Files
trueskill-tt/tests/scored.rs
Anders Olsson 8b53cacd64 T4 (MarginFactor): scored outcomes via Gaussian-margin EP evidence
Adds soft Gaussian-observation evidence on the per-pair diff variable,
enabling continuous score margins as a richer alternative to ranks.

Public API:
- `Outcome::Scored([scores])` (non-breaking enum extension under
  `#[non_exhaustive]`).
- `Game::scored(teams, outcome, options)` constructor parallel to
  `Game::ranked`.
- `EventBuilder::scores([...])` fluent helper.
- `HistoryBuilder::score_sigma(σ)` knob (default 1.0, validated > 0).
- `GameOptions::score_sigma`.
- `EventKind` re-exported from `lib.rs` (annotated `#[non_exhaustive]`).
- New `InferenceError::InvalidParameter { name, value }` variant.

Internals:
- `MarginFactor` (`factor/margin.rs`): Gaussian observation factor that
  closes in one EP step; cavity-cached log-evidence mirrors `TruncFactor`.
- `BuiltinFactor::Margin` dispatch arm.
- `DiffFactor` enum in `game.rs` lets `Game::likelihoods` and the new
  `likelihoods_scored` share the per-pair link abstraction.
- Per-event `EventKind { Ranked, Scored { score_sigma } }` routed through
  `TimeSlice::add_events`, `iteration_direct`, and `log_evidence`.

Tests: 88 lib + 27 integration (4 new in `tests/scored.rs`); existing
goldens byte-identical.  Bench: `benches/scored.rs` baseline ~960µs for
60 events × 20-player pool with default convergence.

Plan: docs/superpowers/plans/2026-04-27-t4-margin-factor.md
Spec item marked Done.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-27 08:47:36 +02:00

140 lines
3.9 KiB
Rust

//! Integration tests for `Outcome::Scored` routing through `History::add_events`.
use smallvec::smallvec;
use trueskill_tt::{ConstantDrift, Event, History, Member, Outcome, Team};
#[test]
fn scored_two_team_one_event_pulls_winner_up() {
let mut h: History = History::builder()
.mu(0.0)
.sigma(2.0)
.beta(1.0)
.drift(ConstantDrift(0.0))
.score_sigma(1.0)
.build();
let events: Vec<Event<i64, &'static str>> = vec![Event {
time: 1,
teams: smallvec![
Team::with_members([Member::new("a")]),
Team::with_members([Member::new("b")]),
],
outcome: Outcome::scores([10.0, 4.0]),
}];
h.add_events(events).unwrap();
let mu_a = h.current_skill(&"a").unwrap().mu();
let mu_b = h.current_skill(&"b").unwrap().mu();
assert!(
mu_a > 0.0,
"winner mu should be pulled up; got mu_a = {mu_a}"
);
assert!(
mu_b < 0.0,
"loser mu should be pulled down; got mu_b = {mu_b}"
);
assert!(
mu_a > mu_b,
"winner mu should exceed loser mu; got mu_a = {mu_a}, mu_b = {mu_b}"
);
}
#[test]
fn scored_zero_margin_treats_as_tie() {
let mut h: History = History::builder()
.mu(0.0)
.sigma(2.0)
.beta(1.0)
.drift(ConstantDrift(0.0))
.score_sigma(1.0)
.build();
let events: Vec<Event<i64, &'static str>> = vec![Event {
time: 1,
teams: smallvec![
Team::with_members([Member::new("a")]),
Team::with_members([Member::new("b")]),
],
outcome: Outcome::scores([5.0, 5.0]),
}];
h.add_events(events).unwrap();
let mu_a = h.current_skill(&"a").unwrap().mu();
let mu_b = h.current_skill(&"b").unwrap().mu();
let sigma_a = h.current_skill(&"a").unwrap().sigma();
// Equal scores: posterior means stay symmetric around the prior mean.
assert!(
(mu_a - mu_b).abs() < 1e-9,
"equal scores should leave mu_a == mu_b; got {mu_a} vs {mu_b}"
);
assert!(
mu_a.abs() < 1e-9,
"equal scores against equal priors should leave mu near zero; got {mu_a}"
);
// A zero-margin scored event still reduces uncertainty.
assert!(
sigma_a < 2.0,
"expected sigma to tighten below prior 2.0; got {}",
sigma_a
);
}
#[test]
fn scored_three_team_partial_order() {
let mut h: History = History::builder()
.mu(0.0)
.sigma(2.0)
.beta(1.0)
.drift(ConstantDrift(0.0))
.score_sigma(1.0)
.build();
let events: Vec<Event<i64, &'static str>> = vec![Event {
time: 1,
teams: smallvec![
Team::with_members([Member::new("a")]),
Team::with_members([Member::new("b")]),
Team::with_members([Member::new("c")]),
],
outcome: Outcome::scores([9.0, 5.0, 1.0]),
}];
h.add_events(events).unwrap();
let mu_a = h.current_skill(&"a").unwrap().mu();
let mu_b = h.current_skill(&"b").unwrap().mu();
let mu_c = h.current_skill(&"c").unwrap().mu();
assert!(
mu_a > mu_b,
"team with highest score should rank highest; mu_a = {mu_a}, mu_b = {mu_b}"
);
assert!(
mu_b > mu_c,
"middle score should outrank lowest; mu_b = {mu_b}, mu_c = {mu_c}"
);
}
#[test]
fn scored_rejects_outcome_team_count_mismatch() {
use trueskill_tt::InferenceError;
let mut h: History = History::builder().build();
let events: Vec<Event<i64, &'static str>> = vec![Event {
time: 1,
teams: smallvec![
Team::with_members([Member::new("a")]),
Team::with_members([Member::new("b")]),
],
outcome: Outcome::scores([10.0, 4.0, 1.0]), // 3 scores, 2 teams
}];
let err = h.add_events(events).unwrap_err();
assert!(
matches!(err, InferenceError::MismatchedShape { .. }),
"expected MismatchedShape error, got {err:?}"
);
}