{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TX4JNSKYI75AQT5GTOAMFMF2DY","short_pith_number":"pith:TX4JNSKY","schema_version":"1.0","canonical_sha256":"9df896c95847fa084fa69b80c2b0ba1e0748106fbb5b51d84585105cf88dc332","source":{"kind":"arxiv","id":"2408.04223","version":2},"attestation_state":"computed","paper":{"title":"VideoQA in the Era of LLMs: An Empirical Study","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Angela Yao, Dongyang Li, Fengbin Zhu, Hangyu Qin, Jianxing Yu, Junbin Xiao, Liang Lin, Nanxin Huang, Tat-Seng Chua, Yicong Li, Zhulin Tao","submitted_at":"2024-08-08T05:14:07Z","abstract_excerpt":"Video Large Language Models (Video-LLMs) are flourishing and has advanced many video-language tasks. As a golden testbed, Video Question Answering (VideoQA) plays pivotal role in Video-LLM developing. This work conducts a timely and comprehensive study of Video-LLMs' behavior in VideoQA, aiming to elucidate their success and failure modes, and provide insights towards more human-like video understanding and question answering. Our analyses demonstrate that Video-LLMs excel in VideoQA; they can correlate contextual cues and generate plausible responses to questions about varied video contents. "},"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":"2408.04223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-08T05:14:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c2198af8b1c981b0400aa0e23aba37bc863c7ed7f32f32d28ee916a640a7db19","abstract_canon_sha256":"fbad3c50df08e8e0e0388007972bd6fa9de290396304337f3325dba6ef1b1a7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:34.685588Z","signature_b64":"eLdJbHTCCXLzJ55DDCYs96V3X8ymYLQCN4b5874ZRngCVpDXh3RmROG3O2XlDfJgIfnry0SW+lm1B99miYj2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9df896c95847fa084fa69b80c2b0ba1e0748106fbb5b51d84585105cf88dc332","last_reissued_at":"2026-07-05T11:21:34.685038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:34.685038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoQA in the Era of LLMs: An Empirical Study","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Angela Yao, Dongyang Li, Fengbin Zhu, Hangyu Qin, Jianxing Yu, Junbin Xiao, Liang Lin, Nanxin Huang, Tat-Seng Chua, Yicong Li, Zhulin Tao","submitted_at":"2024-08-08T05:14:07Z","abstract_excerpt":"Video Large Language Models (Video-LLMs) are flourishing and has advanced many video-language tasks. As a golden testbed, Video Question Answering (VideoQA) plays pivotal role in Video-LLM developing. This work conducts a timely and comprehensive study of Video-LLMs' behavior in VideoQA, aiming to elucidate their success and failure modes, and provide insights towards more human-like video understanding and question answering. Our analyses demonstrate that Video-LLMs excel in VideoQA; they can correlate contextual cues and generate plausible responses to questions about varied video contents. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04223","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/2408.04223/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":"2408.04223","created_at":"2026-07-05T11:21:34.685099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04223v2","created_at":"2026-07-05T11:21:34.685099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04223","created_at":"2026-07-05T11:21:34.685099+00:00"},{"alias_kind":"pith_short_12","alias_value":"TX4JNSKYI75A","created_at":"2026-07-05T11:21:34.685099+00:00"},{"alias_kind":"pith_short_16","alias_value":"TX4JNSKYI75AQT5G","created_at":"2026-07-05T11:21:34.685099+00:00"},{"alias_kind":"pith_short_8","alias_value":"TX4JNSKY","created_at":"2026-07-05T11:21:34.685099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23145","citing_title":"UpstreamQA: A Modular Framework for Explicit Reasoning on Video Question Answering Tasks","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TX4JNSKYI75AQT5GTOAMFMF2DY","json":"https://pith.science/pith/TX4JNSKYI75AQT5GTOAMFMF2DY.json","graph_json":"https://pith.science/api/pith-number/TX4JNSKYI75AQT5GTOAMFMF2DY/graph.json","events_json":"https://pith.science/api/pith-number/TX4JNSKYI75AQT5GTOAMFMF2DY/events.json","paper":"https://pith.science/paper/TX4JNSKY"},"agent_actions":{"view_html":"https://pith.science/pith/TX4JNSKYI75AQT5GTOAMFMF2DY","download_json":"https://pith.science/pith/TX4JNSKYI75AQT5GTOAMFMF2DY.json","view_paper":"https://pith.science/paper/TX4JNSKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04223&json=true","fetch_graph":"https://pith.science/api/pith-number/TX4JNSKYI75AQT5GTOAMFMF2DY/graph.json","fetch_events":"https://pith.science/api/pith-number/TX4JNSKYI75AQT5GTOAMFMF2DY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TX4JNSKYI75AQT5GTOAMFMF2DY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TX4JNSKYI75AQT5GTOAMFMF2DY/action/storage_attestation","attest_author":"https://pith.science/pith/TX4JNSKYI75AQT5GTOAMFMF2DY/action/author_attestation","sign_citation":"https://pith.science/pith/TX4JNSKYI75AQT5GTOAMFMF2DY/action/citation_signature","submit_replication":"https://pith.science/pith/TX4JNSKYI75AQT5GTOAMFMF2DY/action/replication_record"}},"created_at":"2026-07-05T11:21:34.685099+00:00","updated_at":"2026-07-05T11:21:34.685099+00:00"}