{
 "system": "p4v2_gr_s4",
 "split": "test_iid",
 "checkpoint": "experiments/runs/p4v2_gr_seed04_20261030001749/checkpoint",
 "checkpoint_sha256": "d5d35da1c2fd5f918d9215edc54c1000100974c54ac4898b788569bfadf53e37",
 "config_sha256": "21232da8236be2d13f77e7722603f974371e9e2140ced5b4db480016a7fb9b62",
 "code_commit": "unknown",
 "device": "mps",
 "precision": "fp32",
 "evaluated_at": "2026-10-30T04:05:56-0400",
 "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": 0.389,
   "n": 1000,
   "by_family": {
    "bind": 0.2350230414746544,
    "fsm": 0.4935897435897436,
    "arith": 0.07216494845360824,
    "excl": 0.3348623853211009,
    "sched": 0.8093023255813954
   },
   "edits_per_token": 2.0
  }
 },
 "seconds": 13.8
}