{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HTWRT6EDFSG3VT3KPBFQNWY32L","short_pith_number":"pith:HTWRT6ED","schema_version":"1.0","canonical_sha256":"3ced19f8832c8dbacf6a784b06db1bd2f648e02fb0a42925e1c740f94a91a672","source":{"kind":"arxiv","id":"2312.04817","version":2},"attestation_state":"computed","paper":{"title":"LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongjie Zhang, Limin Wang, Lu Dong, Yali Wang, Yifei Huang, Yi Liu, Yu Qiao","submitted_at":"2023-12-08T03:33:38Z","abstract_excerpt":"Despite remarkable recent progress, existing long-form VideoQA datasets fall short of meeting the criteria for genuine long-form video understanding. This is primarily due to the use of short videos for question curation, and the reliance on limited-length sub-clips as clues to answer those questions. Meanwhile, previous datasets have limited focus on question type and modality. To remedy this, we introduce LvBench, a Long-form video understanding benchmark for versatile multi-modal question-answering. Our LvBench stands out from existing long-form VideoQA datasets through three key characteri"},"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":"2312.04817","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-08T03:33:38Z","cross_cats_sorted":[],"title_canon_sha256":"e8afa9ecad54432d18693db63583824d051025accdcd1a340c978440501591d6","abstract_canon_sha256":"d533851c30fb89d397b0aafac800a63357b2b3a297788e83b37c4455c9b4adab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:32.863424Z","signature_b64":"jdx0vW0eQcQAvp0PofOH9pJa4fg+98BAV1iUL+Ka1Gqop0FphG7u9qmGJN5U4dBVrncOTJ+FxjiyoBL5dNlHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ced19f8832c8dbacf6a784b06db1bd2f648e02fb0a42925e1c740f94a91a672","last_reissued_at":"2026-07-05T12:02:32.862926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:32.862926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongjie Zhang, Limin Wang, Lu Dong, Yali Wang, Yifei Huang, Yi Liu, Yu Qiao","submitted_at":"2023-12-08T03:33:38Z","abstract_excerpt":"Despite remarkable recent progress, existing long-form VideoQA datasets fall short of meeting the criteria for genuine long-form video understanding. This is primarily due to the use of short videos for question curation, and the reliance on limited-length sub-clips as clues to answer those questions. Meanwhile, previous datasets have limited focus on question type and modality. To remedy this, we introduce LvBench, a Long-form video understanding benchmark for versatile multi-modal question-answering. Our LvBench stands out from existing long-form VideoQA datasets through three key characteri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04817","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/2312.04817/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":"2312.04817","created_at":"2026-07-05T12:02:32.862982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04817v2","created_at":"2026-07-05T12:02:32.862982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04817","created_at":"2026-07-05T12:02:32.862982+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTWRT6EDFSG3","created_at":"2026-07-05T12:02:32.862982+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTWRT6EDFSG3VT3K","created_at":"2026-07-05T12:02:32.862982+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTWRT6ED","created_at":"2026-07-05T12:02:32.862982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12195","citing_title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","ref_index":299,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05748","citing_title":"UNIVID: Unified Vision-Language Model for Video Moderation","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2406.08035","citing_title":"LVBench: An Extreme Long Video Understanding Benchmark","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00574","citing_title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2311.17005","citing_title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2501.12386","citing_title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22779","citing_title":"TrajTok: Learning Trajectory Tokens enables better Video Understanding","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27259","citing_title":"Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HTWRT6EDFSG3VT3KPBFQNWY32L","json":"https://pith.science/pith/HTWRT6EDFSG3VT3KPBFQNWY32L.json","graph_json":"https://pith.science/api/pith-number/HTWRT6EDFSG3VT3KPBFQNWY32L/graph.json","events_json":"https://pith.science/api/pith-number/HTWRT6EDFSG3VT3KPBFQNWY32L/events.json","paper":"https://pith.science/paper/HTWRT6ED"},"agent_actions":{"view_html":"https://pith.science/pith/HTWRT6EDFSG3VT3KPBFQNWY32L","download_json":"https://pith.science/pith/HTWRT6EDFSG3VT3KPBFQNWY32L.json","view_paper":"https://pith.science/paper/HTWRT6ED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04817&json=true","fetch_graph":"https://pith.science/api/pith-number/HTWRT6EDFSG3VT3KPBFQNWY32L/graph.json","fetch_events":"https://pith.science/api/pith-number/HTWRT6EDFSG3VT3KPBFQNWY32L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTWRT6EDFSG3VT3KPBFQNWY32L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTWRT6EDFSG3VT3KPBFQNWY32L/action/storage_attestation","attest_author":"https://pith.science/pith/HTWRT6EDFSG3VT3KPBFQNWY32L/action/author_attestation","sign_citation":"https://pith.science/pith/HTWRT6EDFSG3VT3KPBFQNWY32L/action/citation_signature","submit_replication":"https://pith.science/pith/HTWRT6EDFSG3VT3KPBFQNWY32L/action/replication_record"}},"created_at":"2026-07-05T12:02:32.862982+00:00","updated_at":"2026-07-05T12:02:32.862982+00:00"}