Ground truth comes only from third-party annotations (MMLongBench-Doc
evidence_page_ids, VisRAG qrels, ScreenSpot-v2 bboxes, Video-MME QA,
LongMemEval answer_session_ids, CodeSearchNet func_path+func_name) and
from document structure; no model judgement is used anywhere.
- bench/corpus/manifest.jsonl: 28 sources with url, retrieved_at, sha256,
annotation_source, license, files[]; verified by bench.manifest_check
- bench/sets/{pdf,image,ui_screenshot,video,code,conversation}.{jsonl} plus
corpus indexes and a manifest that freezes every file's sha256
- 2,928 answerable + 2,380 unanswerable queries over 854 holders; every
query carries scope {holder, scenario, as_of} for transactive routing
- bench/validate_sets.py fails on missing gold, holder mismatch between
gold and query, gold observed after as_of, and manifest digest drift
38 lines
1.0 KiB
JSON
38 lines
1.0 KiB
JSON
{
|
|
"annotation_rows": 1091,
|
|
"corpus_records": 123,
|
|
"corpus_sha256": "68f20f0b5b203b73aa08adbb4e61a512d5c9d55f60d10ea229bbdfc3322cf713",
|
|
"datasets": [
|
|
"yubo2333/MMLongBench-Doc"
|
|
],
|
|
"documents_annotated": 135,
|
|
"documents_dropped": [
|
|
"2023.acl-long.386.pdf",
|
|
"2307.09288v2.pdf",
|
|
"2312.09390v1.pdf",
|
|
"NYU_graduate.pdf",
|
|
"PI_2018.11.19_algorithms_FINAL.pdf",
|
|
"PS_2018.01.09_STEM_FINAL.pdf",
|
|
"bigdatatrends-120723191058-phpapp02_95.pdf",
|
|
"edb88a99670417f64a6b719646aed326.pdf",
|
|
"f1f5242528411b262be447e61e2eb10f.pdf",
|
|
"mi_phone.pdf",
|
|
"san-francisco-11-contents.pdf",
|
|
"stereo_headset.pdf"
|
|
],
|
|
"documents_usable": 123,
|
|
"holders": [
|
|
"Academic-paper",
|
|
"Administration-Industry-file",
|
|
"Brochure",
|
|
"Financial-report",
|
|
"Guidebook",
|
|
"Research-report-Introduction",
|
|
"Tutorial-Workshop"
|
|
],
|
|
"queries": 984,
|
|
"queries_dropped_no_evidence_page": 9,
|
|
"queries_sha256": "0cec488e660bf1bfa7ccfc72dbae8b7e3005f0b6a0255028e502296d4ecd4536",
|
|
"revision": "2ff6aa9237fc777b6627dc57a486e9225ac5fb86",
|
|
"unanswerable": 218
|
|
} |