feat!: Game is the type you get, and one_v_one returns one

`lib.rs` advertised `Game` in "Core types" as "one match in isolation".
It had no public constructor: every `Game::*` returned `OwnedGame`, so
`let g: Game = Game::ranked(..)?` did not compile.

Names swapped. The public type is the owned one — `Game<T, D>`, no
lifetime — and the borrowing form is `pub(crate) GameRef<'a, T, D>`,
which is what it always was: an implementation detail about whether the
result and weight slices are borrowed from `History`'s storage. That
distinction meant nothing to someone scoring one match, and it showed
the module's surface twice in rustdoc, since both types carried
`posteriors()` / `log_evidence()`.

`one_v_one` returned `(Gaussian, Gaussian)` while every sibling returned
a game, making it the one constructor you could not ask for
`log_evidence()`. It returns `Self` now; `.posteriors()` recovers the old
shape, and the test that covers it now also asserts the evidence of two
identical ratings is exactly `ln(0.5)`.

`ranked`, `scored` and `free_for_all` had `# Errors` as their entire
doc, so rustdoc's index rendered the error list as the summary. They
have summary lines, and `Game` has a worked example — it was advertised
as a core type with none anywhere in the crate.

Closes #69.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011hcFjNDmHXZF8URGLku5zZ

src/lib.rs

@@ -154,7 +154,7 @@ pub use drift::{ConstantDrift, Drift};
 pub use error::{InferenceError, UnknownKeys};
 pub use event::{Event, Member, Team};
 pub use event_builder::EventBuilder;
-pub use game::{Game, GameOptions, OwnedGame};
+pub use game::{Game, GameOptions};
 pub use gaussian::Gaussian;
 pub use history::{History, HistoryBuilder, Joint};
 use matrix::Matrix;