{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TC3OA3ALHUNVIGDKKF4TQMRJVO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d1b13fe08856b7348fc4fd6e335c3233ff946d050d8009c7bb3f0552fd796786","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-08T18:34:21Z","title_canon_sha256":"ff173bc29f3979ce978e26308f1156426986a9e881eeea5ad4b52d14818522cf"},"schema_version":"1.0","source":{"id":"2106.04632","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.04632","created_at":"2026-07-05T03:07:07Z"},{"alias_kind":"arxiv_version","alias_value":"2106.04632v2","created_at":"2026-07-05T03:07:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04632","created_at":"2026-07-05T03:07:07Z"},{"alias_kind":"pith_short_12","alias_value":"TC3OA3ALHUNV","created_at":"2026-07-05T03:07:07Z"},{"alias_kind":"pith_short_16","alias_value":"TC3OA3ALHUNVIGDK","created_at":"2026-07-05T03:07:07Z"},{"alias_kind":"pith_short_8","alias_value":"TC3OA3AL","created_at":"2026-07-05T03:07:07Z"}],"graph_snapshots":[{"event_id":"sha256:138c36f625bf96fff1e5c5071505b5a6f557223392d20198d80ca15406d34054","target":"graph","created_at":"2026-07-05T03:07:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.04632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most existing video-and-language (VidL) research focuses on a single dataset, or multiple datasets of a single task. In reality, a truly useful VidL system is expected to be easily generalizable to diverse tasks, domains, and datasets. To facilitate the evaluation of such systems, we introduce Video-And-Language Understanding Evaluation (VALUE) benchmark, an assemblage of 11 VidL datasets over 3 popular tasks: (i) text-to-video retrieval; (ii) video question answering; and (iii) video captioning. VALUE benchmark aims to cover a broad range of video genres, video lengths, data volumes, and task","authors_text":"Jie Lei, Jingjing Liu, Licheng Yu, Lijuan Wang, Linjie Li, Luowei Zhou, Mohit Bansal, Rohit Pillai, Tamara Lee Berg, William Yang Wang, Xin Eric Wang, Yen-Chun Chen, Yu Cheng, Zhe Gan, Zicheng Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-08T18:34:21Z","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04632","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b683c72c0b0c4f14c85d881ae1266bb567a20aed94730d11a69ab1384648e084","target":"record","created_at":"2026-07-05T03:07:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d1b13fe08856b7348fc4fd6e335c3233ff946d050d8009c7bb3f0552fd796786","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-08T18:34:21Z","title_canon_sha256":"ff173bc29f3979ce978e26308f1156426986a9e881eeea5ad4b52d14818522cf"},"schema_version":"1.0","source":{"id":"2106.04632","kind":"arxiv","version":2}},"canonical_sha256":"98b6e06c0b3d1b54186a5179383229ab9f998065604b6a6f79166fb79e65c7b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98b6e06c0b3d1b54186a5179383229ab9f998065604b6a6f79166fb79e65c7b0","first_computed_at":"2026-07-05T03:07:07.081159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:07:07.081159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IH0NCAO1A6Kf2QOf1KKwTXq4cbRVnMZbD5zvIHJPbt3xGtYgkn1SrR/o16wMqtY6qn/PEjcdWimWJ56xDrSKCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:07:07.081738Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.04632","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b683c72c0b0c4f14c85d881ae1266bb567a20aed94730d11a69ab1384648e084","sha256:138c36f625bf96fff1e5c5071505b5a6f557223392d20198d80ca15406d34054"],"state_sha256":"c1f3ca8814b273cfa782e979a04a24c1282428df378d10de13d99ef6659d31e0"}