Files
trueskill-tt/src/game.rs
T
logaritmiskandClaude Opus 5 633a503900 refactor!: remove the factor-graph surface nothing used, add try_winner
Two decisions taken before cutting 0.5.0.

#42 — the `Schedule` trait was public API the engine never called. Its
only call site was `Game::custom`, itself `#[doc(hidden)]`, and
`EpsilonOrMax` was never constructed anywhere. Removing that surface
showed the problem was larger than the issue described: with `custom`
gone, the compiler found `Factor`, `BuiltinFactor`, `RankDiffFactor` and
`TeamSumFactor` all dead too.

`Game::run_chain` drives a local `DiffFactor` enum and bypasses the
whole T1 abstraction — it has done since it was written. So this is not
just an unused extension point but the machinery it was built on, and
`CLAUDE.md` was documenting it as live architecture.

Removed: `graph` module, `Schedule`, `EpsilonOrMax`, `ScheduleReport`,
`Game::custom`, `Factor`, `BuiltinFactor`, `RankDiffFactor`,
`TeamSumFactor`. `TruncFactor`, `MarginFactor`, `VarStore` and `VarId`
stay — inference uses those. The measurement behind choosing removal
over wiring is in #42: the within-game loop converges in 1 to 8
iterations against a cap of 30, so a `Residual` schedule has no headroom
to reclaim, and `Damped` already shipped as `ConvergenceOptions::alpha`.

#20 — `Outcome::winner` panicking on an out-of-range index. Kept, and
the reasoning is now on the method. It is the only constructor here that
validates, which looks inconsistent until you try deferring like its
siblings: `winner(5, 2)` produces ranks `[1, 1]`, an all-tied draw that
ingestion accepts without complaint when `p_draw > 0`. Asking "team 5
won" and silently getting "everyone drew" is the exact failure this
crate keeps removing, so the check belongs where the mistake is.

Adds `Outcome::try_winner` for indices that are computed or parsed
rather than written literally, following the `new`/`try_new` convention.
That is additive; the panicking form stays because every call site in
this repo, its tests and its README passes literals, where a `?` would
be noise.

BREAKING CHANGE: the `graph` module and everything it exported are
removed, as are `Game::custom` and `ScheduleReport`.

Closes #42. Closes #20.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011hcFjNDmHXZF8URGLku5zZ
2026-09-08 02:14:43 +02:00

1460 lines
45 KiB
Rust
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
use std::cmp::Ordering;
use crate::{
N_INF, N00,
arena::ScratchArena,
compute_margin,
drift::Drift,
factor::{VarId, margin::MarginFactor, trunc::TruncFactor},
gaussian::Gaussian,
rating::Rating,
time::Time,
tuple_gt, tuple_max,
};
/// Per-adjacent-pair link factor in the game's diff chain.
///
/// `Trunc` is used for `Outcome::Ranked` (rank-based truncation).
/// `Margin` is used for `Outcome::Scored` (Gaussian observation on the diff).
#[derive(Debug)]
pub(crate) enum DiffFactor {
Trunc(TruncFactor),
Margin(MarginFactor),
}
impl DiffFactor {
pub(crate) fn diff(&self) -> VarId {
match self {
Self::Trunc(f) => f.diff,
Self::Margin(f) => f.diff,
}
}
pub(crate) fn msg(&self) -> Gaussian {
match self {
Self::Trunc(f) => f.msg,
Self::Margin(f) => f.msg,
}
}
/// Log of this link's cached evidence.
///
/// Accumulating in log space keeps a long diff chain from underflowing:
/// each link contributes a probability in `(0, 1]`, so the linear product
/// over an n-team game decays geometrically and flushes to zero — and
/// `ln(0.0)` is `-inf` — well within the team counts a large free-for-all
/// reaches.
pub(crate) fn log_evidence(&self) -> f64 {
match self {
Self::Trunc(f) => f.log_evidence_cached.unwrap_or(0.0),
Self::Margin(f) => f.log_evidence_cached.unwrap_or(0.0),
}
}
pub(crate) fn propagate(
&mut self,
vars: &mut crate::factor::VarStore,
alpha: f64,
) -> (f64, f64) {
match self {
Self::Trunc(f) => f.propagate_with_alpha(vars, alpha),
Self::Margin(f) => f.propagate_with_alpha(vars, alpha),
}
}
}
/// Per-game inference options.
///
/// `p_draw` and `convergence` apply to ranked outcomes (`Game::ranked`).
/// `score_sigma` applies only to scored outcomes (`Game::scored`); it controls
/// how much the engine trusts the observed score margin (smaller σ = more trust).
#[derive(Clone, Copy, Debug)]
pub struct GameOptions {
pub p_draw: f64,
pub score_sigma: f64,
pub convergence: crate::ConvergenceOptions,
}
impl Default for GameOptions {
fn default() -> Self {
Self {
p_draw: crate::P_DRAW,
score_sigma: 1.0,
convergence: crate::ConvergenceOptions::default(),
}
}
}
/// Owned variant of `Game` returned by public constructors.
///
/// Unlike `Game<'a, T, D>` (which borrows its result/weights slices from
/// History's internal state), `OwnedGame<T, D>` owns the team ratings, so it
/// can be returned freely from public constructors. The inference inputs
/// themselves are not retained — nothing reads them back.
#[derive(Debug)]
pub struct OwnedGame<T: Time, D: Drift<T>> {
teams: Vec<Vec<Rating<T, D>>>,
pub(crate) likelihoods: Vec<Vec<Gaussian>>,
pub(crate) log_evidence: f64,
}
impl<T: Time, D: Drift<T>> OwnedGame<T, D> {
pub(crate) fn new(
teams: Vec<Vec<Rating<T, D>>>,
result: Vec<f64>,
weights: Vec<Vec<f64>>,
p_draw: f64,
convergence: crate::ConvergenceOptions,
) -> Self {
let mut arena = ScratchArena::new();
// `Game` takes the teams by value and is dropped here, so take the vec
// back out of it rather than handing it a clone.
let g = Game::ranked_with_arena(teams, &result, &weights, p_draw, convergence, &mut arena);
Self {
teams: g.teams,
likelihoods: g.likelihoods,
log_evidence: g.log_evidence,
}
}
pub(crate) fn new_scored(
teams: Vec<Vec<Rating<T, D>>>,
scores: Vec<f64>,
weights: Vec<Vec<f64>>,
score_sigma: f64,
convergence: crate::ConvergenceOptions,
) -> Self {
let mut arena = ScratchArena::new();
let g = Game::scored_with_arena(
teams,
&scores,
&weights,
score_sigma,
convergence,
&mut arena,
);
Self {
teams: g.teams,
likelihoods: g.likelihoods,
log_evidence: g.log_evidence,
}
}
#[must_use]
pub fn posteriors(&self) -> Vec<Vec<Gaussian>> {
self.likelihoods
.iter()
.zip(self.teams.iter())
.map(|(l, t)| l.iter().zip(t.iter()).map(|(&l, r)| l * r.prior).collect())
.collect()
}
#[must_use]
pub fn log_evidence(&self) -> f64 {
self.log_evidence
}
}
#[derive(Debug)]
pub struct Game<'a, T: Time = i64, D: Drift<T> = crate::drift::ConstantDrift> {
teams: Vec<Vec<Rating<T, D>>>,
result: &'a [f64],
weights: &'a [Vec<f64>],
p_draw: f64,
pub(crate) convergence: crate::ConvergenceOptions,
pub(crate) likelihoods: Vec<Vec<Gaussian>>,
pub(crate) log_evidence: f64,
}
impl<'a, T: Time, D: Drift<T>> Game<'a, T, D> {
pub(crate) fn ranked_with_arena(
teams: Vec<Vec<Rating<T, D>>>,
result: &'a [f64],
weights: &'a [Vec<f64>],
p_draw: f64,
convergence: crate::ConvergenceOptions,
arena: &mut ScratchArena,
) -> Self {
debug_assert!(
result.len() == teams.len(),
"result must have the same length as teams"
);
debug_assert!(
weights
.iter()
.zip(teams.iter())
.all(|(w, t)| w.len() == t.len()),
"weights must have the same dimensions as teams"
);
debug_assert!(
(0.0..1.0).contains(&p_draw),
"draw probability must be >= 0.0 and < 1.0"
);
debug_assert!(
p_draw > 0.0 || {
let mut r = result.to_vec();
r.sort_unstable_by(|a, b| a.partial_cmp(b).unwrap());
r.windows(2).all(|w| w[0] != w[1])
},
"draw must be > 0.0 if there are teams with draw"
);
debug_assert!(
convergence.alpha > 0.0 && convergence.alpha <= 1.0,
"convergence alpha must be in (0.0, 1.0]"
);
let mut this = Self {
teams,
result,
weights,
p_draw,
convergence,
likelihoods: Vec::new(),
log_evidence: 0.0,
};
this.likelihoods(arena);
this
}
pub(crate) fn scored_with_arena(
teams: Vec<Vec<Rating<T, D>>>,
scores: &'a [f64],
weights: &'a [Vec<f64>],
score_sigma: f64,
convergence: crate::ConvergenceOptions,
arena: &mut ScratchArena,
) -> Self {
debug_assert!(
scores.len() == teams.len(),
"scores must have the same length as teams"
);
debug_assert!(
weights
.iter()
.zip(teams.iter())
.all(|(w, t)| w.len() == t.len()),
"weights must have the same dimensions as teams"
);
debug_assert!(score_sigma > 0.0, "score_sigma must be positive");
debug_assert!(
convergence.alpha > 0.0 && convergence.alpha <= 1.0,
"convergence alpha must be in (0.0, 1.0]"
);
let mut this = Self {
teams,
result: scores,
weights,
p_draw: 0.0,
convergence,
likelihoods: Vec::new(),
log_evidence: 0.0,
};
this.likelihoods_scored(arena, score_sigma);
this
}
fn run_chain<F>(&self, arena: &mut ScratchArena, mut make_link: F) -> (f64, Vec<Vec<Gaussian>>)
where
F: FnMut(usize, &[usize], &mut crate::factor::VarStore) -> DiffFactor,
{
arena.reset();
let alpha = self.convergence.alpha;
let epsilon = self.convergence.epsilon;
let max_iter = self.convergence.max_iter;
let n_teams = self.teams.len();
arena.sort_buf.extend(0..n_teams);
arena.sort_buf.sort_by(|&i, &j| {
self.result[j]
.partial_cmp(&self.result[i])
.unwrap_or(Ordering::Equal)
});
arena.team_prior.extend(arena.sort_buf.iter().map(|&t| {
self.teams[t]
.iter()
.zip(self.weights[t].iter())
.fold(N00, |p, (player, &w)| p + (player.performance() * w))
}));
let n_diffs = n_teams.saturating_sub(1);
let mut links: Vec<DiffFactor> = (0..n_diffs)
.map(|i| make_link(i, &arena.sort_buf, &mut arena.vars))
.collect();
arena.lhood_lose.resize(n_teams, N_INF);
arena.lhood_win.resize(n_teams, N_INF);
let mut step = (f64::INFINITY, f64::INFINITY);
let mut iter = 0;
while tuple_gt(step, epsilon) && iter < max_iter {
step = (0.0_f64, 0.0_f64);
for (e, lf) in links[..n_diffs.saturating_sub(1)].iter_mut().enumerate() {
let pw = arena.team_prior[e] * arena.lhood_lose[e];
let pl = arena.team_prior[e + 1] * arena.lhood_win[e + 1];
let raw = pw - pl;
arena.vars.set(lf.diff(), raw * lf.msg());
let d = lf.propagate(&mut arena.vars, alpha);
step = tuple_max(step, d);
let new_ll = pw - lf.msg();
step = tuple_max(step, arena.lhood_lose[e + 1].delta(new_ll));
arena.lhood_lose[e + 1] = new_ll;
}
for (rev_i, lf) in links[1..].iter_mut().rev().enumerate() {
let e = n_diffs - 1 - rev_i;
let pw = arena.team_prior[e] * arena.lhood_lose[e];
let pl = arena.team_prior[e + 1] * arena.lhood_win[e + 1];
let raw = pw - pl;
arena.vars.set(lf.diff(), raw * lf.msg());
let d = lf.propagate(&mut arena.vars, alpha);
step = tuple_max(step, d);
let new_lw = pl + lf.msg();
step = tuple_max(step, arena.lhood_win[e].delta(new_lw));
arena.lhood_win[e] = new_lw;
}
iter += 1;
}
// Special case: exactly 1 diff (2-team game); loop body was empty.
if n_diffs == 1 {
let raw = (arena.team_prior[0] * arena.lhood_lose[0])
- (arena.team_prior[1] * arena.lhood_win[1]);
arena.vars.set(links[0].diff(), raw * links[0].msg());
links[0].propagate(&mut arena.vars, alpha);
}
// Boundary updates: close the chain at both ends.
if n_diffs > 0 {
let pl1 = arena.team_prior[1] * arena.lhood_win[1];
arena.lhood_win[0] = pl1 + links[0].msg();
let pw_last = arena.team_prior[n_teams - 2] * arena.lhood_lose[n_teams - 2];
arena.lhood_lose[n_teams - 1] = pw_last - links[n_diffs - 1].msg();
}
let log_evidence: f64 = links.iter().map(DiffFactor::log_evidence).sum();
// Inverse permutation: inv_buf[orig_i] = sorted_i.
arena.inv_buf.resize(n_teams, 0);
for (si, &orig_i) in arena.sort_buf.iter().enumerate() {
arena.inv_buf[orig_i] = si;
}
let likelihoods = self
.teams
.iter()
.zip(self.weights.iter())
.enumerate()
.map(|(orig_i, (players, weights))| {
let si = arena.inv_buf[orig_i];
let m = arena.lhood_win[si] * arena.lhood_lose[si];
// Already folded into `team_prior` at the top of the chain,
// indexed by sorted position.
let performance = arena.team_prior[si];
players
.iter()
.zip(weights.iter())
.map(|(player, &w)| {
((m - performance.exclude(player.performance() * w)) * (1.0 / w))
.forget(player.beta.powi(2))
})
.collect::<Vec<_>>()
})
.collect::<Vec<_>>();
(log_evidence, likelihoods)
}
fn likelihoods(&mut self, arena: &mut ScratchArena) {
let (log_evidence, likelihoods) = self.run_chain(arena, |i, sort_buf, vars| {
let tie = self.result[sort_buf[i]] == self.result[sort_buf[i + 1]];
let margin = if self.p_draw == 0.0 {
0.0
} else {
let a: f64 = self.teams[sort_buf[i]].iter().map(|p| p.beta.powi(2)).sum();
let b: f64 = self.teams[sort_buf[i + 1]]
.iter()
.map(|p| p.beta.powi(2))
.sum();
compute_margin(self.p_draw, (a + b).sqrt())
};
let vid = vars.alloc(N_INF);
DiffFactor::Trunc(TruncFactor::new(vid, margin, tie))
});
self.log_evidence = log_evidence;
self.likelihoods = likelihoods;
}
fn likelihoods_scored(&mut self, arena: &mut ScratchArena, score_sigma: f64) {
let (log_evidence, likelihoods) = self.run_chain(arena, |i, sort_buf, vars| {
let m_obs = self.result[sort_buf[i]] - self.result[sort_buf[i + 1]];
let vid = vars.alloc(N_INF);
DiffFactor::Margin(MarginFactor::new(vid, m_obs, score_sigma))
});
self.log_evidence = log_evidence;
self.likelihoods = likelihoods;
}
#[must_use]
pub fn posteriors(&self) -> Vec<Vec<Gaussian>> {
self.likelihoods
.iter()
.zip(self.teams.iter())
.map(|(l, t)| {
l.iter()
.zip(t.iter())
.map(|(&l, p)| l * p.prior)
.collect::<Vec<_>>()
})
.collect::<Vec<_>>()
}
#[must_use]
pub fn log_evidence(&self) -> f64 {
self.log_evidence
}
}
impl<T: Time, D: Drift<T>> Game<'_, T, D> {
/// # Errors
///
/// - `InvalidParameter` if `options.convergence` is out of range — an
/// `alpha` of zero would leave every EP update unapplied and silently
/// return the priors.
/// - `InvalidProbability` if `options.p_draw` is outside `[0.0, 1.0)`.
/// - `MismatchedShape` if the outcome's rank count differs from `teams.len()`.
/// - `WrongOutcomeKind` if `outcome` is not `Outcome::Ranked`.
/// - `TieWithoutDrawProbability` if the outcome ties two teams while
/// `p_draw` is zero: the truncation margin is then zero and the two-sided
/// tie update evaluates `0/0`.
pub fn ranked(
teams: &[&[Rating<T, D>]],
outcome: crate::Outcome,
options: &GameOptions,
) -> Result<OwnedGame<T, D>, crate::InferenceError> {
options.convergence.validate()?;
if !(0.0..1.0).contains(&options.p_draw) {
return Err(crate::InferenceError::InvalidProbability {
value: options.p_draw,
});
}
if outcome.team_count() != teams.len() {
return Err(crate::InferenceError::MismatchedShape {
kind: "outcome ranks vs teams",
expected: teams.len(),
got: outcome.team_count(),
});
}
let ranks = outcome
.as_ranks()
.ok_or(crate::InferenceError::WrongOutcomeKind {
context: "Game::ranked",
expected: "Outcome::Ranked",
got: "Outcome::Scored",
})?;
let tied = if options.p_draw == 0.0 {
crate::first_tied_pair(ranks)
} else {
None
};
if let Some(teams) = tied {
return Err(crate::InferenceError::TieWithoutDrawProbability { teams });
}
let max_rank = ranks.iter().copied().max().unwrap_or(0) as f64;
let result: Vec<f64> = ranks.iter().map(|&r| max_rank - r as f64).collect();
let teams_owned: Vec<Vec<Rating<T, D>>> = teams.iter().map(|t| t.to_vec()).collect();
let weights: Vec<Vec<f64>> = teams.iter().map(|t| vec![1.0; t.len()]).collect();
Ok(OwnedGame::new(
teams_owned,
result,
weights,
options.p_draw,
options.convergence,
))
}
/// # Errors
///
/// - `InvalidParameter` if `options.score_sigma` is not strictly positive
/// or is NaN, or if `options.convergence` is out of range.
/// - `MismatchedShape` if the outcome's score count differs from `teams.len()`.
/// - `WrongOutcomeKind` if `outcome` is not `Outcome::Scored`.
pub fn scored(
teams: &[&[Rating<T, D>]],
outcome: crate::Outcome,
options: &GameOptions,
) -> Result<OwnedGame<T, D>, crate::InferenceError> {
options.convergence.validate()?;
if options.score_sigma <= 0.0 || options.score_sigma.is_nan() {
return Err(crate::InferenceError::InvalidParameter {
name: "score_sigma",
value: options.score_sigma,
});
}
if outcome.team_count() != teams.len() {
return Err(crate::InferenceError::MismatchedShape {
kind: "outcome scores vs teams",
expected: teams.len(),
got: outcome.team_count(),
});
}
let scores = outcome
.as_scores()
.ok_or(crate::InferenceError::WrongOutcomeKind {
context: "Game::scored",
expected: "Outcome::Scored",
got: "Outcome::Ranked",
})?
.to_vec();
let teams_owned: Vec<Vec<Rating<T, D>>> = teams.iter().map(|t| t.to_vec()).collect();
let weights: Vec<Vec<f64>> = teams.iter().map(|t| vec![1.0; t.len()]).collect();
Ok(OwnedGame::new_scored(
teams_owned,
scores,
weights,
options.score_sigma,
options.convergence,
))
}
/// Convenience wrapper over [`Game::ranked`] for two single-player teams.
///
/// # Errors
///
/// Delegates to [`Game::ranked`], so it returns the same errors — in
/// practice `WrongOutcomeKind` for a non-ranked outcome, or
/// `TieWithoutDrawProbability` for a draw when `options.p_draw` is zero.
pub fn one_v_one(
a: &Rating<T, D>,
b: &Rating<T, D>,
outcome: crate::Outcome,
options: &GameOptions,
) -> Result<(Gaussian, Gaussian), crate::InferenceError> {
let game = Self::ranked(&[&[*a], &[*b]], outcome, options)?;
let post = game.posteriors();
Ok((post[0][0], post[1][0]))
}
/// # Errors
///
/// Wraps each player in a one-member team and delegates to
/// [`Game::ranked`], so it returns the same errors.
pub fn free_for_all(
players: &[&Rating<T, D>],
outcome: crate::Outcome,
options: &GameOptions,
) -> Result<OwnedGame<T, D>, crate::InferenceError> {
let teams: Vec<Vec<Rating<T, D>>> = players.iter().map(|p| vec![**p]).collect();
let team_refs: Vec<&[Rating<T, D>]> = teams.iter().map(|t| t.as_slice()).collect();
Self::ranked(&team_refs, outcome, options)
}
}
#[cfg(test)]
mod tests {
use ::approx::assert_ulps_eq;
use super::*;
use crate::{ConstantDrift, GAMMA, Gaussian, N_INF, Rating, arena::ScratchArena};
type R = Rating<i64, ConstantDrift>;
#[test]
fn test_1vs1() {
let t_a = R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let t_b = R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let w = [vec![1.0], vec![1.0]];
let g = Game::ranked_with_arena(
vec![vec![t_a], vec![t_b]],
&[0.0, 1.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
let a = p[0][0];
let b = p[1][0];
assert_ulps_eq!(a, Gaussian::from_ms(20.794779, 7.194481), epsilon = 1e-6);
assert_ulps_eq!(b, Gaussian::from_ms(29.205220, 7.194481), epsilon = 1e-6);
let t_a = R::new(
Gaussian::from_ms(29.0, 1.0),
25.0 / 6.0,
ConstantDrift(GAMMA),
);
let t_b = R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(GAMMA),
);
let w = [vec![1.0], vec![1.0]];
let g = Game::ranked_with_arena(
vec![vec![t_a], vec![t_b]],
&[0.0, 1.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
let a = p[0][0];
let b = p[1][0];
assert_ulps_eq!(a, Gaussian::from_ms(28.896475, 0.996604), epsilon = 1e-6);
assert_ulps_eq!(b, Gaussian::from_ms(32.189211, 6.062063), epsilon = 1e-6);
let t_a = R::new(Gaussian::from_ms(1.139, 0.531), 1.0, ConstantDrift(0.2125));
let t_b = R::new(Gaussian::from_ms(15.568, 0.51), 1.0, ConstantDrift(0.2125));
let w = [vec![1.0], vec![1.0]];
let g = Game::ranked_with_arena(
vec![vec![t_a], vec![t_b]],
&[0.0, 1.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
assert_eq!(g.likelihoods[0][0], N_INF);
assert_eq!(g.likelihoods[1][0], N_INF);
}
#[test]
fn test_1vs1vs1() {
let teams = vec![
vec![R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
)],
vec![R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
)],
vec![R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
)],
];
let w = [vec![1.0], vec![1.0], vec![1.0]];
let g = Game::ranked_with_arena(
teams.clone(),
&[1.0, 2.0, 0.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
let a = p[0][0];
let b = p[1][0];
assert_ulps_eq!(a, Gaussian::from_ms(25.000000, 6.238469), epsilon = 1e-6);
assert_ulps_eq!(b, Gaussian::from_ms(31.311358, 6.698818), epsilon = 1e-6);
let w = [vec![1.0], vec![1.0], vec![1.0]];
let g = Game::ranked_with_arena(
teams.clone(),
&[2.0, 1.0, 0.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
let a = p[0][0];
let b = p[1][0];
assert_ulps_eq!(a, Gaussian::from_ms(31.311358, 6.698818), epsilon = 1e-6);
assert_ulps_eq!(b, Gaussian::from_ms(25.000000, 6.238469), epsilon = 1e-6);
let w = [vec![1.0], vec![1.0], vec![1.0]];
let g = Game::ranked_with_arena(
teams,
&[1.0, 2.0, 0.0],
&w,
0.5,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
let a = p[0][0];
let b = p[1][0];
let c = p[2][0];
// T1 ULP shift: mu rounds to 25.0 (was 24.999999) under natural-parameter storage.
//
// The 1e-6-place values moved when `erfc_inv`'s sign error was fixed:
// this case runs at `p_draw = 0.5`, so it goes through `compute_margin`,
// and the margin is now 8.4e-8 from the exact quantile where it was
// 1.46e-7. Verified as movement *toward* analytic truth, not a
// regression — see `erfc_inv_matches_known_quantiles`.
assert_ulps_eq!(a, Gaussian::from_ms(25.0, 6.092561), epsilon = 1e-6);
assert_ulps_eq!(b, Gaussian::from_ms(33.379315, 6.483576), epsilon = 1e-6);
assert_ulps_eq!(c, Gaussian::from_ms(16.620685, 6.483576), epsilon = 1e-6);
}
#[test]
fn test_1vs1_draw() {
let t_a = R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let t_b = R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let w = [vec![1.0], vec![1.0]];
let g = Game::ranked_with_arena(
vec![vec![t_a], vec![t_b]],
&[0.0, 0.0],
&w,
0.25,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
let a = p[0][0];
let b = p[1][0];
// Two identical competitors drawing must land on their shared prior
// mean exactly, by symmetry. The reference transcription of 24.999999
// is that value rounded to six decimals; asserting it at epsilon 1e-6
// left no headroom. The root-free variance path now hits 25.0 exactly.
assert_ulps_eq!(a, Gaussian::from_ms(25.0, 6.469480), epsilon = 1e-6);
assert_ulps_eq!(b, Gaussian::from_ms(25.0, 6.469480), epsilon = 1e-6);
let t_a = R::new(
Gaussian::from_ms(25.0, 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let t_b = R::new(
Gaussian::from_ms(29.0, 2.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let w = [vec![1.0], vec![1.0]];
let g = Game::ranked_with_arena(
vec![vec![t_a], vec![t_b]],
&[0.0, 0.0],
&w,
0.25,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
let a = p[0][0];
let b = p[1][0];
assert_ulps_eq!(a, Gaussian::from_ms(25.736001, 2.709956), epsilon = 1e-6);
assert_ulps_eq!(b, Gaussian::from_ms(28.672888, 1.916471), epsilon = 1e-6);
}
#[test]
fn test_1vs1vs1_draw() {
let t_a = R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let t_b = R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let t_c = R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let w = [vec![1.0], vec![1.0], vec![1.0]];
let g = Game::ranked_with_arena(
vec![vec![t_a], vec![t_b], vec![t_c]],
&[0.0, 0.0, 0.0],
&w,
0.25,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
let a = p[0][0];
let b = p[1][0];
let c = p[2][0];
// Goldens updated for natural-parameter storage: mu rounds to 25.0 (was 24.999999),
// sigma shifts by ~3e-7 ULPs (within 1e-6 of original). Both bounded differences.
assert_ulps_eq!(a, Gaussian::from_ms(25.0, 5.729069), epsilon = 1e-6);
assert_ulps_eq!(b, Gaussian::from_ms(25.0, 5.707424), epsilon = 1e-6);
assert_ulps_eq!(c, Gaussian::from_ms(25.0, 5.729069), epsilon = 1e-6);
let t_a = R::new(
Gaussian::from_ms(25.0, 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let t_b = R::new(
Gaussian::from_ms(25.0, 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let t_c = R::new(
Gaussian::from_ms(29.0, 2.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let w = [vec![1.0], vec![1.0], vec![1.0]];
let g = Game::ranked_with_arena(
vec![vec![t_a], vec![t_b], vec![t_c]],
&[0.0, 0.0, 0.0],
&w,
0.25,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
let a = p[0][0];
let b = p[1][0];
let c = p[2][0];
assert_ulps_eq!(a, Gaussian::from_ms(25.488507, 2.638208), epsilon = 1e-6);
assert_ulps_eq!(b, Gaussian::from_ms(25.510671, 2.628751), epsilon = 1e-6);
assert_ulps_eq!(c, Gaussian::from_ms(28.555920, 1.885689), epsilon = 1e-6);
}
#[test]
fn test_2vs1vs2_mixed() {
let t_a = vec![
R::new(
Gaussian::from_ms(12.0, 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
),
R::new(
Gaussian::from_ms(18.0, 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
),
];
let t_b = vec![R::new(
Gaussian::from_ms(30.0, 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
)];
let t_c = vec![
R::new(
Gaussian::from_ms(14.0, 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
),
R::new(
Gaussian::from_ms(16., 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
),
];
let w = [vec![1.0, 1.0], vec![1.0], vec![1.0, 1.0]];
let g = Game::ranked_with_arena(
vec![t_a, t_b, t_c],
&[1.0, 0.0, 0.0],
&w,
0.25,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
assert_ulps_eq!(p[0][0], Gaussian::from_ms(13.051, 2.864), epsilon = 1e-3);
assert_ulps_eq!(p[0][1], Gaussian::from_ms(19.051, 2.864), epsilon = 1e-3);
assert_ulps_eq!(p[1][0], Gaussian::from_ms(29.292, 2.764), epsilon = 1e-3);
assert_ulps_eq!(p[2][0], Gaussian::from_ms(13.658, 2.813), epsilon = 1e-3);
assert_ulps_eq!(p[2][1], Gaussian::from_ms(15.658, 2.813), epsilon = 1e-3);
}
#[test]
fn test_1vs1_weighted() {
let w_a = vec![1.0];
let w_b = vec![2.0];
let t_a = vec![R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(0.0),
)];
let t_b = vec![R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(0.0),
)];
let w = [w_a, w_b];
let g = Game::ranked_with_arena(
vec![t_a.clone(), t_b.clone()],
&[1.0, 0.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
assert_ulps_eq!(
p[0][0],
Gaussian::from_ms(30.625173, 7.765472),
epsilon = 1e-6
);
assert_ulps_eq!(
p[1][0],
Gaussian::from_ms(13.749653, 5.733840),
epsilon = 1e-6
);
let w_a = vec![1.0];
let w_b = vec![0.7];
let w = [w_a, w_b];
let g = Game::ranked_with_arena(
vec![t_a.clone(), t_b.clone()],
&[1.0, 0.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
assert_ulps_eq!(
p[0][0],
Gaussian::from_ms(27.630080, 7.206676),
epsilon = 1e-6
);
assert_ulps_eq!(
p[1][0],
Gaussian::from_ms(23.158943, 7.801628),
epsilon = 1e-6
);
let w_a = vec![1.6];
let w_b = vec![0.7];
let w = [w_a, w_b];
let g = Game::ranked_with_arena(
vec![t_a, t_b],
&[1.0, 0.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
assert_ulps_eq!(
p[0][0],
Gaussian::from_ms(26.142438, 7.573088),
epsilon = 1e-6
);
assert_ulps_eq!(
p[1][0],
Gaussian::from_ms(24.500183, 8.193278),
epsilon = 1e-6
);
let w_a = vec![1.0];
let w_b = vec![0.0];
let t_a = vec![R::new(Gaussian::from_ms(2.0, 6.0), 1.0, ConstantDrift(0.0))];
let t_b = vec![R::new(Gaussian::from_ms(2.0, 6.0), 1.0, ConstantDrift(0.0))];
let w = [w_a, w_b];
let g = Game::ranked_with_arena(
vec![t_a, t_b],
&[1.0, 0.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
assert_ulps_eq!(
p[0][0],
Gaussian::from_ms(5.557067, 4.052826),
epsilon = 1e-6
);
assert_ulps_eq!(
p[1][0],
Gaussian::from_ms(2.000000, 6.000000),
epsilon = 1e-6
);
let w_a = vec![1.0];
let w_b = vec![-1.0];
let t_a = vec![R::new(Gaussian::from_ms(2.0, 6.0), 1.0, ConstantDrift(0.0))];
let t_b = vec![R::new(Gaussian::from_ms(2.0, 6.0), 1.0, ConstantDrift(0.0))];
let w = [w_a, w_b];
let g = Game::ranked_with_arena(
vec![t_a, t_b],
&[1.0, 0.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
assert_ulps_eq!(p[0][0], p[1][0], epsilon = 1e-6);
}
#[test]
fn diff_factor_dispatch_trunc_and_margin() {
use super::DiffFactor;
use crate::factor::{VarStore, margin::MarginFactor, trunc::TruncFactor};
let mut vars = VarStore::new();
let dt = vars.alloc(Gaussian::from_ms(0.0, 6.0));
let dm = vars.alloc(Gaussian::from_ms(0.0, 6.0));
let mut t = DiffFactor::Trunc(TruncFactor::new(dt, 0.0, false));
let mut m = DiffFactor::Margin(MarginFactor::new(dm, 5.0, 1.0));
let _ = t.propagate(&mut vars, 1.0);
let _ = m.propagate(&mut vars, 1.0);
// Smoke: both diffs got written; their msgs are non-N_INF.
assert!(t.msg().pi() > 0.0);
assert!(m.msg().pi() > 0.0);
assert_eq!(t.diff(), dt);
assert_eq!(m.diff(), dm);
}
#[test]
fn scored_path_sharper_when_margin_is_large() {
let prior = R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let teams = vec![vec![prior], vec![prior]];
let result = vec![10.0, 0.0]; // a beat b by 10
let weights = [vec![1.0], vec![1.0]];
let mut arena = ScratchArena::new();
let g = Game::scored_with_arena(
teams,
&result,
&weights,
1.0,
crate::ConvergenceOptions::default(),
&mut arena,
);
let p = g.posteriors();
let a = p[0][0];
let b = p[1][0];
assert!(
a.mu() > b.mu(),
"expected team a posterior mu > team b; got {} vs {}",
a.mu(),
b.mu()
);
// Tighter score_sigma should produce a stronger update.
let mut arena2 = ScratchArena::new();
let g_tight = Game::scored_with_arena(
vec![vec![prior], vec![prior]],
&result,
&weights,
0.1,
crate::ConvergenceOptions::default(),
&mut arena2,
);
let p_tight = g_tight.posteriors();
let a_tight = p_tight[0][0];
assert!(
a_tight.mu() > a.mu(),
"expected tighter sigma to push posterior further; {} vs {}",
a_tight.mu(),
a.mu()
);
}
#[test]
fn game_scored_public_ctor() {
use crate::Outcome;
let prior = R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let opts = GameOptions {
score_sigma: 1.0,
..GameOptions::default()
};
let g = Game::scored(&[&[prior], &[prior]], Outcome::scores([8.0, 2.0]), &opts).unwrap();
let p = g.posteriors();
assert!(p[0][0].mu() > p[1][0].mu());
}
#[test]
fn game_scored_rejects_ranked_outcome() {
let prior = R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let err = Game::scored(
&[&[prior], &[prior]],
crate::Outcome::winner(0, 2),
&GameOptions::default(),
)
.unwrap_err();
assert!(matches!(
err,
crate::InferenceError::WrongOutcomeKind { .. }
));
}
#[test]
fn game_scored_rejects_zero_score_sigma() {
let prior = R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(25.0 / 300.0),
);
let opts = GameOptions {
score_sigma: 0.0,
..GameOptions::default()
};
let err = Game::scored(
&[&[prior], &[prior]],
crate::Outcome::scores([1.0, 0.0]),
&opts,
)
.unwrap_err();
assert!(matches!(
err,
crate::InferenceError::InvalidParameter {
name: "score_sigma",
..
}
));
}
#[test]
fn test_2vs2_weighted() {
let t_a = vec![
R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(0.0),
),
R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(0.0),
),
];
let w_a = vec![0.4, 0.8];
let t_b = vec![
R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(0.0),
),
R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(0.0),
),
];
let w_b = vec![0.9, 0.6];
let w = [w_a, w_b];
let g = Game::ranked_with_arena(
vec![t_a.clone(), t_b.clone()],
&[1.0, 0.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
assert_ulps_eq!(
p[0][0],
Gaussian::from_ms(27.539023, 8.129639),
epsilon = 1e-6
);
assert_ulps_eq!(
p[0][1],
Gaussian::from_ms(30.078046, 7.485372),
epsilon = 1e-6
);
assert_ulps_eq!(
p[1][0],
Gaussian::from_ms(19.287198285, 7.243465848),
epsilon = 1e-6
);
assert_ulps_eq!(
p[1][1],
Gaussian::from_ms(21.191465, 7.867608),
epsilon = 1e-6
);
let w_a = vec![1.3, 1.5];
let w_b = vec![0.7, 0.4];
let w = [w_a, w_b];
let g = Game::ranked_with_arena(
vec![t_a.clone(), t_b.clone()],
&[1.0, 0.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
assert_ulps_eq!(
p[0][0],
Gaussian::from_ms(25.190190, 8.220511),
epsilon = 1e-6
);
assert_ulps_eq!(
p[0][1],
Gaussian::from_ms(25.219450, 8.182783),
epsilon = 1e-6
);
assert_ulps_eq!(
p[1][0],
Gaussian::from_ms(24.897589, 8.300779),
epsilon = 1e-6
);
assert_ulps_eq!(
p[1][1],
Gaussian::from_ms(24.941479, 8.322717),
epsilon = 1e-6
);
let w_a = vec![1.6, 0.2];
let w_b = vec![0.7, 2.4];
let w = [w_a, w_b];
let g = Game::ranked_with_arena(
vec![t_a.clone(), t_b.clone()],
&[1.0, 0.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
assert_ulps_eq!(
p[0][0],
Gaussian::from_ms(31.674698083, 7.501180037),
epsilon = 1e-6
);
assert_ulps_eq!(
p[0][1],
Gaussian::from_ms(25.834337, 8.320970),
epsilon = 1e-6
);
assert_ulps_eq!(
p[1][0],
Gaussian::from_ms(22.079819, 8.180607),
epsilon = 1e-6
);
assert_ulps_eq!(
p[1][1],
Gaussian::from_ms(14.987953, 6.308469),
epsilon = 1e-6
);
let w = [vec![1.0, 1.0], vec![1.0]];
let g = Game::ranked_with_arena(
vec![
t_a.clone(),
vec![R::new(
Gaussian::from_ms(25.0, 25.0 / 3.0),
25.0 / 6.0,
ConstantDrift(0.0),
)],
],
&[1.0, 0.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let post_2vs1 = g.posteriors();
let w_a = vec![1.0, 1.0];
let w_b = vec![1.0, 0.0];
let w = [w_a, w_b];
let g = Game::ranked_with_arena(
vec![t_a, t_b.clone()],
&[1.0, 0.0],
&w,
0.0,
crate::ConvergenceOptions::default(),
&mut ScratchArena::new(),
);
let p = g.posteriors();
assert_ulps_eq!(p[0][0], post_2vs1[0][0], epsilon = 1e-6);
assert_ulps_eq!(p[0][1], post_2vs1[0][1], epsilon = 1e-6);
assert_ulps_eq!(p[1][0], post_2vs1[1][0], epsilon = 1e-6);
assert_ulps_eq!(p[1][1], t_b[1].prior, epsilon = 1e-6);
}
#[test]
fn run_chain_honours_max_iter_in_convergence_options() {
let players: Vec<R> = (0..4).map(|_| R::default()).collect();
let teams: Vec<Vec<_>> = players.iter().map(|p| vec![*p]).collect();
let result = vec![3.0, 2.0, 1.0, 0.0];
let weights = vec![vec![1.0]; 4];
// Capped at 1 iteration: cannot fully propagate down a 4-team chain.
let mut arena = ScratchArena::new();
let g_capped = Game::ranked_with_arena(
teams.clone(),
&result,
&weights,
0.0,
crate::ConvergenceOptions {
max_iter: 1,
..crate::ConvergenceOptions::default()
},
&mut arena,
);
let posteriors_capped = g_capped.posteriors();
// Same inputs, plenty of iterations: fully converged.
let mut arena = ScratchArena::new();
let g_full = Game::ranked_with_arena(
teams,
&result,
&weights,
0.0,
crate::ConvergenceOptions::default(),
&mut arena,
);
let posteriors_full = g_full.posteriors();
// The two posteriors should differ — capped did not converge.
let mut max_diff: f64 = 0.0;
for (team_capped, team_full) in posteriors_capped.iter().zip(posteriors_full.iter()) {
for (g_capped, g_full) in team_capped.iter().zip(team_full.iter()) {
max_diff = max_diff.max((g_capped.mu() - g_full.mu()).abs());
max_diff = max_diff.max((g_capped.sigma() - g_full.sigma()).abs());
}
}
assert!(
max_diff > 1e-6,
"max_iter=1 should differ from full convergence; max_diff={max_diff}"
);
}
#[test]
fn run_chain_with_damping_converges_to_same_posterior() {
let players: Vec<R> = (0..4).map(|_| R::default()).collect();
let teams: Vec<Vec<_>> = players.iter().map(|p| vec![*p]).collect();
let result = vec![3.0, 2.0, 1.0, 0.0];
let weights = vec![vec![1.0]; 4];
let mut arena = ScratchArena::new();
let g_undamped = Game::ranked_with_arena(
teams.clone(),
&result,
&weights,
0.0,
crate::ConvergenceOptions::default(),
&mut arena,
);
let posteriors_undamped = g_undamped.posteriors();
// alpha=0.5 with extra iterations: should reach the same fixed point.
let mut arena = ScratchArena::new();
let g_damped = Game::ranked_with_arena(
teams,
&result,
&weights,
0.0,
crate::ConvergenceOptions {
alpha: 0.5,
max_iter: 100,
..crate::ConvergenceOptions::default()
},
&mut arena,
);
let posteriors_damped = g_damped.posteriors();
let mut max_diff: f64 = 0.0;
for (team_u, team_d) in posteriors_undamped.iter().zip(posteriors_damped.iter()) {
for (g_u, g_d) in team_u.iter().zip(team_d.iter()) {
max_diff = max_diff.max((g_u.mu() - g_d.mu()).abs());
max_diff = max_diff.max((g_u.sigma() - g_d.sigma()).abs());
}
}
assert!(
max_diff < 1e-4,
"α=0.5 should reach the same fixed point as α=1.0; max_diff={max_diff}"
);
}
}