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
217 lines
6.2 KiB
JSON
217 lines
6.2 KiB
JSON
{
|
|
"schema_version": 1,
|
|
"experiment": "10-5",
|
|
"run_id": "exp10-5-qwen37flash-20260804-v1",
|
|
"passed": true,
|
|
"gates": {
|
|
"pinned_clean_source": true,
|
|
"shared_history_seed": true,
|
|
"exact_three_arm_shape": true,
|
|
"exact_two_virtual_days": true,
|
|
"complete_movement_streams": true,
|
|
"complete_memory_streams": true,
|
|
"custom_goal_applied": true,
|
|
"reflection_ablation_effective": true,
|
|
"provider_receipts_real_and_complete": true,
|
|
"action_arena_compatibility_bounded": true,
|
|
"deterministic_analysis_complete": true,
|
|
"blind_plausibility_judgments": true,
|
|
"manifest_complete_and_valid": true,
|
|
"credential_scan_clean": true
|
|
},
|
|
"counts": {
|
|
"arms": 3,
|
|
"personas_per_arm": 25,
|
|
"steps_per_arm": 17280,
|
|
"provider_receipts": 148856,
|
|
"provider_response_ids": 148856,
|
|
"action_arena_compatibility_corrections": 231,
|
|
"judge_response_ids": 25,
|
|
"movement_rows": {
|
|
"baseline": 17280,
|
|
"custom_goal": 17280,
|
|
"no_reflection": 17280
|
|
},
|
|
"memory_rows": {
|
|
"baseline": 17469,
|
|
"custom_goal": 14008,
|
|
"no_reflection": 14053
|
|
},
|
|
"manifest_files": 321
|
|
},
|
|
"results": {
|
|
"baseline_event_diffusion": {
|
|
"terms": [
|
|
"valentine",
|
|
"party"
|
|
],
|
|
"aware_agents": 3,
|
|
"first_mention_by_agent": {
|
|
"Isabella Rodriguez": "2023-02-13 00:00:00",
|
|
"Jennifer Moore": "2023-02-14 05:01:20",
|
|
"Sam Moore": "2023-02-14 05:01:20"
|
|
},
|
|
"memory_mentions_by_agent": {
|
|
"Isabella Rodriguez": 36,
|
|
"Jennifer Moore": 5,
|
|
"Sam Moore": 5
|
|
}
|
|
},
|
|
"custom_event_diffusion": {
|
|
"terms": [
|
|
"climate",
|
|
"resilience",
|
|
"workshop"
|
|
],
|
|
"aware_agents": 1,
|
|
"first_mention_by_agent": {
|
|
"Isabella Rodriguez": "2023-02-13 08:30:10"
|
|
},
|
|
"memory_mentions_by_agent": {
|
|
"Isabella Rodriguez": 5
|
|
}
|
|
},
|
|
"election_diffusion": {
|
|
"baseline": {
|
|
"terms": [
|
|
"mayor",
|
|
"election"
|
|
],
|
|
"aware_agents": 11,
|
|
"first_mention_by_agent": {
|
|
"Adam Smith": "2023-02-13 00:00:00",
|
|
"Carmen Ortiz": "2023-02-13 00:00:00",
|
|
"Francisco Lopez": "2023-02-13 07:36:20",
|
|
"Giorgio Rossi": "2023-02-13 07:15:10",
|
|
"Jennifer Moore": "2023-02-13 00:00:00",
|
|
"John Lin": "2023-02-13 00:00:00",
|
|
"Latoya Williams": "2023-02-13 00:00:00",
|
|
"Rajiv Patel": "2023-02-13 00:00:00",
|
|
"Sam Moore": "2023-02-13 00:00:00",
|
|
"Tom Moreno": "2023-02-13 00:00:00",
|
|
"Yuriko Yamamoto": "2023-02-13 00:00:00"
|
|
},
|
|
"memory_mentions_by_agent": {
|
|
"Adam Smith": 24,
|
|
"Carmen Ortiz": 6,
|
|
"Francisco Lopez": 5,
|
|
"Giorgio Rossi": 3,
|
|
"Jennifer Moore": 21,
|
|
"John Lin": 7,
|
|
"Latoya Williams": 13,
|
|
"Rajiv Patel": 4,
|
|
"Sam Moore": 19,
|
|
"Tom Moreno": 17,
|
|
"Yuriko Yamamoto": 6
|
|
}
|
|
},
|
|
"custom_goal": {
|
|
"terms": [
|
|
"mayor",
|
|
"election"
|
|
],
|
|
"aware_agents": 14,
|
|
"first_mention_by_agent": {
|
|
"Abigail Chen": "2023-02-13 18:09:10",
|
|
"Adam Smith": "2023-02-13 00:00:00",
|
|
"Carmen Ortiz": "2023-02-13 00:00:00",
|
|
"Francisco Lopez": "2023-02-13 08:49:00",
|
|
"Giorgio Rossi": "2023-02-13 00:00:00",
|
|
"Hailey Johnson": "2023-02-13 15:13:00",
|
|
"Jane Moreno": "2023-02-13 23:35:10",
|
|
"Jennifer Moore": "2023-02-13 00:00:00",
|
|
"John Lin": "2023-02-13 00:00:00",
|
|
"Latoya Williams": "2023-02-13 00:00:00",
|
|
"Rajiv Patel": "2023-02-13 00:00:00",
|
|
"Sam Moore": "2023-02-13 00:00:00",
|
|
"Tom Moreno": "2023-02-13 00:00:00",
|
|
"Yuriko Yamamoto": "2023-02-13 00:00:00"
|
|
},
|
|
"memory_mentions_by_agent": {
|
|
"Abigail Chen": 5,
|
|
"Adam Smith": 4,
|
|
"Carmen Ortiz": 3,
|
|
"Francisco Lopez": 6,
|
|
"Giorgio Rossi": 10,
|
|
"Hailey Johnson": 1,
|
|
"Jane Moreno": 1,
|
|
"Jennifer Moore": 12,
|
|
"John Lin": 8,
|
|
"Latoya Williams": 24,
|
|
"Rajiv Patel": 2,
|
|
"Sam Moore": 23,
|
|
"Tom Moreno": 29,
|
|
"Yuriko Yamamoto": 16
|
|
}
|
|
},
|
|
"no_reflection": {
|
|
"terms": [
|
|
"mayor",
|
|
"election"
|
|
],
|
|
"aware_agents": 13,
|
|
"first_mention_by_agent": {
|
|
"Adam Smith": "2023-02-13 00:00:00",
|
|
"Carmen Ortiz": "2023-02-13 00:00:00",
|
|
"Eddy Lin": "2023-02-13 07:25:00",
|
|
"Francisco Lopez": "2023-02-13 07:16:40",
|
|
"Giorgio Rossi": "2023-02-13 00:00:00",
|
|
"Jennifer Moore": "2023-02-13 00:00:00",
|
|
"John Lin": "2023-02-13 00:00:00",
|
|
"Latoya Williams": "2023-02-13 00:00:00",
|
|
"Mei Lin": "2023-02-13 07:25:00",
|
|
"Rajiv Patel": "2023-02-13 00:00:00",
|
|
"Sam Moore": "2023-02-13 00:00:00",
|
|
"Tom Moreno": "2023-02-13 00:00:00",
|
|
"Yuriko Yamamoto": "2023-02-13 00:00:00"
|
|
},
|
|
"memory_mentions_by_agent": {
|
|
"Adam Smith": 10,
|
|
"Carmen Ortiz": 3,
|
|
"Eddy Lin": 31,
|
|
"Francisco Lopez": 6,
|
|
"Giorgio Rossi": 2,
|
|
"Jennifer Moore": 1,
|
|
"John Lin": 34,
|
|
"Latoya Williams": 13,
|
|
"Mei Lin": 17,
|
|
"Rajiv Patel": 2,
|
|
"Sam Moore": 2,
|
|
"Tom Moreno": 9,
|
|
"Yuriko Yamamoto": 4
|
|
}
|
|
}
|
|
},
|
|
"plausibility": {
|
|
"schema_version": 1,
|
|
"experiment": "10-5",
|
|
"model": "claude-sonnet-4-5-20250929",
|
|
"judgments": 25,
|
|
"preferences": {
|
|
"baseline": 17,
|
|
"no_reflection": 8,
|
|
"tie": 0
|
|
},
|
|
"mean_scores": {
|
|
"temporal_coherence": {
|
|
"baseline": 2.12,
|
|
"no_reflection": 1.56
|
|
},
|
|
"personality_consistency": {
|
|
"baseline": 3.2,
|
|
"no_reflection": 2.2
|
|
},
|
|
"memory_continuity": {
|
|
"baseline": 2.72,
|
|
"no_reflection": 1.52
|
|
},
|
|
"social_responsiveness": {
|
|
"baseline": 3.44,
|
|
"no_reflection": 2.48
|
|
}
|
|
},
|
|
"raw_receipts": "analysis/plausibility_judgments.jsonl"
|
|
}
|
|
}
|
|
}
|