restore winning v8 config on main; README: final-day results (v11-v13 all negative)

README.md

@@ -101,8 +101,13 @@ Environment knobs (all optional, defaults match the platform):
 | 2 | greedy-anchored voting (vote no longer fires) | **0.0712** | 0.2029 | 0.0250 |
 | 3 | + "capitalise English answers" style rule | 0.0679 | 0.2117 | 0.0218 |
 | 4 | + mirror-gloss-style, answer normalisation, equation hints | 0.0000 | 0.1527 | 0.0000 |
-| 5 | revert to 2, plus the match_letters assignment solver | | | |
-| 6 | + `repetition_penalty=1.0` (the model ships 1.05) | | | |
+| 5 | revert to 2, plus the match_letters assignment solver | 0.0712 | 0.2029 | 0.0250 |
+| 6 | + `repetition_penalty=1.0` (the model ships 1.05) | 0.0830 | 0.2067 | 0.0333 |
+| 8 (v8) | **baseline replication + `repetition_penalty=1.0`** | **0.2245** | 0.3150 | 0.1600 |
+| 10 (v10) | v8 but batch=4 (left-padded batching) | 0.1940 | 0.2818 | 0.1336 |
+| 11 (v11) | v8 + beam search `num_beams=4` on the answer pass | 0.1964 | 0.2888 | 0.1336 |
+| 12 (v12) | v8 + assignment solver for `match_letters` only | 0.1624 | 0.2526 | 0.1044 |
+| 13 (v13) | v8 + a one-shot worked exemplar as chat turns | 0.0920 | 0.2259 | 0.0375 |
 
 Every layer of prompt/post-processing cleverness measurably *hurt*. Submission 5
 therefore reverts to the configuration of submission 2 and adds exactly one
@@ -158,3 +163,26 @@ style rules, output normalisation, forcing exactly N answers — reduced exact
 match. Submissions 2 -> 3 -> 4 fell 0.0712 -> 0.0679 -> 0.0000 as more
 engineering went in. The winning move was deleting all of it and fixing one
 decoding flag.
+
+## Final-day probes (all negative, all single changes on v8)
+
+Three orthogonal, individually-motivated improvements were each tested as a
+minimal diff on the frozen v8 script, one variable at a time:
+
+* **v11 — beam search** (`num_beams=4`, batch 1, greedy fallback on OOM/low
+  budget): 0.2245 → 0.1964. Exact match fell to 0.1336 — the same value as
+  left-padded batch=4 — suggesting a shared fp16-numerics mechanism in
+  multi-sequence forward passes rather than anything about search.
+* **v12 — assignment solver for `match_letters`**: 0.2245 → 0.1624, and
+  explanation coverage fell to 50% from the solver's extra forward passes.
+  The hidden set evidently does not reward bare option letters where
+  free-form text had been earning chrF credit.
+* **v13 — one-shot worked exemplar** (a public-Linguini Kayapo problem as a
+  genuine user→assistant exchange): 0.2245 → 0.0920. The demonstration
+  derailed the model far more than any instruction-style prompt addition.
+
+With those, every direction adjacent to v8 has been measured: chain-of-thought,
+answer-style rules, output normalisation, N-forcing, batching, beam search,
+constrained decoding, few-shot. All reduced the score. The shipped
+configuration — the organizers' minimal structure plus `repetition_penalty=1.0`
+— is a sharp local optimum, and `script.py` on `main` is exactly that config.