| { |
| "format": "topos-scope-head-1", |
| "kind": "encoder", |
| "labels": [ |
| "activity:read", |
| "ai_conversations:read", |
| "attention:read", |
| "availability:read", |
| "complexity:read", |
| "contacts:resolve", |
| "health:read", |
| "messages:read", |
| "places:read", |
| "public_bio:read", |
| "relationship_context:read", |
| "resources:read", |
| "schedule:read", |
| "work_context:read", |
| "none" |
| ], |
| "base_model": "distilbert-base-uncased", |
| "embedding_model": "", |
| "tau_high": 0.7, |
| "tau_low": 0.5499999999999999, |
| "max_length": 64, |
| "corpus_manifest": { |
| "corpora": [ |
| { |
| "source": "schema-grounded (G3)", |
| "licence": "internal", |
| "url": "-", |
| "rows": 2767, |
| "note": "the only source for the nine uncovered scopes; `train` split only (2767 of 5987) \u2014 the rest belongs to the benchmark" |
| }, |
| { |
| "source": "compound positives (B1)", |
| "licence": "internal", |
| "url": "-", |
| "rows": 2545, |
| "note": "multi-scope conjunctions of train-split parents at 0.92x positives; the corpus was 100% single-label and trained AGAINST co-activation (multi-gold recall 0.165 vs 0.356 single)" |
| }, |
| { |
| "source": "negative twins (G4)", |
| "licence": "internal", |
| "url": "-", |
| "rows": 1660, |
| "note": "third-party + generalize at 0.60x positives (3544 available); teaches 'whose data', which M1 found rung 1 cannot represent" |
| }, |
| { |
| "source": "concept negatives (G4b)", |
| "licence": "internal", |
| "url": "-", |
| "rows": 397, |
| "note": "mechanism + definition frames over the positives' own concept vocabulary; replaces the mined QA band, which yielded 102 usable rows from 119,700 questions and reached only 8 of 14 scopes" |
| }, |
| { |
| "source": "AmazonScience/massive", |
| "licence": "CC BY-4.0", |
| "url": "https://amazon-massive-nlu-dataset.s3.amazonaws.com/amazon-massive-dataset-1.1.tar.gz", |
| "rows": 5200, |
| "note": "en-US only; positives cue-filtered (see POSITIVE_CUES)" |
| }, |
| { |
| "source": "clinc/oos-eval", |
| "licence": "CC BY-3.0", |
| "url": "https://raw.githubusercontent.com/clinc/oos-eval/master/data/data_full.json", |
| "rows": 1200, |
| "note": "all `none`; the OOS split is the near-miss anchor" |
| } |
| ], |
| "total_rows": 13769, |
| "attribution_required": [ |
| "AmazonScience/massive", |
| "clinc/oos-eval" |
| ] |
| }, |
| "metrics": { |
| "n": 1071, |
| "macro_f1": 0.6127984463644067, |
| "exact": 0.5583566760037348, |
| "negatives_abstained": 0.9407114624505929, |
| "scopes_below_floor": [ |
| "ai_conversations:read", |
| "availability:read", |
| "complexity:read", |
| "health:read", |
| "places:read", |
| "relationship_context:read", |
| "resources:read", |
| "work_context:read" |
| ], |
| "recall_single_gold": 0.5021645021645021, |
| "recall_multi_gold": 0.5964912280701754, |
| "multi_gap": -0.09432672590567326, |
| "dead_rate": 0.1491442542787286, |
| "disjoint_rate": 0.2063758389261745, |
| "threshold": 0.7 |
| }, |
| "trained_at": "2026-08-16" |
| } |
|
|
