feat: add UnknownKeys::Prior, and explain why there is no Skip

#44's third ask was an opt-in mode so a caller with partially-known
teams need not pre-filter. The requested shape was `Skip` — drop unknown
members. Measured, that is the wrong mode to build.

A team's performance is the *sum* of its members, so dropping one drops
its variance too. On a two-member team with one unknown:

    SKIP  (drop the member)  : performance sigma 2.37
    PRIOR (member at prior)  : performance sigma 6.53   (2.76x wider)

Skipping makes the model *more* certain because it knows *less*, which
is backwards. `Prior` is also the answer the model already gives for a
competitor it knows about but has no evidence for — measured, such a
competitor sits at sigma 4.99 against the prior's 6.0 — so it
corresponds to a state the model can actually be in. Skipping does not.

So the enum is `Reject` (default, unchanged) and `Prior`, and it is
`#[non_exhaustive]` in case a real use for skipping turns up later.

Placed on `HistoryBuilder` rather than per-call. Neither consumer wants
it to vary between queries: one scores thousands of candidate matchups
in a loop, the other's headline feature is predicting a competitor
nobody has faced. That makes it a property of how the model is being
used, and keeps five prediction signatures unchanged.

This also gives #48 the semantics it asked for — "I have never seen this
competitor, here is the prior-informed answer" — which it needs for
predicting a course nobody has played.

`an_unknown_member_widens_its_team_rather_than_narrowing_it` pins the
property that ruled `Skip` out, so a future convenience cannot quietly
reintroduce it.

Closes #44. Refs #48

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011hcFjNDmHXZF8URGLku5zZ
This commit is contained in:
2026-09-08 01:28:49 +02:00
co-authored by Claude Opus 5
parent 2cf21a753d
commit 71554fd944
5 changed files with 177 additions and 14 deletions
+19 -4
View File
@@ -195,10 +195,25 @@ stay available at any size:
quadratic in team count.
- `predict_ranking(teams, ranks)` — one specific finishing order.
Unknown keys are an error, not a silent omission: a team the history has never
seen cannot produce a confident-looking probability. The error names the key, and
every key must already be known — pre-filter with `lookup` or `current_skill` if
your caller cannot guarantee that.
Unknown keys are an error by default, not a silent omission: a team the history
has never seen cannot produce a confident-looking probability. The error names
the key, and every key must already be known — pre-filter with `lookup` or
`current_skill` if your caller cannot guarantee that.
If predicting for competitors you have never seen is the point rather than a
mistake, say so once:
```rust
use trueskill_tt::{History, UnknownKeys};
let h = History::builder().unknown_keys(UnknownKeys::Prior).build();
```
An unknown competitor is then answered from the configured prior, which is the
honest reading — you have no evidence about them — and correctly *widens* a team
that contains one. There is deliberately no "skip the member" mode: a team's
performance is the sum of its members, so dropping one would make the model more
certain because it knows less.
### Asking about one competitor
+39
View File
@@ -1,5 +1,44 @@
use std::fmt;
/// How a prediction should treat a key the history has never seen.
///
/// Configured once per history via
/// [`HistoryBuilder::unknown_keys`](crate::HistoryBuilder::unknown_keys).
/// Neither known consumer wants this to vary between queries — one predicts
/// thousands of candidate matchups in a loop, the other's headline feature is
/// predicting a competitor nobody has faced — so it is a property of how you
/// intend to use the model rather than an argument on five call sites.
///
/// # There is deliberately no `Skip`
///
/// Dropping an unknown member is the obvious third option and it is wrong. A
/// team's performance is the *sum* of its members, so removing one removes its
/// variance too: measured on a two-member team with one unknown, skipping gives
/// a performance sigma of 2.37 where treating the member as unknown gives 6.53.
/// An unknown competitor would make the model *more* certain, which is
/// backwards. `Prior` is also the answer the model already gives for a
/// competitor it knows about but has no evidence for, so it corresponds to a
/// state the model can actually be in; skipping does not.
#[derive(Clone, Copy, Debug, Default, PartialEq, Eq)]
#[non_exhaustive]
pub enum UnknownKeys {
/// Reject the prediction with [`InferenceError::UnknownKey`].
///
/// The default, and the right one when every key is expected to be known:
/// a team of strangers should not silently produce a confident-looking
/// answer.
#[default]
Reject,
/// Treat an unknown competitor as one sitting at the history's configured
/// prior.
///
/// This is the honest Bayesian reading — a competitor you have never
/// observed is exactly the prior — and it makes "predict a matchup
/// involving someone new" a first-class question rather than something a
/// caller fakes with a neutral constant.
Prior,
}
#[derive(Debug, Clone, PartialEq)]
#[non_exhaustive]
pub enum InferenceError {
+40 -9
View File
@@ -33,6 +33,7 @@ pub struct HistoryBuilder<
score_sigma: f64,
convergence: ConvergenceOptions,
observer: O,
unknown_keys: crate::UnknownKeys,
_time: PhantomData<T>,
_key: PhantomData<K>,
}
@@ -63,6 +64,7 @@ impl<T: Time, D: Drift<T>, O: Observer<T>, K: Eq + Hash + Clone> HistoryBuilder<
score_sigma: self.score_sigma,
convergence: self.convergence,
observer: self.observer,
unknown_keys: self.unknown_keys,
_time: self._time,
_key: self._key,
}
@@ -100,6 +102,20 @@ impl<T: Time, D: Drift<T>, O: Observer<T>, K: Eq + Hash + Clone> HistoryBuilder<
self
}
/// How predictions treat a key the history has never seen.
///
/// Defaults to [`UnknownKeys::Reject`](crate::UnknownKeys::Reject), which
/// errors. Set [`UnknownKeys::Prior`](crate::UnknownKeys::Prior) to have an
/// unknown competitor answered from the configured prior instead, which
/// makes "predict a matchup involving someone new" a first-class question.
///
/// This affects predictions only. Ingestion always creates a competitor for
/// a key it has not seen, because that is what an event *is*.
pub fn unknown_keys(mut self, unknown_keys: crate::UnknownKeys) -> Self {
self.unknown_keys = unknown_keys;
self
}
/// Convergence tolerance, iteration cap, and EP damping.
///
/// # Panics
@@ -132,6 +148,7 @@ impl<T: Time, D: Drift<T>, O: Observer<T>, K: Eq + Hash + Clone> HistoryBuilder<
score_sigma: self.score_sigma,
convergence: self.convergence,
observer,
unknown_keys: self.unknown_keys,
_time: self._time,
_key: self._key,
}
@@ -151,6 +168,7 @@ impl<T: Time, D: Drift<T>, O: Observer<T>, K: Eq + Hash + Clone> HistoryBuilder<
score_sigma: self.score_sigma,
convergence: self.convergence,
observer: self.observer,
unknown_keys: self.unknown_keys,
}
}
}
@@ -166,6 +184,7 @@ impl Default for HistoryBuilder<i64, ConstantDrift, NullObserver, &'static str>
score_sigma: 1.0,
convergence: ConvergenceOptions::default(),
observer: NullObserver,
unknown_keys: crate::UnknownKeys::default(),
_time: PhantomData,
_key: PhantomData,
}
@@ -233,6 +252,7 @@ pub struct History<
score_sigma: f64,
convergence: ConvergenceOptions,
observer: O,
unknown_keys: crate::UnknownKeys,
}
impl Default for History<i64, ConstantDrift, NullObserver, &'static str> {
@@ -261,6 +281,7 @@ impl<K: Eq + Hash + Clone> History<i64, ConstantDrift, NullObserver, K> {
score_sigma: 1.0,
convergence: ConvergenceOptions::default(),
observer: NullObserver,
unknown_keys: crate::UnknownKeys::default(),
_time: PhantomData,
_key: PhantomData,
}
@@ -626,19 +647,29 @@ impl<T: Time, D: Drift<T>, O: Observer<T>, K: Eq + Hash + Clone> History<T, D, O
let mut members = Vec::with_capacity(team.len());
for (member_idx, key) in team.iter().enumerate() {
let unknown = InferenceError::UnknownKey {
team: team_idx,
member: member_idx,
key: format!("{key:?}"),
};
let index = self.keys.get(*key).ok_or(unknown.clone())?;
members.push(
// A key can be missing two ways — never interned, or interned
// with no recorded skill — and both mean the same thing to a
// caller, so they take the same branch.
let skill = self.keys.get(*key).and_then(|index| {
self.time_slices
.iter()
.rev()
.find_map(|ts| ts.skills.get(index).map(|s| s.posterior()))
.ok_or(unknown)?,
);
});
members.push(match skill {
Some(skill) => skill,
None => match self.unknown_keys {
crate::UnknownKeys::Prior => Gaussian::from_ms(self.mu, self.sigma),
_ => {
return Err(InferenceError::UnknownKey {
team: team_idx,
member: member_idx,
key: format!("{key:?}"),
});
}
},
});
}
gathered.push(members);
+1 -1
View File
@@ -137,7 +137,7 @@ pub use acquisition::expected_information_gain;
pub use competitor::Competitor;
pub use convergence::{ConvergenceOptions, ConvergenceReport};
pub use drift::{ConstantDrift, Drift};
pub use error::InferenceError;
pub use error::{InferenceError, UnknownKeys};
pub use event::{Event, Member, Team};
pub use event_builder::EventBuilder;
pub use game::{Game, GameOptions, OwnedGame};
+78
View File
@@ -337,3 +337,81 @@ fn unknown_key_names_the_key_it_could_not_find() {
"Display should say what to do about it: {rendered}"
);
}
// ---------------------------------------------------------------------------
// UnknownKeys policy
// ---------------------------------------------------------------------------
fn history_with_policy(names: &[&'static str], policy: trueskill_tt::UnknownKeys) -> History {
let mut h = History::builder().unknown_keys(policy).build();
for pair in names.windows(2) {
h.record_winner(&pair[0], &pair[1], 1).unwrap();
}
let _ = h.converge().unwrap();
h
}
#[test]
fn reject_is_the_default() {
let h = history_with(&["a", "b"], 0.0);
assert!(matches!(
h.predict_outcome(&[&[&"a"], &[&"ghost"]]),
Err(InferenceError::UnknownKey { .. })
));
}
#[test]
fn prior_answers_instead_of_erroring() {
let h = history_with_policy(&["a", "b"], trueskill_tt::UnknownKeys::Prior);
let p = h
.predict_outcome(&[&[&"a"], &[&"ghost"]])
.expect("Prior should answer rather than reject");
assert!((p.total() - 1.0).abs() < 1e-6);
}
/// Two competitors the model has never seen are genuinely a coin flip. The
/// point is that this is now *derived* rather than a constant a caller
/// substitutes after swallowing an error.
#[test]
fn two_unknown_competitors_are_an_honest_coin_flip() {
let h = history_with_policy(&["a", "b"], trueskill_tt::UnknownKeys::Prior);
let wins = h
.predict_win_probabilities(&[&[&"nobody"], &[&"no_one"]])
.unwrap();
assert!((wins[0] - 0.5).abs() < 1e-9, "{wins:?}");
assert!((wins[1] - 0.5).abs() < 1e-9, "{wins:?}");
}
/// The property that rules out a `Skip` mode: an unknown member must make a
/// team *less* certain, never more. Skipping would drop the member's variance
/// from the sum and narrow the team, which is backwards.
#[test]
fn an_unknown_member_widens_its_team_rather_than_narrowing_it() {
let h = history_with_policy(&["a", "b", "c"], trueskill_tt::UnknownKeys::Prior);
// "a" alone against "b" — then "a" plus an unknown partner against "b".
let solo = h.predict_win_probabilities(&[&[&"a"], &[&"b"]]).unwrap();
let with_unknown = h
.predict_win_probabilities(&[&[&"a", &"stranger"], &[&"b"]])
.unwrap();
// Adding an unknown partner pulls the outcome toward even, because the
// team's performance spread grew.
assert!(
(with_unknown[0] - 0.5).abs() < (solo[0] - 0.5).abs(),
"an unknown partner should make the result less certain: solo {solo:?}, \
with unknown {with_unknown:?}"
);
}
#[test]
fn prior_reaches_every_prediction_entry_point() {
let h = history_with_policy(&["a", "b"], trueskill_tt::UnknownKeys::Prior);
let teams: &[&[&&str]] = &[&[&"a"], &[&"ghost"]];
assert!(h.predict_quality(teams).is_ok());
assert!(h.predict_win_probabilities(teams).is_ok());
assert!(h.predict_outcome(teams).is_ok());
assert!(h.predict_ranking(teams, &[0, 1]).is_ok());
assert!(h.expected_information_gain(teams).is_ok());
}