Update TwIL-LM3: weights, tokenizer and model card

README.md

@@ -70,9 +70,27 @@ yet reported for it.
 for the Δ table above, hence 0.3466 against 0.3356 — run-to-run variation of the same
 checkpoint. The paired run is the correct basis for the improvement claim.
 
-`strict-7` is the mean of seven lanes scored under strict metrics only (`fol_translation`,
+The three summary rows aggregate the objective lanes in different ways. None of them include the
+perplexity lanes or the token-F1 scorings, which are not on a common 0–1 accuracy scale.
+
+**`macro gate`** is the headline metric and the one the training pipeline gates on. It is the
+equal-weight mean of five objectives: the four bounded classification lanes (`entailment_label`,
+`mcq_answer`, `procedural`, `lean_critic`) plus `rule_induction`, scored by its continuous
+derivation score. Rule induction is included specifically so a fine-tune cannot pass the gate
+while quietly regressing inductive reasoning. In the gate, `mcq_answer` and `procedural` are
+credited as `max(exact_match, loose_match)`: for free-text answer lanes, a response that is
+correct but differently formatted is a formatting artefact rather than a reasoning failure. This
+affects the aggregate only — the per-lane rows above stay strict.
+
+**`macro_primary`** is the same mean over the four classification lanes alone, without
+`rule_induction`. It is the narrower "bounded classification" view, kept for comparability with
+earlier reports; the gate is the metric to read for overall in-domain capability.
+
+**`strict-7`** is the mean of seven lanes scored under strict metrics only (`fol_translation`,
 `entailment_label`, `mcq_answer`, `semantic_parse` and `lean_formalize` exact match,
-`lean_critic` and `procedural` accuracy), with no loose-match credit anywhere.
+`lean_critic` and `procedural` accuracy), with no loose-match credit anywhere. It is deliberately
+harsh — exact match on generative lanes is near zero for every arm — so it is useful for ranking
+models against each other but not as an absolute capability measure.
 
 Among the released models, TwIL-LM3 leads both headline metrics and wins every lane the pipeline
 targets directly: `lean_formalize` token-F1 0.5869 against 0.4655 for the nearest arm,
@@ -91,7 +109,7 @@ better.
 
 It is also the most efficient arm in the table by a wide margin — 28.1 answers/sec, from
 generations averaging 564 tokens where every other arm except Llama runs past 690. The Liquid
-models decode faster in raw tokens per second, 25000 and 22000 against 15880, but their length
+models decode faster in raw tokens per second, 25230 and 22480 against 15880, but their length
 more than cancels it.
 
 #### Track B — held-out benchmarks