{
 "system": "p4v2_dense_s4",
 "split": "test_iid",
 "checkpoint": "experiments/runs/p4v2_dense_seed04_20261030001749/checkpoint",
 "checkpoint_sha256": "8424e19c8ff4bb15b787bd768057d3ac75224146817e6e20636f1f54ae3ee22c",
 "config_sha256": "f317af9aa8d9a9e64b5a4ce3651617abc670de771726b901de118029352af723",
 "code_commit": "unknown",
 "device": "mps",
 "precision": "fp32",
 "evaluated_at": "2026-10-30T04:06:34-0400",
 "data_sha256": "06620e1cf60b7250aac71f4fb5ee74e3705f4b9aab102e22b5c5bdbed76c4ae2",
 "exact_match": {
  "budget0": {
   "accuracy": 0.368,
   "n": 1000,
   "by_family": {
    "bind": 0.2119815668202765,
    "fsm": 0.4358974358974359,
    "arith": 0.06701030927835051,
    "excl": 0.3348623853211009,
    "sched": 0.7813953488372093
   },
   "edits_per_token": 0.0
  },
  "forced_b2": {
   "accuracy": 0.377,
   "n": 1000,
   "by_family": {
    "bind": 0.22119815668202766,
    "fsm": 0.48717948717948717,
    "arith": 0.061855670103092786,
    "excl": 0.3440366972477064,
    "sched": 0.772093023255814
   },
   "edits_per_token": 2.0
  }
 },
 "seconds": 11.4
}