{ "arm": "binary_cond", "spec": { "drop": [], "max_tokens": 32, "completion": "binary", "rows": "silver", "labels": "relabel", "kind": "train", "prompt": "binary_cond", "task": "binary", "replaces": "NONE: detection-only diagnostic", "question": "Exp 4 control: binary probe with the conditional 'If this becomes an incident' wording." }, "inputs": { "human_test": "bf144282b08cd5bc9b5281c73506e91a21ccd3fa63134cc34c6f74cd5e667050", "silver_test": "51f08374972f3064881ee1de419d2be5629ef7b3c6a85b6f61632896d4ff9ea2", "human_train": "d8972298c00123b00dff9c876c783ce67d2788ab0e02fc59d4d876f6a6310b1b", "silver_train": "b2ba4d8d270c1dc37e3502f5ec136ac4ded72bb60826ee2f0d9bbaf895f3a0e9" }, "eval_rows": { "human_test": 435, "silver_test": 2675, "probes": 20 }, "train": { "rows": 8389, "sha256": "457a043a43005212d285fc38881c2820379e7f9100bd2a8fa6c1ce34f6fef123", "stats": { "dropped_by_source": 0 }, "by_source": { "aiid": 724, "cisa_aa": 65, "atlas": 46, "oecd": 6083, "cisa_kev": 1464, "flagship": 7 }, "by_label": { "Discrimination and Toxicity": 160, "No incident (potential only)": 6593, "AI system safety, failures, and limitations": 449, "Privacy & Security": 275, "Misinformation": 162, "Socioeconomic & Environmental Harms": 91, "Human-Computer Interaction": 66, "Malicious Actors & Misuse": 593 }, "share_no_incident": 0.7859 } }