| { |
| "documents": 29103, |
| "excluded": { |
| "title_matches_aozora": 138, |
| "near_duplicate": 60 |
| }, |
| "near_duplicate_rate": 0.002164111812443643, |
| "sources": { |
| "aozora-bunko": { |
| "documents": 1576, |
| "characters": 15457625 |
| }, |
| "ndl-next-digital-library": { |
| "documents": 27527, |
| "characters": 1944648693 |
| } |
| }, |
| "new_orthography": { |
| "used": false, |
| "decision": "not needed because quality-passed pre-1946 NDL OCR exceeded the 200M-token gate" |
| }, |
| "fixed_phase1_test_ids": [ |
| "001323", |
| "001670", |
| "004525", |
| "024386", |
| "024388", |
| "043025", |
| "043634", |
| "046845", |
| "047869", |
| "047876", |
| "048360", |
| "048379", |
| "050028", |
| "050702", |
| "050784", |
| "053616", |
| "055209", |
| "055417", |
| "055869", |
| "058491", |
| "058761", |
| "059333", |
| "059989", |
| "060074" |
| ], |
| "manifest_sha256": "dd8c22806f385226e5c06b486b72e7742f969d8c3a6226f295cd799c16cf8671" |
| } |
|
|
