](@ref).
     because it fails to fully take into consideration the joint relationships between the variables.
     Pick your estimator according to your needs.
 
-See also: [`Counts`](@ref), [`Probabilities`](@ref), [`ProbabilitiesEstimator`](@extref ComplexityMeasures),
-[`OutcomeSpace`](@ref), [`DiscreteInfoEstimator`](@extref ComplexityMeasures).
+See also: [`Counts`](@extref ComplexityMeasures.Counts), [`Probabilities`](@extref ComplexityMeasures.Probabilities), [`ProbabilitiesEstimator`](@extref ComplexityMeasures.ProbabilitiesEstimator),
+[`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace), [`DiscreteInfoEstimator`](@extref ComplexityMeasures.DiscreteInfoEstimator).
 """
 struct JointProbabilities{M<:MultivariateInformationMeasure,O,P} <: MultivariateInformationMeasureEstimator{M}
     definition::M # API from complexity measures: definition must be the first field of the infoestimator.
diff --git a/src/methods/information/estimators/codify_marginals.jl b/src/methods/information/estimators/codify_marginals.jl
index 5f00f4b0..45178223 100644
--- a/src/methods/information/estimators/codify_marginals.jl
+++ b/src/methods/information/estimators/codify_marginals.jl
@@ -18,23 +18,23 @@ to handle discretization.
 
 ## Supported estimators
 
-- [`ValueBinning`](@extref ComplexityMeasures). Bin visitation frequencies are counted in the joint space `XY`,
+- [`ValueBinning`](@extref ComplexityMeasures.ValueBinning). Bin visitation frequencies are counted in the joint space `XY`,
     then marginal visitations are obtained from the joint bin visits.
-    This behaviour is the same for both [`FixedRectangularBinning`](@ref) and
-    [`RectangularBinning`](@ref) (which adapts the grid to the data).
-    When using [`FixedRectangularBinning`](@ref), the range along the first dimension
+    This behaviour is the same for both [`FixedRectangularBinning`](@extref ComplexityMeasures.FixedRectangularBinning) and
+    [`RectangularBinning`](@extref ComplexityMeasures.RectangularBinning) (which adapts the grid to the data).
+    When using [`FixedRectangularBinning`](@extref ComplexityMeasures.FixedRectangularBinning), the range along the first dimension
     is used as a template for all other dimensions.
-- [`OrdinalPatterns`](@extref ComplexityMeasures). Each timeseries is separately [`codify`](@ref)-ed by 
+- [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns). Each timeseries is separately [`codify`](@ref)-ed by 
     embedding the timeseries, then sequentially encoding the ordinal patterns of 
     the embedding vectors.
-- [`Dispersion`](@extref ComplexityMeasures). Each timeseries is separately [`codify`](@ref)-ed by 
+- [`Dispersion`](@extref ComplexityMeasures.Dispersion). Each timeseries is separately [`codify`](@ref)-ed by 
     embedding the timeseries, then sequentially encoding the embedding vectors
     according to their dispersion pattern (which for each embedding vector is computed
     relative to all other embedding vectors).
-- [`CosineSimilarityBinning`](@ref). Each timeseries is separately [`codify`](@ref)-ed
+- [`CosineSimilarityBinning`](@extref ComplexityMeasures.CosineSimilarityBinning). Each timeseries is separately [`codify`](@ref)-ed
     by embedding the timeseries, the encoding the embedding points in a 
     in a sequential manner according to the cosine similarity of the embedding vectors.
-- [`UniqueElements`](@extref ComplexityMeasures). Each timeseries is [`codify`](@ref)-ed according to 
+- [`UniqueElements`](@extref ComplexityMeasures.UniqueElements). Each timeseries is [`codify`](@ref)-ed according to 
     its unique values (i.e. each unique element gets assigned a specific integer).
 
 More implementations are possible.
diff --git a/src/methods/information/estimators/conditional_mutual_info_estimators/FPVP.jl b/src/methods/information/estimators/conditional_mutual_info_estimators/FPVP.jl
index b19291ef..da9cde4e 100644
--- a/src/methods/information/estimators/conditional_mutual_info_estimators/FPVP.jl
+++ b/src/methods/information/estimators/conditional_mutual_info_estimators/FPVP.jl
@@ -12,7 +12,7 @@ export FPVP
 The Frenzel-Pompe-Vejmelka-Paluš (or `FPVP` for short)
 [`ConditionalMutualInformationEstimator`](@ref) is used to estimate the
 conditional mutual information using a `k`-th nearest neighbor approach that is
-analogous to that of the [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) mutual information
+analogous to that of the [`KraskovStögbauerGrassberger2`](@ref) mutual information
 estimator from [Frenzel2007](@citet) and [Vejmelka2008](@citet).
 
 `k` is the number of nearest neighbors. `w` is the Theiler window, which controls the
diff --git a/src/methods/information/estimators/conditional_mutual_info_estimators/Rahimzamani.jl b/src/methods/information/estimators/conditional_mutual_info_estimators/Rahimzamani.jl
index 88552e2f..c6a44973 100644
--- a/src/methods/information/estimators/conditional_mutual_info_estimators/Rahimzamani.jl
+++ b/src/methods/information/estimators/conditional_mutual_info_estimators/Rahimzamani.jl
@@ -18,7 +18,7 @@ for data that can be mixtures of discrete and continuous data [Rahimzamani2018](
 
 ## Description
 
-This estimator is very similar to the [`GaoKannanOhViswanath`](@extref ComplexityMeasures) mutual information
+This estimator is very similar to the [`GaoKannanOhViswanath`](@ref) mutual information
 estimator, but has been expanded to the conditional mutual information case.
 
 `k` is the number of nearest neighbors. `w` is the Theiler window, which controls the
diff --git a/src/methods/information/estimators/decomposition/EntropyDecomposition.jl b/src/methods/information/estimators/decomposition/EntropyDecomposition.jl
index cd1ff24e..40c58fb4 100644
--- a/src/methods/information/estimators/decomposition/EntropyDecomposition.jl
+++ b/src/methods/information/estimators/decomposition/EntropyDecomposition.jl
@@ -25,14 +25,14 @@ per variable/column and each column is encoded into integers using [`codify`](@r
 
 The entropy terms are estimated using `est`, and then combined to form the final 
 estimate of `definition`. No bias correction is applied.
-If `est` is a [`DifferentialInfoEstimator`](@extref ComplexityMeasures), then `discretization` and `pest` 
-are ignored. If `est` is a [`DiscreteInfoEstimator`](@extref ComplexityMeasures), then `discretization` and a
+If `est` is a [`DifferentialInfoEstimator`](@extref ComplexityMeasures.DifferentialInfoEstimator), then `discretization` and `pest` 
+are ignored. If `est` is a [`DiscreteInfoEstimator`](@extref ComplexityMeasures.DiscreteInfoEstimator), then `discretization` and a
 probabilities estimator `pest` must also be provided (default to `RelativeAmount`, 
 which uses naive plug-in probabilities).
 
 ## Compatible differential information estimators
 
-If using the first signature, any compatible [`DifferentialInfoEstimator`](@extref ComplexityMeasures) can be 
+If using the first signature, any compatible [`DifferentialInfoEstimator`](@extref ComplexityMeasures.DifferentialInfoEstimator) can be 
 used.
 
 ## Compatible outcome spaces for discrete estimation
@@ -42,12 +42,12 @@ Note that not all outcome spaces will work with all measures.
 
 | Estimator                         | Principle                     |
 | :-------------------------------- | :---------------------------- |
-| [`UniqueElements`](@extref ComplexityMeasures)          | Count of unique elements      |
-| [`ValueBinning`](@extref ComplexityMeasures)            | Binning (histogram)           |
-| [`OrdinalPatterns`](@extref ComplexityMeasures)         | Ordinal patterns              |
-| [`Dispersion`](@extref ComplexityMeasures)              | Dispersion patterns           |
-| [`BubbleSortSwaps`](@ref)         | Sorting complexity            |
-| [`CosineSimilarityBinning`](@ref) | Cosine similarities histogram |
+| [`UniqueElements`](@extref ComplexityMeasures.UniqueElements)          | Count of unique elements      |
+| [`ValueBinning`](@extref ComplexityMeasures.ValueBinning)            | Binning (histogram)           |
+| [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)         | Ordinal patterns              |
+| [`Dispersion`](@extref ComplexityMeasures.Dispersion)              | Dispersion patterns           |
+| [`BubbleSortSwaps`](@extref ComplexityMeasures.BubbleSortSwaps)         | Sorting complexity            |
+| [`CosineSimilarityBinning`](@extref ComplexityMeasures.CosineSimilarityBinning) | Cosine similarities histogram |
 
 ## Bias 
 
@@ -77,39 +77,39 @@ of entropies using the `Kraskov(Shannon(base = ℯ))` Shannon entropy estimator,
 
 ## Discrete entropy decomposition 
 
-The second signature is for discrete estimation using [`DiscreteInfoEstimator`](@extref ComplexityMeasures)s,
-for example [`PlugIn`](@extref ComplexityMeasures). The given `discretization` scheme (typically an 
-[`OutcomeSpace`](@ref)) controls how the joint/marginals are discretized, and the
+The second signature is for discrete estimation using [`DiscreteInfoEstimator`](@extref ComplexityMeasures.DiscreteInfoEstimator)s,
+for example [`PlugIn`](@extref ComplexityMeasures.PlugIn). The given `discretization` scheme (typically an 
+[`OutcomeSpace`](@extref ComplexityMeasures.OutcomeSpace)) controls how the joint/marginals are discretized, and the
 probabilities estimator `pest` controls how probabilities are estimated from counts.
 
 !!! note "Bias"
-    Like for [`DifferentialInfoEstimator`](@extref ComplexityMeasures), using a dedicated estimator 
+    Like for [`DifferentialInfoEstimator`](@extref ComplexityMeasures.DifferentialInfoEstimator), using a dedicated estimator 
     for the measure in question will be more reliable than using a decomposition
     estimate. Here's how different `discretization`s are applied:
 
-    - [`ValueBinning`](@extref ComplexityMeasures). Bin visitation frequencies are counted in the joint space
+    - [`ValueBinning`](@extref ComplexityMeasures.ValueBinning). Bin visitation frequencies are counted in the joint space
         `XY`, then marginal visitations are obtained from the joint bin visits.
-        This behaviour is the same for both [`FixedRectangularBinning`](@ref) and
-        [`RectangularBinning`](@ref) (which adapts the grid to the data).
-        When using [`FixedRectangularBinning`](@ref), the range along the first dimension
+        This behaviour is the same for both [`FixedRectangularBinning`](@extref ComplexityMeasures.FixedRectangularBinning) and
+        [`RectangularBinning`](@extref ComplexityMeasures.RectangularBinning) (which adapts the grid to the data).
+        When using [`FixedRectangularBinning`](@extref ComplexityMeasures.FixedRectangularBinning), the range along the first dimension
         is used as a template for all other dimensions. This is a bit slower than naively 
         binning each marginal, but lessens bias.
-    - [`OrdinalPatterns`](@extref ComplexityMeasures). Each timeseries is separately [`codify`](@ref)-ed
+    - [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns). Each timeseries is separately [`codify`](@ref)-ed
         according to its ordinal pattern (no bias correction).
-    - [`Dispersion`](@extref ComplexityMeasures). Each timeseries is separately [`codify`](@ref)-ed according
+    - [`Dispersion`](@extref ComplexityMeasures.Dispersion). Each timeseries is separately [`codify`](@ref)-ed according
         to its dispersion pattern  (no bias correction).
 
 ## Examples
 
 - [Example 1](@ref example_MIShannon_EntropyDecomposition_Jackknife_ValueBinning):
-    [`MIShannon`](@ref) estimation using decomposition into discrete [`Shannon`](@extref ComplexityMeasures)
-    entropy estimated using [`CodifyVariables`](@ref) with [`ValueBinning`](@extref ComplexityMeasures).
+    [`MIShannon`](@ref) estimation using decomposition into discrete [`Shannon`](@extref ComplexityMeasures.Shannon)
+    entropy estimated using [`CodifyVariables`](@ref) with [`ValueBinning`](@extref ComplexityMeasures.ValueBinning).
 - [Example 2](@ref example_MIShannon_EntropyDecomposition_BubbleSortSwaps):
-    [`MIShannon`](@ref) estimation using decomposition into discrete [`Shannon`](@extref ComplexityMeasures)
-    entropy estimated using [`CodifyVariables`](@ref) with [`BubbleSortSwaps`](@ref).
+    [`MIShannon`](@ref) estimation using decomposition into discrete [`Shannon`](@extref ComplexityMeasures.Shannon)
+    entropy estimated using [`CodifyVariables`](@ref) with [`BubbleSortSwaps`](@extref ComplexityMeasures.BubbleSortSwaps).
 - [Example 3](@ref example_MIShannon_EntropyDecomposition_Kraskov):
-    [`MIShannon`](@ref) estimation using decomposition into differental [`Shannon`](@extref ComplexityMeasures)
-    entropy estimated using the [`Kraskov`](@extref ComplexityMeasures) estimator.
+    [`MIShannon`](@ref) estimation using decomposition into differental [`Shannon`](@extref ComplexityMeasures.Shannon)
+    entropy estimated using the [`Kraskov`](@extref ComplexityMeasures.Kraskov) estimator.
 
 See also: [`MutualInformationEstimator`](@ref), [`MultivariateInformationMeasure`](@ref).
 """
diff --git a/src/methods/information/estimators/decomposition/MIDecomposition.jl b/src/methods/information/estimators/decomposition/MIDecomposition.jl
index a7c384bf..b512ba52 100644
--- a/src/methods/information/estimators/decomposition/MIDecomposition.jl
+++ b/src/methods/information/estimators/decomposition/MIDecomposition.jl
@@ -21,7 +21,7 @@ value of the measure.
 
 - [Example 1](@ref example_CMIShannon_MIDecomposition): Estimating [`CMIShannon`](@ref)
     using a decomposition into [`MIShannon`](@ref) terms using 
-    the [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) mutual information estimator.
+    the [`KraskovStögbauerGrassberger2`](@ref) mutual information estimator.
 
 See also: [`MultivariateInformationMeasureEstimator`](@ref).
 """
diff --git a/src/methods/information/estimators/mutual_info_estimators/GaoKannanOhViswanath.jl b/src/methods/information/estimators/mutual_info_estimators/GaoKannanOhViswanath.jl
index 9ee81101..f27349d7 100644
--- a/src/methods/information/estimators/mutual_info_estimators/GaoKannanOhViswanath.jl
+++ b/src/methods/information/estimators/mutual_info_estimators/GaoKannanOhViswanath.jl
@@ -40,8 +40,8 @@ variables (by quantization) or making it continuous by adding a small Gaussian n
 
 !!! warn "Implementation note"
     In [GaoKannanOhViswanath2017](@citet), they claim (roughly speaking) that the estimator
-    reduces to the [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) estimator for continuous-valued data.
-    However, [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) uses the digamma function, while `GaoKannanOhViswanath`
+    reduces to the [`KraskovStögbauerGrassberger2`](@ref) estimator for continuous-valued data.
+    However, [`KraskovStögbauerGrassberger2`](@ref) uses the digamma function, while `GaoKannanOhViswanath`
     uses the logarithm instead, so the estimators are not exactly equivalent
     for continuous data.
 
@@ -51,7 +51,7 @@ variables (by quantization) or making it continuous by adding a small Gaussian n
     `k`-th nearest distances among the two marginal spaces, which are in general not the
     same as the `k`-th neighbor distance in the joint space (unless both marginals are
     univariate). Therefore, our implementation here differs slightly from algorithm 1 in
-    `GaoKannanOhViswanath`. We have modified it in a way that mimics [`KraskovStögbauerGrassberger2`](@extref ComplexityMeasures) for
+    `GaoKannanOhViswanath`. We have modified it in a way that mimics [`KraskovStögbauerGrassberger2`](@ref) for
     continous data. Note that because of using the `log` function instead of `digamma`,
     there will be slight differences between the methods. See the source code for more
     details.
diff --git a/src/methods/information/estimators/transfer_entropy_estimators/Hilbert.jl b/src/methods/information/estimators/transfer_entropy_estimators/Hilbert.jl
index 19dc5fb4..aaadddc2 100644
--- a/src/methods/information/estimators/transfer_entropy_estimators/Hilbert.jl
+++ b/src/methods/information/estimators/transfer_entropy_estimators/Hilbert.jl
@@ -30,7 +30,7 @@ obtained by first applying the Hilbert transform to each signal, then extracting
 phases/amplitudes of the resulting complex numbers [Palus2014](@cite). Original time series are
 thus transformed to instantaneous phase/amplitude time series. Transfer
 entropy is then estimated using the provided `est` on those phases/amplitudes (use e.g.
-[`ValueBinning`](@extref ComplexityMeasures), or [`OrdinalPatterns`](@extref ComplexityMeasures)).
+[`ValueBinning`](@extref ComplexityMeasures.ValueBinning), or [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)).
 
 !!! info
     Details on estimation of the transfer entropy (conditional mutual information)
diff --git a/src/methods/information/estimators/transfer_entropy_estimators/SymbolicTransferEntropy.jl b/src/methods/information/estimators/transfer_entropy_estimators/SymbolicTransferEntropy.jl
index 888f1dc0..f9253d93 100644
--- a/src/methods/information/estimators/transfer_entropy_estimators/SymbolicTransferEntropy.jl
+++ b/src/methods/information/estimators/transfer_entropy_estimators/SymbolicTransferEntropy.jl
@@ -16,7 +16,7 @@ A convenience estimator for symbolic transfer entropy [Staniek2008](@cite).
 
 [Symbolic transfer entropy](https://journals.aps.org/prl/abstract/10.1103/PhysRevLett.100.158101)
 consists of two simple steps. First, the input time series are encoded using [`codify`](@ref) with
-the [`CodifyVariables`](@ref) discretization and the [`OrdinalPatterns`](@extref ComplexityMeasures) outcome space. This 
+the [`CodifyVariables`](@ref) discretization and the [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns) outcome space. This 
 transforms the input time series into integer time series. Transfer entropy entropy is then 
 estimated from the encoded time series by applying  
 

From a4fb6758427b23f6b6b010d9665a0f23a6cce622 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 12:39:03 +0200
Subject: [PATCH 13/24] extref for statespaceset

---
 docs/build_docs_with_style.jl                    | 16 +++-------------
 docs/src/api/discretization_counts_probs_api.md  |  6 +++---
 docs/src/index.md                                |  2 +-
 src/methods/closeness/SMeasure.jl                | 11 ++++++-----
 src/methods/correlation/partial_correlation.jl   |  8 ++++----
 src/methods/crossmappings/crossmappings.jl       | 10 +++++-----
 .../information/estimators/codify_marginals.jl   |  2 +-
 .../mutual_info_estimators/GaussianMI.jl         |  8 ++++----
 src/methods/recurrence/MCR.jl                    |  4 ++--
 9 files changed, 29 insertions(+), 38 deletions(-)

diff --git a/docs/build_docs_with_style.jl b/docs/build_docs_with_style.jl
index 1f5c5460..6a43a883 100644
--- a/docs/build_docs_with_style.jl
+++ b/docs/build_docs_with_style.jl
@@ -42,22 +42,12 @@ links = InterLinks(
         "https://juliadynamics.github.io/DynamicalSystemsDocs.jl/complexitymeasures/stable/objects.inv",
         joinpath(@__DIR__, "inventories", "Documenter.toml")
     ),
-    "Documenter" => (
-        "https://documenter.juliadocs.org/stable/",
-        "https://documenter.juliadocs.org/stable/objects.inv",
+    "StateSpaceSets" => (
+        "https://juliadynamics.github.io/DynamicalSystemsDocs.jl/statespacesets/stable/",
+        "https://juliadynamics.github.io/DynamicalSystemsDocs.jl/statespacesets/stable/objects.inv",
         joinpath(@__DIR__, "inventories", "Documenter.toml")
     ),
-    # "StateSpaceSets" => (
-    #     "https://juliadynamics.github.io/DynamicalSystemsDocs.jl/statespacesets/stable/",
-    #     "https://juliadynamics.github.io/DynamicalSystemsDocs.jl/statespacesets/stable/objects.inv",
-    #     joinpath(@__DIR__, "inventories", "Documenter.toml")
-    # ),
 );
-@show links["ComplexityMeasures"]
-@show links["Documenter"]
-for item in links["ComplexityMeasures"]
-    @show item
-end
 
 function build_docs_with_style(pages, modules...; bib=nothing,
     authors="Kristian Haaga, George Datseris and others", draft=false, kwargs...)
diff --git a/docs/src/api/discretization_counts_probs_api.md b/docs/src/api/discretization_counts_probs_api.md
index 85047d2a..6bc47539 100644
--- a/docs/src/api/discretization_counts_probs_api.md
+++ b/docs/src/api/discretization_counts_probs_api.md
@@ -38,7 +38,7 @@ In summary, the two main ways of discretizing data in Associations are as follow
 ### Encoding per point/row
 
 In some cases, it may be desireable to encode data on a row-wise basis. This 
-typically happens when working with pre-embedded time series or [`StateSpaceSet`](@ref)s 
+typically happens when working with pre-embedded time series or [`StateSpaceSet`](@extref StateSpaceSets.StateSpaceSet)s 
 (respecting the fact that time ordering is already taken care of by the 
 embedding procedure). 
 If we want to apply something like [`OrdinalPatternEncoding`](@extref ComplexityMeasures.OrdinalPatternEncoding) to such data, then 
@@ -61,7 +61,7 @@ them in arbitrary ways using [`CombinationEncoding`](@extref ComplexityMeasures.
 #### [Examples: encoding *rows* (one *point* at a time)](@id tutorial_codify_points)
 
 We'll here use the [`OrdinalPatternEncoding`](@extref ComplexityMeasures.OrdinalPatternEncoding) with differing parameter `m` to encode 
-multiple [`StateSpaceSet`](@ref) of differing dimensions.
+multiple [`StateSpaceSet`](@extref StateSpaceSets.StateSpaceSet) of differing dimensions.
 
 ```@example example_encode_points
 using Associations
@@ -155,7 +155,7 @@ o = OrdinalPatterns(m = 3)
 cx = codify(CodifyVariables(o), x)
 ```
 
-We can simultaneously encode multiple variable/columns of a [`StateSpaceSet`](@ref) using 
+We can simultaneously encode multiple variable/columns of a [`StateSpaceSet`](@extref StateSpaceSets.StateSpaceSet) using 
 the same outcome space, as long as the operation will result in the *same* number of encoded 
 data points for each column.
 
diff --git a/docs/src/index.md b/docs/src/index.md
index 32714e77..363e2595 100644
--- a/docs/src/index.md
+++ b/docs/src/index.md
@@ -48,7 +48,7 @@ Input data for Associations.jl are given as:
 
 - Univariate *timeseries*, which are given as standard Julia `Vector`s.
 - Multivariate timeseries, *StateSpaceSets*, or *state space sets*, which are given as
-    [`StateSpaceSet`](@ref)s. Many methods convert *timeseries* inputs to [`StateSpaceSet`](@ref)
+    [`StateSpaceSet`](@extref StateSpaceSets.StateSpaceSet)s. Many methods convert *timeseries* inputs to [`StateSpaceSet`](@extref StateSpaceSets.StateSpaceSet)
     for faster internal computations.
 - Categorical data can be used with [`JointProbabilities`](@ref) to compute various
     information theoretic measures and is represented using any iterable whose elements
diff --git a/src/methods/closeness/SMeasure.jl b/src/methods/closeness/SMeasure.jl
index a3fd9f39..fc16a249 100644
--- a/src/methods/closeness/SMeasure.jl
+++ b/src/methods/closeness/SMeasure.jl
@@ -66,13 +66,13 @@ S^{(k)}(x|y) = \\dfrac{1}{N} \\sum_{i=1}^{N} \\dfrac{R_i^{(k)}(x)}{R_i^{(k)}(x|y
 
 The algorithm is slightly modified from [Arnhold1999](@cite) to allow univariate timeseries as input.
 
-- If `x` and `y` are [`StateSpaceSet`](@ref)s then use `x` and `y` as is and ignore the parameters
+- If `x` and `y` are [`StateSpaceSet`](@extref StateSpaceSets.StateSpaceSet)s then use `x` and `y` as is and ignore the parameters
     `dx`/`τx` and `dy`/`τy`.
 - If `x` and `y` are scalar time series, then create `dx` and `dy` dimensional embeddings,
     respectively, of both `x` and `y`, resulting in `N` different `m`-dimensional embedding points
     ``X = \\{x_1, x_2, \\ldots, x_N \\}`` and ``Y = \\{y_1, y_2, \\ldots, y_N \\}``.
     `τx` and `τy` control the embedding lags for `x` and `y`.
-- If `x` is a scalar-valued vector and `y` is a [`StateSpaceSet`](@ref), or vice versa,
+- If `x` is a scalar-valued vector and `y` is a [`StateSpaceSet`](@extref StateSpaceSets.StateSpaceSet), or vice versa,
     then create an embedding of the scalar timeseries using parameters `dx`/`τx` or `dy`/`τy`.
 
 In all three cases, input StateSpaceSets are length-matched by eliminating points at the end of
@@ -80,7 +80,7 @@ the longest StateSpaceSet (after the embedding step, if relevant) before analysi
 
 See also: [`ClosenessMeasure`](@ref).
 """
-Base.@kwdef struct SMeasure{M, TM} <: ClosenessMeasure
+Base.@kwdef struct SMeasure{M,TM} <: ClosenessMeasure
     K::Int = 2
     metric::M = SqEuclidean()
     tree_metric::TM = Euclidean()
@@ -96,13 +96,14 @@ function association(measure::SMeasure, x::AbstractStateSpaceSet, y::AbstractSta
     (; K, metric, tree_metric, τx, τy, dx, dy, w) = measure
 
     # Match length of StateSpaceSets by excluding end points.
-    lx = length(x); ly = length(y)
+    lx = length(x)
+    ly = length(y)
     lx > ly ? X = x[1:ly, :] : X = x
     ly > lx ? Y = y[1:lx, :] : Y = y
     N = length(X)
 
     T = eltype(1.0)
-     # Pre-allocate vectors to hold indices and distances during loops
+    # Pre-allocate vectors to hold indices and distances during loops
     dists_x = zeros(T, K)
     dists_x_cond_y = zeros(T, K)
 
diff --git a/src/methods/correlation/partial_correlation.jl b/src/methods/correlation/partial_correlation.jl
index 98eddd8c..800bf210 100644
--- a/src/methods/correlation/partial_correlation.jl
+++ b/src/methods/correlation/partial_correlation.jl
@@ -16,7 +16,7 @@ variables removed.
 
 There are several ways of estimating the partial correlation. We follow the
 [matrix inversion method](https://en.wikipedia.org/wiki/Partial_correlation), because
-for [`StateSpaceSet`](@ref)s, we can very efficiently compute the required
+for [`StateSpaceSet`](@extref StateSpaceSets.StateSpaceSet)s, we can very efficiently compute the required
 joint covariance matrix ``\\Sigma`` for the random variables.
 
 Formally, let ``X_1, X_2, \\ldots, X_n`` be a set of ``n`` real-valued random variables.
@@ -44,7 +44,7 @@ max_inputs_vars(::PartialCorrelation) = Inf
 
 # Compatibility with `independence`
 function association(::PartialCorrelation, x::VectorOrStateSpaceSet, y::VectorOrStateSpaceSet,
-        conds::ArrayOrStateSpaceSet...)
+    conds::ArrayOrStateSpaceSet...)
     X, Y, Z = construct_partialcor_datasets(x, y, conds...)
     D = StateSpaceSet(X, Y, Z)
     cov_matrix = cov(D)
@@ -53,7 +53,7 @@ function association(::PartialCorrelation, x::VectorOrStateSpaceSet, y::VectorOr
 end
 
 function construct_partialcor_datasets(x::VectorOrStateSpaceSet, y::VectorOrStateSpaceSet,
-        conds::ArrayOrStateSpaceSet...)
+    conds::ArrayOrStateSpaceSet...)
     dimension(x) == 1 || throw(ArgumentError("Input `x` must be 1-dimensional"))
     dimension(y) == 1 || throw(ArgumentError("Input `y` must be 1-dimensional"))
     X, Y = StateSpaceSet(x), StateSpaceSet(y)
@@ -79,5 +79,5 @@ Given a precision matrix `P`, compute the partial correlation of variables `i` a
 conditional on all other variables.
 """
 function partial_correlation_from_precision(P::AbstractMatrix, i::Int, j::Int)
-    return -P[i, j] / sqrt(P[i, i]*P[j, j])
+    return -P[i, j] / sqrt(P[i, i] * P[j, j])
 end
diff --git a/src/methods/crossmappings/crossmappings.jl b/src/methods/crossmappings/crossmappings.jl
index 5dcc44fc..1d3d68c1 100644
--- a/src/methods/crossmappings/crossmappings.jl
+++ b/src/methods/crossmappings/crossmappings.jl
@@ -59,11 +59,11 @@ for ensemble analysis (see [`Ensemble`](@ref)).
     For spatial analyses (not yet implemented), indices could be more complex and involve
     multi-indices.
 """
-abstract type CrossmapEstimator{M, LIBSIZES, RNG} end
+abstract type CrossmapEstimator{M,LIBSIZES,RNG} end
 
 segment_length_error() = "Segment lengths can be inferred only if both a cross-map " *
-    "measure and an input time series is provided. " *
-    "Do e.g. `ExpandingSegment(CCM(), x)`, where `x` is some time series."
+                         "measure and an input time series is provided. " *
+                         "Do e.g. `ExpandingSegment(CCM(), x)`, where `x` is some time series."
 
 """
     max_segmentlength(x::AbstractVector, measure::CrossmapMeasure)
@@ -122,7 +122,7 @@ according to the algorithm specified by the given cross-map `measure` (e.g.
 
 - **First method**: Jointly embeds the target `t` and source `s` time series (according to
     `measure`) to obtain time-index aligned target timeseries `t̄` and source embedding
-    `S̄` (which is now a [`StateSpaceSet`](@ref)).
+    `S̄` (which is now a [`StateSpaceSet`](@extref StateSpaceSets.StateSpaceSet)).
     Then calls `predict(measure, t̄, S̄)` (the first method), and returns both the
     predictions `t̂ₛ`, observations `t̄` and their correspondence `ρ` according to `measure`.
 - **Second method**: Returns a vector of predictions `t̂ₛ` (`t̂ₛ` := "predictions of `t̄` based
@@ -170,7 +170,7 @@ function predict(measure::CrossmapMeasure, t::AbstractVector, S̄::AbstractState
         if !(first(dᵢ) > 0.0)
             for i = 1:nnd
                 # One order of magnitude higher than smallest possible float
-                dᵢ[i] += eps()*10
+                dᵢ[i] += eps() * 10
             end
         end
         u .= exp.(-dᵢ ./ dᵢ[1])
diff --git a/src/methods/information/estimators/codify_marginals.jl b/src/methods/information/estimators/codify_marginals.jl
index 45178223..fc837695 100644
--- a/src/methods/information/estimators/codify_marginals.jl
+++ b/src/methods/information/estimators/codify_marginals.jl
@@ -8,7 +8,7 @@ Encode/discretize each input vector (e.g. timeseries) `xᵢ ∈ x` according to
 determined by `o`. 
 
 For some outcome spaces, the encoding is sequential (i.e. time ordering matters). 
-Any `xᵢ ∈ X` that are multidimensional ([`StateSpaceSet`](@ref)s) will be encoded
+Any `xᵢ ∈ X` that are multidimensional ([`StateSpaceSet`](@extref StateSpaceSets.StateSpaceSet)s) will be encoded
 column-wise, i.e. each column of `xᵢ` is treated as a timeseries and is encoded separately.
 
 This is useful for discretizing input data when computing some 
diff --git a/src/methods/information/estimators/mutual_info_estimators/GaussianMI.jl b/src/methods/information/estimators/mutual_info_estimators/GaussianMI.jl
index d450187b..205e0742 100644
--- a/src/methods/information/estimators/mutual_info_estimators/GaussianMI.jl
+++ b/src/methods/information/estimators/mutual_info_estimators/GaussianMI.jl
@@ -21,7 +21,7 @@ using LinearAlgebra: eigvals, det
 ## Description
 
 Given ``d_x``-dimensional and ``d_y``-dimensional input data `X` and `Y`,
-`GaussianMI` first constructs the ``d_x + d_y``-dimensional joint [`StateSpaceSet`](@ref) `XY`.
+`GaussianMI` first constructs the ``d_x + d_y``-dimensional joint [`StateSpaceSet`](@extref StateSpaceSets.StateSpaceSet) `XY`.
 If `normalize == true`, then we follow the approach in Vejmelka & Palus
 (2008)[Vejmelka2008](@cite) and transform each column in `XY` to have zero mean and unit
 standard deviation. If `normalize == false`, then the algorithm proceeds without
@@ -31,7 +31,7 @@ Next, the `C_{XY}`, the correlation matrix for the (normalized) joint data `XY`
 computed. The mutual information estimate `GaussianMI` assumes the input variables are distributed according to normal
 distributions with zero means and unit standard deviations.
 Therefore, given ``d_x``-dimensional and ``d_y``-dimensional input data `X` and `Y`,
-`GaussianMI` first constructs the joint [`StateSpaceSet`](@ref) `XY`, then transforms each
+`GaussianMI` first constructs the joint [`StateSpaceSet`](@extref StateSpaceSets.StateSpaceSet) `XY`, then transforms each
 column in `XY` to have zero mean and unit standard deviation, and finally computes
 the `\\Sigma`, the correlation matrix for `XY`.
 
@@ -68,12 +68,12 @@ x = rand(rng, 10000); y = rand(rng, 10000)
 association(GaussianMI(), x, y) # should be near 0 (and can be negative)
 ```
 """
-struct GaussianMI{M <: MutualInformation} <: MutualInformationEstimator{M}
+struct GaussianMI{M<:MutualInformation} <: MutualInformationEstimator{M}
     definition::M
     normalize::Bool
 end
 
-function GaussianMI(definition = MIShannon(); normalize = true)
+function GaussianMI(definition=MIShannon(); normalize=true)
     return GaussianMI(definition, normalize)
 end
 
diff --git a/src/methods/recurrence/MCR.jl b/src/methods/recurrence/MCR.jl
index 190e36a7..9001c6f4 100644
--- a/src/methods/recurrence/MCR.jl
+++ b/src/methods/recurrence/MCR.jl
@@ -47,14 +47,14 @@ defined analogously.
 ## Input data
 
 `X` and `Y` can be either both univariate timeseries, or both multivariate
-[`StateSpaceSet`](@ref)s.
+[`StateSpaceSet`](@extref StateSpaceSets.StateSpaceSet)s.
 
 
 ## Estimation
 
 - [Example 1](@ref example_MCR). Pairwise versus conditional MCR.
 """
-Base.@kwdef struct MCR{R, M} <: AssociationMeasure
+Base.@kwdef struct MCR{R,M} <: AssociationMeasure
     r::R
     metric::M = Euclidean()
 end

From a70d8b73e0fe88b7b15722bd18da9a5b99cf05b3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 13:14:47 +0200
Subject: [PATCH 14/24] fix last doc errors and set collapse = false

---
 docs/src/api/counts_and_probabilities_api.md  | 12 ++--
 docs/src/api/cross_map_api.md                 |  2 +-
 .../api/discretization_counts_probs_api.md    |  2 +-
 docs/src/api/information_multivariate_api.md  |  2 +-
 .../api/information_single_variable_api.md    |  2 +-
 docs/src/associations.md                      |  2 +-
 docs/src/causal_graphs.md                     |  2 +-
 docs/src/examples/examples_associations.md    |  7 +-
 docs/src/independence.md                      |  2 +-
 .../decomposition/EntropyDecomposition.jl     | 71 +++++++++++--------
 10 files changed, 59 insertions(+), 45 deletions(-)

diff --git a/docs/src/api/counts_and_probabilities_api.md b/docs/src/api/counts_and_probabilities_api.md
index 480e9c72..b624ba23 100644
--- a/docs/src/api/counts_and_probabilities_api.md
+++ b/docs/src/api/counts_and_probabilities_api.md
@@ -1,20 +1,18 @@
 
 ```@meta
-CollapsedDocStrings = true
+CollapsedDocStrings = false
 ```
 
 # [Multivariate counts and probabilities API](@id counts_and_probabilities_api)
 
 For counting and probabilities, Associations.jl extends the single-variable machinery
-in ComplexityMeasures.jl to multiple variables.
+in ComplexityMeasures.jl to multiple variables. See the following types:
 
-```@docs
-Associations.Counts
-Associations.counts(::OutcomeSpace)
-```
+- [`Counts`](@extref ComplexityMeasures.Counts)
+- [`Probabilities`](@extref ComplexityMeasures.Probabilities)
 
 ```@docs
-Associations.Probabilities
+Associations.counts(::OutcomeSpace)
 Associations.probabilities(::OutcomeSpace)
 ```
 
diff --git a/docs/src/api/cross_map_api.md b/docs/src/api/cross_map_api.md
index 469280bb..878e26c8 100644
--- a/docs/src/api/cross_map_api.md
+++ b/docs/src/api/cross_map_api.md
@@ -1,5 +1,5 @@
 ```@meta
-CollapsedDocStrings = true
+CollapsedDocStrings = false
 ```
 
 # Cross-map API
diff --git a/docs/src/api/discretization_counts_probs_api.md b/docs/src/api/discretization_counts_probs_api.md
index 6bc47539..89bacd45 100644
--- a/docs/src/api/discretization_counts_probs_api.md
+++ b/docs/src/api/discretization_counts_probs_api.md
@@ -1,5 +1,5 @@
 ```@meta
-CollapsedDocStrings = true
+CollapsedDocStrings = false
 ```
 
 # Discretization API
diff --git a/docs/src/api/information_multivariate_api.md b/docs/src/api/information_multivariate_api.md
index 89736235..71fea2a3 100644
--- a/docs/src/api/information_multivariate_api.md
+++ b/docs/src/api/information_multivariate_api.md
@@ -1,5 +1,5 @@
 ```@meta
-CollapsedDocStrings = true
+CollapsedDocStrings = false
 ```
 
 # [Multivariate information API](@id information_api)
diff --git a/docs/src/api/information_single_variable_api.md b/docs/src/api/information_single_variable_api.md
index 7eace43f..88e6918c 100644
--- a/docs/src/api/information_single_variable_api.md
+++ b/docs/src/api/information_single_variable_api.md
@@ -1,5 +1,5 @@
 ```@meta
-CollapsedDocStrings = true
+CollapsedDocStrings = false
 ```
 
 # Single-variable information API
diff --git a/docs/src/associations.md b/docs/src/associations.md
index 8143384f..ee6f816c 100644
--- a/docs/src/associations.md
+++ b/docs/src/associations.md
@@ -1,5 +1,5 @@
 ```@meta
-CollapsedDocStrings = true
+CollapsedDocStrings = false
 ```
 
 # [Associations](@id association_measures)
diff --git a/docs/src/causal_graphs.md b/docs/src/causal_graphs.md
index dfbfeb4c..6a9cbf47 100644
--- a/docs/src/causal_graphs.md
+++ b/docs/src/causal_graphs.md
@@ -1,5 +1,5 @@
 ```@meta
-CollapsedDocStrings = true
+CollapsedDocStrings = false
 ```
 
 # [Inferring causal graphs](@id causal_graphs)
diff --git a/docs/src/examples/examples_associations.md b/docs/src/examples/examples_associations.md
index 3ca96c68..7f3e36cf 100644
--- a/docs/src/examples/examples_associations.md
+++ b/docs/src/examples/examples_associations.md
@@ -917,8 +917,11 @@ association(est, x, y)
 ### [[`EntropyDecomposition`](@ref) + [`LeonenkoProzantoSavani`](@extref ComplexityMeasures.LeonenkoProzantoSavani)](@id example_MITsallisMartin_EntropyDecomposition_LeonenkoProzantoSavani)
 
 [`MITsallisMartin`](@ref) can be estimated using a decomposition into entropy 
-terms using [`EntropyDecomposition`](@ref) with any compatible estimator 
-that can estimate differential [`Tsallis`](@extref ComplexityMeasures.Tsallis) entropy. 
+terms using [`EntropyDecomposition`](@ref). This is done by using estimators from 
+[ComplexityMeasures.jl](https://juliadynamics.github.io/DynamicalSystemsDocs.jl/complexitymeasures/stable/). We can use any compatible 
+[`InformationMeasureEstimator`](@extref ComplexityMeasures.InformationMeasureEstimator)
+that can estimate differential [`Tsallis`](@extref ComplexityMeasures.Tsallis) entropy from
+[ComplexityMeasures.jl](https://juliadynamics.github.io/DynamicalSystemsDocs.jl/complexitymeasures/stable/).
 
 
 ```@example example_MITsallisMartin
diff --git a/docs/src/independence.md b/docs/src/independence.md
index d9340540..ec536ff6 100644
--- a/docs/src/independence.md
+++ b/docs/src/independence.md
@@ -1,5 +1,5 @@
 ```@meta
-CollapsedDocStrings = true
+CollapsedDocStrings = false
 ```
 
 # [Independence testing](@id independence_testing)
diff --git a/src/methods/information/estimators/decomposition/EntropyDecomposition.jl b/src/methods/information/estimators/decomposition/EntropyDecomposition.jl
index 40c58fb4..2799daec 100644
--- a/src/methods/information/estimators/decomposition/EntropyDecomposition.jl
+++ b/src/methods/information/estimators/decomposition/EntropyDecomposition.jl
@@ -12,8 +12,26 @@ export EntropyDecomposition
 Estimate the multivariate information measure specified by `definition` by rewriting
 its formula into some combination of entropy terms. 
 
-If calling the second method (discrete variant), then discretization is always done 
-per variable/column and each column is encoded into integers using [`codify`](@ref).
+## Estimation 
+
+`EntropyDecomposition` allows using any 
+[`InformationMeasureEstimators`s](@extref ComplexityMeasures.InformationMeasureEstimator) from 
+[ComplexityMeasures.jl](https://juliadynamics.github.io/DynamicalSystemsDocs.jl/complexitymeasures/stable/)
+to estimate multivariate information measures.
+
+Computations are done by computing individual entropy terms using `est`, then combining them according to 
+`definition` to form the final estimate. 
+
+## Bias 
+
+Estimating the `definition` by decomposition into a combination of entropy terms,
+which are estimated independently, will in general be more biased than when using a
+dedicated estimator. One reason is that this decomposition may miss out on crucial
+information in the joint space. To remedy this, dedicated information measure 
+estimators typically derive the marginal estimates by first considering the joint
+space, and then does some clever trick to eliminate the bias that is introduced
+through a naive decomposition. Unless specified below, no bias correction is 
+applied for `EntropyDecomposition`.
 
 ## Usage
 
@@ -23,43 +41,38 @@ per variable/column and each column is encoded into integers using [`codify`](@r
 
 ## Description
 
-The entropy terms are estimated using `est`, and then combined to form the final 
-estimate of `definition`. No bias correction is applied.
 If `est` is a [`DifferentialInfoEstimator`](@extref ComplexityMeasures.DifferentialInfoEstimator), then `discretization` and `pest` 
-are ignored. If `est` is a [`DiscreteInfoEstimator`](@extref ComplexityMeasures.DiscreteInfoEstimator), then `discretization` and a
-probabilities estimator `pest` must also be provided (default to `RelativeAmount`, 
-which uses naive plug-in probabilities).
-
-## Compatible differential information estimators
+are ignored. 
+## Differential estimation
 
 If using the first signature, any compatible [`DifferentialInfoEstimator`](@extref ComplexityMeasures.DifferentialInfoEstimator) can be 
 used.
+[`MITsallisMartin`](@ref) can be estimated using a decomposition into entropy 
+terms using [`EntropyDecomposition`](@ref). This is done by using estimators from 
+[ComplexityMeasures.jl](https://juliadynamics.github.io/DynamicalSystemsDocs.jl/complexitymeasures/stable/). We can use any compatible 
+[`InformationMeasureEstimator`](@extref ComplexityMeasures.InformationMeasureEstimator)
+that can estimate differential [`Tsallis`](@extref ComplexityMeasures.Tsallis) entropy from
+[ComplexityMeasures.jl](https://juliadynamics.github.io/DynamicalSystemsDocs.jl/complexitymeasures/stable/).
+
+## Discrete estimation
 
-## Compatible outcome spaces for discrete estimation
+If `est` is a [`DiscreteInfoEstimator`](@extref ComplexityMeasures.DiscreteInfoEstimator), then 
+`discretization` and a probabilities estimator `pest` must also be provided (default to `RelativeAmount`, 
+which uses naive plug-in probabilities). This will always discretize the input data 
+per variable/column, and the encode the discretized column into integers using [`codify`](@ref).
 
-If using the second signature, the outcome spaces can be used for discretisation. 
+The following [`OutcomeSpace`s](@extref ComplexityMeasures.OutcomeSpace) can be used for discretisation. 
 Note that not all outcome spaces will work with all measures.
 
-| Estimator                         | Principle                     |
-| :-------------------------------- | :---------------------------- |
-| [`UniqueElements`](@extref ComplexityMeasures.UniqueElements)          | Count of unique elements      |
-| [`ValueBinning`](@extref ComplexityMeasures.ValueBinning)            | Binning (histogram)           |
-| [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)         | Ordinal patterns              |
-| [`Dispersion`](@extref ComplexityMeasures.Dispersion)              | Dispersion patterns           |
-| [`BubbleSortSwaps`](@extref ComplexityMeasures.BubbleSortSwaps)         | Sorting complexity            |
+| Estimator                                                                       | Principle                     |
+| :------------------------------------------------------------------------------ | :---------------------------- |
+| [`UniqueElements`](@extref ComplexityMeasures.UniqueElements)                   | Count of unique elements      |
+| [`ValueBinning`](@extref ComplexityMeasures.ValueBinning)                       | Binning (histogram)           |
+| [`OrdinalPatterns`](@extref ComplexityMeasures.OrdinalPatterns)                 | Ordinal patterns              |
+| [`Dispersion`](@extref ComplexityMeasures.Dispersion)                           | Dispersion patterns           |
+| [`BubbleSortSwaps`](@extref ComplexityMeasures.BubbleSortSwaps)                 | Sorting complexity            |
 | [`CosineSimilarityBinning`](@extref ComplexityMeasures.CosineSimilarityBinning) | Cosine similarities histogram |
 
-## Bias 
-
-Estimating the `definition` by decomposition into a combination of entropy terms,
-which are estimated independently, will in general be more biased than when using a
-dedicated estimator. One reason is that this decomposition may miss out on crucial
-information in the joint space. To remedy this, dedicated information measure 
-estimators typically derive the marginal estimates by first considering the joint
-space, and then does some clever trick to eliminate the bias that is introduced
-through a naive decomposition. Unless specified below, no bias correction is 
-applied for `EntropyDecomposition`.
-
 
 ## Handling of overlapping parameters
 

From f19beb08d410e5beff02cacf2b1bb8e6c1892bab Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 13:20:00 +0200
Subject: [PATCH 15/24] up minimum julia version to latest LTS

---
 Project.toml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Project.toml b/Project.toml
index a174fb42..6ee42ecd 100644
--- a/Project.toml
+++ b/Project.toml
@@ -49,4 +49,4 @@ StaticArrays = "^1"
 Statistics = "1"
 StatsBase = "^0.34"
 TimeseriesSurrogates = "2.7"
-julia = "^1.10.6"
+julia = "^1.10.10"

From 6abdbb7ca6cda8eef8738452cf6c82d1507a3f7f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 13:29:25 +0200
Subject: [PATCH 16/24] Don't build StateSpaceSets.

---
 docs/make.jl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/make.jl b/docs/make.jl
index 480c8430..6db62037 100644
--- a/docs/make.jl
+++ b/docs/make.jl
@@ -43,7 +43,7 @@ bibliography = CitationBibliography(
     style=:authoryear
 )
 
-build_docs_with_style(pages, Associations, StateSpaceSets;
+build_docs_with_style(pages, Associations;
     expandfirst=["index.md"],
     bib=bibliography,
     pages=pages,

From 26994f00a957f3b921de96f8b199e574386324c0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 13:29:31 +0200
Subject: [PATCH 17/24] Remove temp dep

---
 docs/Project.toml | 1 -
 1 file changed, 1 deletion(-)

diff --git a/docs/Project.toml b/docs/Project.toml
index 3d76c263..ce89e3e0 100644
--- a/docs/Project.toml
+++ b/docs/Project.toml
@@ -1,5 +1,4 @@
 [deps]
-Associations = "614afb3a-e278-4863-8805-9959372b9ec2"
 CairoMakie = "13f3f980-e62b-5c42-98c6-ff1f3baf88f0"
 ComplexityMeasures = "ab4b797d-85ee-42ba-b621-05d793b346a2"
 DelayEmbeddings = "5732040d-69e3-5649-938a-b6b4f237613f"

From 1743f4c6e7fce38007e66860664158efa5dbf5f4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 14:28:47 +0200
Subject: [PATCH 18/24] Force higher versions for packages

DynamicalSystems.jl v2 is loaded during tests??
---
 test/Project.toml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/test/Project.toml b/test/Project.toml
index 952c219d..ae6aef51 100644
--- a/test/Project.toml
+++ b/test/Project.toml
@@ -16,3 +16,8 @@ Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 TimeseriesSurrogates = "c804724b-8c18-5caa-8579-6025a0767c70"
+
+[compat]
+ComplexityMeasures = "^3.8"
+DynamicalSystemsBase = "3"
+julia = "^1.10.10"

From 64ba382dbd77f93803f95357929fb5d8f76cb541 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 14:32:35 +0200
Subject: [PATCH 19/24] Update checkout

---
 .github/workflows/ci.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 3b5f5914..452f4a44 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -29,7 +29,7 @@ jobs:
           access_token: ${{ github.token }}
 
       # Do tests
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v5
       - uses: julia-actions/setup-julia@v1
         with:
           version: ${{ matrix.version }}

From f134ae92bbc09411db2c976279461c74becf9977 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 14:36:43 +0200
Subject: [PATCH 20/24] explicitly add complexitymeasures to test deps

---
 test/Project.toml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/test/Project.toml b/test/Project.toml
index ae6aef51..ca2d3da4 100644
--- a/test/Project.toml
+++ b/test/Project.toml
@@ -1,6 +1,7 @@
 [deps]
 CausalInference = "8e462317-f959-576b-b3c1-403f26cec956"
 Combinatorics = "861a8166-3701-5b0c-9a16-15d98fcdc6aa"
+ComplexityMeasures = "ab4b797d-85ee-42ba-b621-05d793b346a2"
 DelayEmbeddings = "5732040d-69e3-5649-938a-b6b4f237613f"
 Distances = "b4f34e82-e78d-54a5-968a-f98e89d6e8f7"
 Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"

From 4ac9b40dc07e82aefde8dd43c3705f94eccabdf1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 14:53:34 +0200
Subject: [PATCH 21/24] remove direct reference to statespaceset

---
 docs/src/index.md | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/docs/src/index.md b/docs/src/index.md
index 363e2595..42ef905d 100644
--- a/docs/src/index.md
+++ b/docs/src/index.md
@@ -55,10 +55,6 @@ Input data for Associations.jl are given as:
     can be any arbitrarily complex data type (as long as it's hashable), for example
     `Vector{String}`, `{Vector{Int}}`, or `Vector{Tuple{Int, String}}`.
 
-```@docs
-StateSpaceSets.StateSpaceSet
-```
-
 ## Maintainers and contributors
 
 The Associations.jl software is maintained by

From 621d3ca1bd7c64495134ad43dedf9b3e1dc418cf Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 16:33:21 +0200
Subject: [PATCH 22/24] Up versions

---
 Project.toml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Project.toml b/Project.toml
index 6ee42ecd..67e8cd70 100644
--- a/Project.toml
+++ b/Project.toml
@@ -2,7 +2,7 @@ name = "Associations"
 uuid = "614afb3a-e278-4863-8805-9959372b9ec2"
 authors = ["Kristian Agasøster Haaga <kahaaga@gmail.com>", "Tor Einar Møller <temolle@gmail.com>", "George Datseris <datseris.george@gmail.com>"]
 repo = "https://github.com/kahaaga/Associations.jl.git"
-version = "4.4.3"
+version = "4.5.0"
 
 [deps]
 Accessors = "7d9f7c33-5ae7-4f3b-8dc6-eff91059b697"
@@ -32,7 +32,7 @@ TimeseriesSurrogates = "c804724b-8c18-5caa-8579-6025a0767c70"
 Accessors = "^0.1.28"
 Combinatorics = "1"
 ComplexityMeasures = "3.8"
-DSP = "^0.7"
+DSP = "^0.8"
 DelayEmbeddings = "2.8"
 Distances = "^0.10"
 Distributions = "^0.25"

From 9ad51d8c1926dcc0d3a1d63f64b914762dac4ffd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 16:33:28 +0200
Subject: [PATCH 23/24] remove collapse info

---
 docs/src/index.md | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/docs/src/index.md b/docs/src/index.md
index 42ef905d..b787c757 100644
--- a/docs/src/index.md
+++ b/docs/src/index.md
@@ -26,12 +26,6 @@ Important changes are:
 
 The quickest way to get going with the package is to check out the examples in the left-hand menu.
 
-!!! info
-    To make it easier to navigate the extensive documentation, all documentation strings are 
-    collapsed by default. Click the arrow icon in 
-    the top toolbar to expand/collapse the docstrings in a page.
-
-
 ## Documentation content 
 
 - [Association measures](@ref association_measures) lists all implemented association measures and their estimators.

From 4dcff67390eb48a1250e94fcc6f14822ea6b00e9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kristian=20Agas=C3=B8ster=20Haaga?= <kahaaga@gmail.com>
Date: Sun, 17 Aug 2025 16:35:33 +0200
Subject: [PATCH 24/24] less strict dsp requirement

---
 Project.toml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Project.toml b/Project.toml
index 67e8cd70..5808d59e 100644
--- a/Project.toml
+++ b/Project.toml
@@ -32,7 +32,7 @@ TimeseriesSurrogates = "c804724b-8c18-5caa-8579-6025a0767c70"
 Accessors = "^0.1.28"
 Combinatorics = "1"
 ComplexityMeasures = "3.8"
-DSP = "^0.8"
+DSP = "^0.7, 0.8"
 DelayEmbeddings = "2.8"
 Distances = "^0.10"
 Distributions = "^0.25"