{
 "schema": "cain.e104.gates.v1",
 "gates": [
  {
   "gate": "Failure analysis (E102 sealed failures)",
   "status": "PASS",
   "evidence": "35 of 48 failures were key-and-door worlds, 47 of 48 with the mechanics already identified: the bottleneck is hidden-precondition discovery"
  },
  {
   "gate": "Learning from experience (bandit over the trigger)",
   "status": "PARTIAL",
   "evidence": "UCB1 over 160 training episodes chose m = 5 (pulls {'None': 23, '2': 35, '3': 29, '5': 39, '8': 34}); the unpaired training estimate favoured it"
  },
  {
   "gate": "Strict acceptance (validation + confirmation)",
   "status": "PASS",
   "evidence": "the gate REJECTED the learned skill: validation 84 vs 84 of 100 solved (McNemar p = 1); mean steps 25.84 vs 25.17; confirmation 86 vs 87 of 100 solved (McNemar p = 1); mean steps 24.34 vs 23.66. The gate worked: it stopped a skill that does not help"
  },
  {
   "gate": "H1 sealed grid (300)",
   "status": "FAIL",
   "evidence": "256 vs 257 of 300 solved (McNemar p = 1); mean steps 24.133 vs 23.37"
  },
  {
   "gate": "H1b key-and-door (60)",
   "status": "FAIL",
   "evidence": "35 vs 35 of 60 solved (McNemar p = 1); mean steps 50.483 vs 47.1"
  },
  {
   "gate": "H1c no loss on other families (240)",
   "status": "PASS",
   "evidence": "221 vs 222 of 240 solved (McNemar p = 1); mean steps 17.546 vs 17.438"
  },
  {
   "gate": "H2 cross-domain precondition (service lock, 100)",
   "status": "FAIL",
   "evidence": "18 vs 18 of 100 solved (McNemar p = 1); mean steps 56.17 vs 55.87"
  },
  {
   "gate": "Plain service, no loss (100)",
   "status": "FAIL",
   "evidence": "54 vs 65 of 100 solved (McNemar p = 0.019); mean steps 42.86 vs 40.06; a significant LOSS: the switch would have harmed this domain"
  }
 ],
 "counts": {
  "PASS": 3,
  "PARTIAL": 1,
  "FAIL": 4
 }
}