{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TC3OA3ALHUNVIGDKKF4TQMRJVO","short_pith_number":"pith:TC3OA3AL","schema_version":"1.0","canonical_sha256":"98b6e06c0b3d1b54186a5179383229ab9f998065604b6a6f79166fb79e65c7b0","source":{"kind":"arxiv","id":"2106.04632","version":2},"attestation_state":"computed","paper":{"title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","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","submitted_at":"2021-06-08T18:34:21Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2106.04632","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-08T18:34:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ff173bc29f3979ce978e26308f1156426986a9e881eeea5ad4b52d14818522cf","abstract_canon_sha256":"d1b13fe08856b7348fc4fd6e335c3233ff946d050d8009c7bb3f0552fd796786"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:07.081738Z","signature_b64":"IH0NCAO1A6Kf2QOf1KKwTXq4cbRVnMZbD5zvIHJPbt3xGtYgkn1SrR/o16wMqtY6qn/PEjcdWimWJ56xDrSKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98b6e06c0b3d1b54186a5179383229ab9f998065604b6a6f79166fb79e65c7b0","last_reissued_at":"2026-07-05T03:07:07.081159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:07.081159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","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","submitted_at":"2021-06-08T18:34:21Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04632","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.04632/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.04632","created_at":"2026-07-05T03:07:07.081221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.04632v2","created_at":"2026-07-05T03:07:07.081221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04632","created_at":"2026-07-05T03:07:07.081221+00:00"},{"alias_kind":"pith_short_12","alias_value":"TC3OA3ALHUNV","created_at":"2026-07-05T03:07:07.081221+00:00"},{"alias_kind":"pith_short_16","alias_value":"TC3OA3ALHUNVIGDK","created_at":"2026-07-05T03:07:07.081221+00:00"},{"alias_kind":"pith_short_8","alias_value":"TC3OA3AL","created_at":"2026-07-05T03:07:07.081221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04549","citing_title":"MSC: A Marine Wildlife Video Dataset with Grounded Segmentation and Clip-Level Captioning","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TC3OA3ALHUNVIGDKKF4TQMRJVO","json":"https://pith.science/pith/TC3OA3ALHUNVIGDKKF4TQMRJVO.json","graph_json":"https://pith.science/api/pith-number/TC3OA3ALHUNVIGDKKF4TQMRJVO/graph.json","events_json":"https://pith.science/api/pith-number/TC3OA3ALHUNVIGDKKF4TQMRJVO/events.json","paper":"https://pith.science/paper/TC3OA3AL"},"agent_actions":{"view_html":"https://pith.science/pith/TC3OA3ALHUNVIGDKKF4TQMRJVO","download_json":"https://pith.science/pith/TC3OA3ALHUNVIGDKKF4TQMRJVO.json","view_paper":"https://pith.science/paper/TC3OA3AL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.04632&json=true","fetch_graph":"https://pith.science/api/pith-number/TC3OA3ALHUNVIGDKKF4TQMRJVO/graph.json","fetch_events":"https://pith.science/api/pith-number/TC3OA3ALHUNVIGDKKF4TQMRJVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TC3OA3ALHUNVIGDKKF4TQMRJVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TC3OA3ALHUNVIGDKKF4TQMRJVO/action/storage_attestation","attest_author":"https://pith.science/pith/TC3OA3ALHUNVIGDKKF4TQMRJVO/action/author_attestation","sign_citation":"https://pith.science/pith/TC3OA3ALHUNVIGDKKF4TQMRJVO/action/citation_signature","submit_replication":"https://pith.science/pith/TC3OA3ALHUNVIGDKKF4TQMRJVO/action/replication_record"}},"created_at":"2026-07-05T03:07:07.081221+00:00","updated_at":"2026-07-05T03:07:07.081221+00:00"}