liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
40 lines
1.4 KiB
JSON
40 lines
1.4 KiB
JSON
{
|
|
"schema_version": 1,
|
|
"experiment": "10-6",
|
|
"generated_at": "2026-07-29T20:29:44+0800",
|
|
"mode": "real_llm_audit_of_offline_all_ai_supplement",
|
|
"acceptance_path": false,
|
|
"human_audio_used": false,
|
|
"provider": "ark",
|
|
"model": "doubao-seed-1-6-250615",
|
|
"completed_cycles": 2,
|
|
"winner": "狼人阵营",
|
|
"action_count": 31,
|
|
"audit": {
|
|
"criteria": {
|
|
"werewolf_concealment": {
|
|
"status": "fail",
|
|
"evidence": "P6 speech: '我是好人，从发言看 P1 有点可疑，建议重点关注他。' (Accuses teammate P1)"
|
|
},
|
|
"seer_timing_and_evidence": {
|
|
"status": "fail",
|
|
"evidence": "P4 never reveals the known P7/P5 investigation results in its public speeches"
|
|
},
|
|
"villager_logical_reasoning": {
|
|
"status": "fail",
|
|
"evidence": "P3 says it merely feels P7 is suspicious without citing public speech or voting behavior"
|
|
},
|
|
"role_consistency": {
|
|
"status": "fail",
|
|
"evidence": "P4 withholds Seer results and P6 accuses its Werewolf teammate P1"
|
|
}
|
|
},
|
|
"model_overall_pass_claim": false,
|
|
"schema_valid": true,
|
|
"validation_errors": [],
|
|
"overall_pass": false
|
|
},
|
|
"overall_status": "supplemental_only",
|
|
"acceptance_note": "The audit used a real text-model endpoint, but graded deterministic offline actions, had no human seat/audio, completed only two cycles, and failed all role-strategy criteria. It is not live acceptance."
|
|
}
|