[
 {
  "set": "real (4 AI Model Benchmark sessions)",
  "completion_claims": 7,
  "unbacked_without_gate": "1/7",
  "unbacked_reaching_user_with_gate": "0/7",
  "gate_blocks": 1,
  "false_blocks": 0,
  "false_passes": [],
  "false_block_keys": [],
  "non_claims_blocked": [
   ""
  ]
 },
 {
  "set": "synthetic (10 scripted sessions, written by us)",
  "completion_claims": 10,
  "unbacked_without_gate": "7/10",
  "unbacked_reaching_user_with_gate": "2/10",
  "gate_blocks": 6,
  "false_blocks": 1,
  "false_passes": [
   "s08_wrong_file_rendered\u00405",
   "s09_parse_only_visual_claim\u00405"
  ],
  "false_block_keys": [
   "s05_copy_into_place\u00407"
  ],
  "non_claims_blocked": []
 }
]