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
31 lines
626 B
JSON
31 lines
626 B
JSON
{
|
|
"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"
|
|
}
|