{
 "system": "p4v2_gr_s1",
 "split": "test_iid",
 "checkpoint": "experiments/runs/p4v2_gr_seed01_20261030001749/checkpoint",
 "checkpoint_sha256": "597a91e3beb1daea126d7c5b2ecd2bac327eb323b55cebe57a153e1f27b95f80",
 "config_sha256": "0b796604197779959d0bcdc2c38bdf81a3d839c7f9ecbd53dd757def310268bc",
 "code_commit": "unknown",
 "device": "mps",
 "precision": "fp32",
 "evaluated_at": "2026-10-30T04:06:03-0400",
 "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": 0.38,
   "n": 1000,
   "by_family": {
    "bind": 0.2119815668202765,
    "fsm": 0.4807692307692308,
    "arith": 0.09278350515463918,
    "excl": 0.3211009174311927,
    "sched": 0.7953488372093023
   },
   "edits_per_token": 2.0
  }
 },
 "seconds": 20.6
}