diff --git a/.gitlab-ci/pages.yml b/.gitlab-ci/pages.yml
index 4d16a2871e5366acaa6e0a2d2860c888874fbe86..874358de7fa762ee2c5ffb92fcebd338ce42cd05 100644
--- a/.gitlab-ci/pages.yml
+++ b/.gitlab-ci/pages.yml
@@ -9,6 +9,7 @@ pages:
pacman -Sy --noconfirm \
base-devel \
rustup \
+ ripgrep \
python-pytorch \
texlive \
pdf2svg
diff --git a/doc/src/intro.md b/doc/src/intro.md
index 3848078caf4d0169651a1fba5075988f7036dbda..93fcd64ab2c489ed1e84c654f95cd35f48a4be01 100644
--- a/doc/src/intro.md
+++ b/doc/src/intro.md
@@ -20,7 +20,7 @@ and the associated command-line program:
This document assumes that you are familiar
with the method described in the paper.
-Reader interested in the context, the intuition,
+Readers interested in the context, the intuition,
or the meaning of the method
are encouraged to refer to the original paper instead,
as these are not covered here.
@@ -28,7 +28,7 @@ as these are not covered here.
This document explains how to install the `aphid` program
and how to use it.
It also specifies the detail of expected inputs,
-of the calculation performed within the program
+of the calculation performed by the program
and the outputs produced.
Bug reports, feature requests and contributions are welcome [here][repo].
diff --git a/doc/src/learn.md b/doc/src/learn.md
index a577ab96a2ada7f4074cfefd4f5e60ada7647c58..f4e8cf87664db317b6d150f6b905c3a422c06cd2 100644
--- a/doc/src/learn.md
+++ b/doc/src/learn.md
@@ -48,6 +48,7 @@ Then use these as default starting points:
\end{align}
\\]
+(see aphid's [default values for `theta` = \\(𝜃\\)](./use.md#init))
## Reparametrization { #transform }
diff --git a/doc/src/likelihood.md b/doc/src/likelihood.md
index 1be4033b7fb931e2dfd4647e3e3d084bdc1ece8a..8f01eeb3920086e3f0a72e08416fc365c1d078ba 100644
--- a/doc/src/likelihood.md
+++ b/doc/src/likelihood.md
@@ -34,7 +34,8 @@ At the global level:
- \\(\pbc\\) :
probability that GF occured between \\(B\\) and \\(C\\) (*idem*).
- \\(\po\\) :
- probability that GF occured at the **o**ldest date in \\(gt\\) (*idem*).
+ knowing that GF occured,
+ probability it occured at the **o**ldest date in \\(gt\\) (*idem*).
[learn]: ./learn.md
[gft]: ./use.md#gft
@@ -81,7 +82,7 @@ For every gene tree \\(g\\):
The formula values are subject to the following constraints:
- No negative values.
-- \\(\sl_g\\) integer (number of bases)
+- \\(\sl_g\\) integer (number of sites)
- \\(𝜏_1 \leq 𝜏_2\\) (older coalescence last)
- \\(p_* \leq 1\\) (probabilities)
- \\(\pab + \pac + \pbc \leq 1\\) (total probability of GF)
diff --git a/doc/src/preprocess.md b/doc/src/preprocess.md
index 0576ac350c005426b406db6d47a21d3618e910df..a051c2bd98a6a76c4088c7c06eced77f6600de23 100644
--- a/doc/src/preprocess.md
+++ b/doc/src/preprocess.md
@@ -19,12 +19,12 @@ the [`other`](./use.md#other)
section of the input [`[taxa]`](./use.md#taxa) table.
This process reduces the number of node in every tree,
-but the branches lengths are conserved.
+but the branch lengths are conserved.
For instance,
pruning species
`A`, `C`, `E` and `H`
in the following raw gene tree
-with branches lengths `a`, `b`, `c`, *etc.*:
+with branch lengths `a`, `b`, `c`, *etc.*:
```
│q
@@ -148,7 +148,7 @@ The 'imbalance' of every tree is calculated with respect to the whole forest.
\\]
If a tree has a high imbalance value,
it means that it is dissimilar to its enclosing forest,
-and the hypothesis that mutation rate is constant accross the tree(s)
+and the hypothesis that mutation rate is constant accross the tree
is weakened.
The tree geometry is rejected if its imbalance is greater than
diff --git a/src/config/raw.rs b/src/config/raw.rs
index abedb858643b934e31a7b04a25d33b783d205050..6444b4427743eaaf67515c9299999d3df749e09f 100644
--- a/src/config/raw.rs
+++ b/src/config/raw.rs
@@ -28,7 +28,10 @@ pub struct Config {
/// List the relative dates for possible gene flow events.
/// At least one event must be specified,
/// but no more than [`model::parameters::MAX_N_GF_TIMES`].
- /// Dates are relative to the divergence times of the `triplet` species.
+ /// Dates are relative to the A|B divergence time.
+ /// They must take values between 0 and 1:
+ /// 0 meaning present-day gene flow time,
+ /// and 1 meaning that gene flow happened at A|B divergence time.
#[serde(default = "defaults::gf_times")]
pub gf_times: GeneFlowTimes,
@@ -39,11 +42,7 @@ pub struct Config {
/// In this situation,
/// every scenario contributes to the likelihood
/// instead of only the ones with a concordant topology.
- /// The possible internal branch discordance
- /// between actual and expected length
- /// is neglected because the the actual length is small.
- /// For this reason, only values inferior
- /// to [`config::MAX_UNRESOLVED_COUNTS`] are accepted.
+ /// Only values inferior to [`config::MAX_UNRESOLVED_COUNTS`] are accepted.
/// The value is given in *mutations count* units,
/// so branch length × sequence length.
pub unresolved_mutations_count: Option<f64>,
@@ -105,7 +104,7 @@ pub struct Taxa {
/// <tree> <TAB> <sequence_length> <TAB> <identifier>
/// ```
/// The `<tree>` part being a [Newick] representation of the gene tree,
- /// with branches lengths specified.
+ /// with branches lengths specified in unit of 'per site substitution'.
///
/// [Newick]: https://en.wikipedia.org/wiki/Newick_format
///
@@ -113,7 +112,7 @@ pub struct Taxa {
pub trees: PathBuf,
/// This parameter is where you specify
- /// the three species of interest and their phylogenetical topology.
+ /// the triplet of species of interest its topology.
/// Either forms `["A", ["B", "C"]]` or `"(A, (B, C))"` are accepted,
/// provided `A`, `B` and `C` match names within the provided `taxa.trees`.
pub triplet: Triplet,
@@ -127,7 +126,7 @@ pub struct Taxa {
/// Species listed in this parameter
/// are used as extra leaves in the tree
- /// to estimate branch lengths properties.
+ /// to estimate branch length properties.
#[serde_as(as = "FromInto<ListOfStrings>")]
pub other: Vec<String>,
}