evalroute-lane-encoder / eval_predictions.jsonl
keppy's picture
lane encoder v1: ModernBERT-small-v2, 9 lanes; eval 19 real rows 63.2%; gonogo: opt-in (tie vs rules+llm); public training rows only
ae0b2f6 verified
Raw History Blame Contribute Delete
2.64 kB
{"id": "6292a60a9a2241e08603b294ae393b3c", "label": "routine-coding", "predicted": "long-doc-reading", "confidence": 0.41951555013656616}
{"id": "72c3a76e6eb04afdba944b8cbd8bf9b0", "label": "routine-coding", "predicted": "long-doc-reading", "confidence": 0.6065808534622192}
{"id": "a9f795fd0bb5419fb634cd98cb9b07b2", "label": "routine-coding", "predicted": "routine-coding", "confidence": 0.7151268124580383}
{"id": "fa85d94d4b0f4f59bb3d334dcc27004d", "label": "dl-ml-research-engineering", "predicted": "routine-coding", "confidence": 0.49763408303260803}
{"id": "1a84b311446b4571969af0f31c7ffd70", "label": "routine-coding", "predicted": "web-research", "confidence": 0.49626997113227844}
{"id": "e025c31944f446de9e69bb969adad8b1", "label": "routine-coding", "predicted": "prose", "confidence": 0.32139402627944946}
{"id": "ece1863753294f4bbbaa36527cc662a5", "label": "routine-coding", "predicted": "prose", "confidence": 0.5279013514518738}
{"id": "e47fca02cf0542eab1b25ef8398b80c5", "label": "routine-coding", "predicted": "hard-agentic-coding", "confidence": 0.800709068775177}
{"id": "540704307436479487184f6b019ee4bd", "label": "routine-coding", "predicted": "routine-coding", "confidence": 0.8717922568321228}
{"id": "taskset:align-interpretability-circuits", "label": "alignment-reasoning", "predicted": "alignment-reasoning", "confidence": 0.953163743019104}
{"id": "taskset:align-shard-theory", "label": "alignment-reasoning", "predicted": "alignment-reasoning", "confidence": 0.866253674030304}
{"id": "taskset:align-emergent-deception", "label": "alignment-reasoning", "predicted": "alignment-reasoning", "confidence": 0.5977520942687988}
{"id": "taskset:dl-grad-accum", "label": "dl-ml-research-engineering", "predicted": "dl-ml-research-engineering", "confidence": 0.9232227802276611}
{"id": "taskset:dl-train-loop-epochs", "label": "dl-ml-research-engineering", "predicted": "dl-ml-research-engineering", "confidence": 0.7878546118736267}
{"id": "taskset:dl-early-stop-patience", "label": "dl-ml-research-engineering", "predicted": "dl-ml-research-engineering", "confidence": 0.9592454433441162}
{"id": "taskset:rc-log-parse", "label": "routine-coding", "predicted": "routine-coding", "confidence": 0.8627690672874451}
{"id": "taskset:rc-csv-group-count", "label": "routine-coding", "predicted": "routine-coding", "confidence": 0.7975051999092102}
{"id": "taskset:rc-backoff-schedule", "label": "routine-coding", "predicted": "routine-coding", "confidence": 0.47848784923553467}
{"id": "taskset:rc-iso-dates", "label": "routine-coding", "predicted": "routine-coding", "confidence": 0.7108357548713684}