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
42 lines
1.2 KiB
JSON
42 lines
1.2 KiB
JSON
{
|
|
"schema_version": "1.0",
|
|
"experiment": "5-1",
|
|
"run_id": "exp5-1-ark-doubao-flash-aime2024-20260730-v1",
|
|
"result_status": "complete_exact_experiment",
|
|
"official_complete": true,
|
|
"hypothesis_supported": false,
|
|
"result": {
|
|
"cot_correct": 11,
|
|
"code_correct": 16,
|
|
"n": 30,
|
|
"accuracy_delta": 0.16666666666666669,
|
|
"mcnemar_exact_p_value": 0.125
|
|
},
|
|
"gates": {
|
|
"exact_pinned_aime_2024_manifest": true,
|
|
"all_30_unique_aime_i_and_ii_tasks": true,
|
|
"all_required_cot_trajectories_complete": true,
|
|
"all_required_code_trajectories_complete": true,
|
|
"zero_provider_errors": true,
|
|
"every_code_trajectory_called_real_sandbox": true
|
|
},
|
|
"artifacts": {
|
|
"aime_2024.json": {
|
|
"sha256": "8ce3b0e62b7e680e0909ed7afa810ed6a43ad11e66d65ff7897fb2f94508c6d4",
|
|
"bytes": 21719
|
|
},
|
|
"aime_2024.manifest.json": {
|
|
"sha256": "ef698a4071fa8e3bbfefebe65835909a96087f4d056e24f36e4454d163dbc37b",
|
|
"bytes": 481
|
|
},
|
|
"command.json": {
|
|
"sha256": "d5cb01ffb8eccb68859616ae2b5f8f5dbc4b3669b920a844630ee7ee285f339c",
|
|
"bytes": 353
|
|
},
|
|
"result.json": {
|
|
"sha256": "846e2e2431b0b2c704b6d139df952047229060cbbd29df8400def80c42d266ac",
|
|
"bytes": 354724
|
|
}
|
|
}
|
|
}
|