{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TX4JNSKYI75AQT5GTOAMFMF2DY","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":"fbad3c50df08e8e0e0388007972bd6fa9de290396304337f3325dba6ef1b1a7d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-08T05:14:07Z","title_canon_sha256":"c2198af8b1c981b0400aa0e23aba37bc863c7ed7f32f32d28ee916a640a7db19"},"schema_version":"1.0","source":{"id":"2408.04223","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04223","created_at":"2026-07-05T11:21:34Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04223v2","created_at":"2026-07-05T11:21:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04223","created_at":"2026-07-05T11:21:34Z"},{"alias_kind":"pith_short_12","alias_value":"TX4JNSKYI75A","created_at":"2026-07-05T11:21:34Z"},{"alias_kind":"pith_short_16","alias_value":"TX4JNSKYI75AQT5G","created_at":"2026-07-05T11:21:34Z"},{"alias_kind":"pith_short_8","alias_value":"TX4JNSKY","created_at":"2026-07-05T11:21:34Z"}],"graph_snapshots":[{"event_id":"sha256:2df4b6914b043453aba3b1ea071adcc7184a257740d507b30903be9bff21222c","target":"graph","created_at":"2026-07-05T11:21:34Z","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/2408.04223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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. ","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","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-08T05:14:07Z","title":"VideoQA in the Era of LLMs: An Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04223","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:cbf8ebd7896ac49cafb47717274c1dacdfe2be66f0634ace86815c9eaa2d02a2","target":"record","created_at":"2026-07-05T11:21:34Z","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":"fbad3c50df08e8e0e0388007972bd6fa9de290396304337f3325dba6ef1b1a7d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-08T05:14:07Z","title_canon_sha256":"c2198af8b1c981b0400aa0e23aba37bc863c7ed7f32f32d28ee916a640a7db19"},"schema_version":"1.0","source":{"id":"2408.04223","kind":"arxiv","version":2}},"canonical_sha256":"9df896c95847fa084fa69b80c2b0ba1e0748106fbb5b51d84585105cf88dc332","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9df896c95847fa084fa69b80c2b0ba1e0748106fbb5b51d84585105cf88dc332","first_computed_at":"2026-07-05T11:21:34.685038Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:34.685038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eLdJbHTCCXLzJ55DDCYs96V3X8ymYLQCN4b5874ZRngCVpDXh3RmROG3O2XlDfJgIfnry0SW+lm1B99miYj2Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:34.685588Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.04223","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbf8ebd7896ac49cafb47717274c1dacdfe2be66f0634ace86815c9eaa2d02a2","sha256:2df4b6914b043453aba3b1ea071adcc7184a257740d507b30903be9bff21222c"],"state_sha256":"890bbed5f68aa163ffa4ea22596dcb89fd93538ac293d511ab45934801c9dc20"}