docs: consolidate v0 benchmark results

README.md

@@ -23,24 +23,15 @@ It is LateOn (~149M parameters) fine-tuned on 512k real decisions covering three
 **Why this architecture.** The situation (state + question) is encoded once into token vectors and reused for every candidate set, while each option is encoded independently. That gives two properties classifier heads don't have: caching the situation across decisions, and outputs that don't depend on option order (verified exactly permutation-equivariant).
 
 - **Base model:** [`lightonai/LateOn`](https://huggingface.co/lightonai/LateOn)
-- **Training data:** [`tasksource/tasksource-jev-typed-decisions`](https://huggingface.co/datasets/tasksource/tasksource-jev-typed-decisions) (pinned revision `071f0cf2`), 512k-decision stream, natural mix of the three judgment types, 519 tasks
+- **Training data:** [`tasksource/tasksource-jev-typed-decisions`](https://huggingface.co/datasets/tasksource/tasksource-jev-typed-decisions) (pinned revision [`071f0cf2201f06b2dea3e55323aa3e264284e139`](https://huggingface.co/datasets/tasksource/tasksource-jev-typed-decisions/tree/071f0cf2201f06b2dea3e55323aa3e264284e139)), 512k-decision stream, natural mix of the three judgment types, 519 tasks
 - **Checkpoint selection:** Tasksource unseen tasks only (step 4000 of 8000)
 - **Training code:** `decision-models` repo (`scripts/train_multivector.py`, canonical run)
 
-## How it scores
+## Evaluation
 
-| Benchmark (1k examples each, same samples for every model) | v0 |
-|---|---|
-| Tasksource, unseen tasks (all three judgment types) | 46.8% |
-| Tasksource, unseen test tasks (all three judgment types) | 49.7% |
-| Typed Decisions | 42.6% |
-| AG News | 73.8% |
-| Emotion | 49.0% |
-| Banking77 (77 options) | 44.7% |
-| Fast Decisions (2,900 cases, 17 domains) | 41.3% exact match |
-| classifier-benchmark v2 (866 cases) | 57.5 micro / 57.2 macro |
+On Tasksource's held-out tasks across all three judgment types, v0 scores **46.8%** on unseen-dev and **49.7%** on unseen-test (1k examples each). It reaches **41.3% exact match** on Fast Decisions (2,900 cases across 17 domains). The table compares models on the same 1k examples per public dataset; classifier-benchmark v2 has 866 cases.
 
-## Compact peers (all under 200M, same 1k samples)
+### Compact peers (all under 200M)
 
 | Model | Size | AG News | Emotion | Banking77 | Typed | cb-v2 micro |
 |---|---|---|---|---|---|---|
@@ -51,6 +42,8 @@ It is LateOn (~149M parameters) fine-tuned on 512k real decisions covering three
 | GLiNER2.5 Small | 74M | 70.4 | 54.2 | 66.5 | 34.0 | 53.5 |
 | GLiClass Edge v3 | 33M | 65.5 | 50.1 | 23.2 | 40.0 | 35.3 |
 
+v0's classifier-benchmark v2 macro accuracy is **57.2%**.
+
 Larger peers (GLiClass Modern-Large 399M, GLiNER2.5-Multi 287M, Laya-Multilingual 322M) are omitted from this table; Laya's 90.0 AG News is training overlap (AG News is in its training mix). v0 trades some raw high-cardinality accuracy for state caching and order-independence, which none of the classifier heads offer.
 
 ## Use it (only public packages)