Files
ely-eye/bench/sets/reports/conversation.json
T
ZacharyZhang-NY 77219c930b Add third-party benchmark suite frozen at 50,789 sources / 5,308 queries
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
2026-10-06 12:05:43 -04:00

178 lines
3.0 KiB
JSON

{
"as_of_pushed_to_newest_answer_session": 10,
"by_category": {
"knowledge-update": 25,
"multi-session": 25,
"single-session-assistant": 25,
"single-session-preference": 25,
"single-session-user": 25,
"temporal-reasoning": 25
},
"corpus_records": 7188,
"corpus_sha256": "9cc8263c6a6d54ddc86ff1936ca57ddfd03e58d4b6dc0013cd0c47100e95a92f",
"datasets": [
"xiaowu0162/longmemeval-cleaned"
],
"holders": [
"00ca467f",
"01493427",
"06878be2",
"06db6396",
"06f04340",
"07b6f563",
"0862e8bf",
"08e075c7",
"08f4fc43",
"09d032c9",
"0a34ad58",
"0a995998",
"0ddfec37_abs",
"0e5e2d1a",
"0edc2aef",
"10e09553",
"118b2229",
"15745da0_abs",
"157a136e",
"16c90bf4",
"1903aded",
"195a1a1b",
"19b5f2b3_abs",
"1a1907b4",
"1c0ddc50",
"1d4e3b97",
"1da05512",
"1de5cff2",
"2133c1b5",
"21436231",
"2311e44b",
"2698e78f",
"28dc39ac",
"29f2956b",
"2a1811e2",
"2bf43736",
"311778f1",
"32260d93",
"352ab8bd",
"35a27287",
"37d43f65",
"37f165cf",
"38146c39",
"3ba21379",
"3d86fd0a",
"4100d0a0",
"41275add",
"45dc21b6",
"46a3abf7",
"488d3006",
"4c36ccef",
"4dfccbf7",
"505af2f5",
"50635ada",
"51a45a95",
"51c32626",
"54026fce",
"561fabcd",
"577d4d32",
"57f827a0",
"58470ed2",
"5a4f22c0",
"5d3d2817",
"60472f9c",
"6071bd76",
"6456829e_abs",
"65240037",
"66f24dbb",
"6a1eabeb",
"6aeb4375_abs",
"6b168ec8",
"6b7dfb22",
"6d550036",
"6e984302",
"70b3e69b",
"71a3fd6b",
"726462e0",
"7401057b",
"75499fd8",
"75832dbd",
"75f70248",
"77eafa52",
"7a8d0b71",
"830ce83f",
"8464fc84",
"853b0a1d",
"86b68151",
"87f22b4a",
"89527b6b",
"89941a94",
"8a137a7f",
"8a2466db",
"8b9d4367",
"8e91e7d9",
"8ebdbe50",
"95228167",
"95bcc1c8",
"982b5123",
"9bbe84a2",
"a08a253f",
"a2f3aa27",
"a3045048",
"a40e080f",
"a4996e51",
"a82c026e",
"a89d7624",
"af8d2e46",
"afdc33df",
"b0479f84",
"b3c15d39",
"b46e15ee",
"b6019101",
"b759caee",
"b86304ba",
"bc149d6b",
"c6853660",
"c7cf7dfd",
"c8090214_abs",
"cc06de0d",
"cc539528",
"cf22b7bf",
"d596882b",
"d905b33f",
"db467c8c",
"e3fc4d6e",
"e4e14d04",
"e5ba910e_abs",
"e61a7584",
"e8a79c70",
"ed4ddc30",
"eeda8a6d",
"f0e564bc",
"gpt4_0b2f1d21",
"gpt4_1d80365e",
"gpt4_2312f94c",
"gpt4_2f56ae70",
"gpt4_2f8be40d",
"gpt4_468eb064",
"gpt4_4ef30696",
"gpt4_5501fe77",
"gpt4_5dcc0aab",
"gpt4_6dc9b45b",
"gpt4_78cf46a3",
"gpt4_7ddcf75f",
"gpt4_85da3956",
"gpt4_93159ced_abs",
"gpt4_a2d1d1f6",
"gpt4_b5700ca9",
"gpt4_d6585ce9",
"gpt4_e414231e"
],
"items_dropped_duplicate_sessions": 13,
"items_sampled": 150,
"items_total": 500,
"queries": 300,
"queries_answerable": 150,
"queries_cross_holder_unanswerable": 150,
"queries_sha256": "dc106d90e7749bee8be01b1fab3b645a5459d7527ef40e7fbf983677d5898d11",
"queries_with_turn_level_gold": 136,
"revision": "98d7416c24c778c2fee6e6f3006e7a073259d48f",
"sessions": 7188
}