Jens/geointel
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

audit: seal accuracy phase 1 evidence

Browse Source
This commit is contained in:
Jens
2026-08-01 19:02:24 +02:00
parent 3d442ef43f
commit cebeb5f3b4
29 changed files with 11269 additions and 10990 deletions
Download Patch File Download Diff File Expand all files Collapse all files
artifacts/evidence/accuracy/P1/golden-qa-reproducibility.json
+11 -11
View File
@@ -1,11 +1,11 @@
{
"schema_version": 1,
"command": "python scripts/run_golden_qa_benchmark.py --json",
"run_1_exit_code": 0,
"run_2_exit_code": 0,
"run_1_sha256": "ec96862b024987b59e56579920361582e718126b07885732335ac1b4d51b61bc",
"run_2_sha256": "4f900711a706dd56dd16b368e261761051f6d52a38bfd421e7d1c5f66ee51e49",
"byte_identical": false,
"semantic_results_equal": true,
"interpretation": "Metric values are stable, but UUID4-backed run identity makes retained JSON byte-nondeterministic."
}
{
"schema_version": 1,
"command": "python scripts/run_golden_qa_benchmark.py --json",
"run_1_exit_code": 0,
"run_2_exit_code": 0,
"run_1_sha256": "ec96862b024987b59e56579920361582e718126b07885732335ac1b4d51b61bc",
"run_2_sha256": "4f900711a706dd56dd16b368e261761051f6d52a38bfd421e7d1c5f66ee51e49",
"byte_identical": false,
"semantic_results_equal": true,
"interpretation": "Metric values are stable, but UUID4-backed run identity makes retained JSON byte-nondeterministic."
}