{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QXUARRCVTCQH5WJU4OBJV3IGPS","short_pith_number":"pith:QXUARRCV","schema_version":"1.0","canonical_sha256":"85e808c45598a07ed934e3829aed067c9a26e519173c91e3143bfc4de168e68f","source":{"kind":"arxiv","id":"2503.07298","version":2},"attestation_state":"computed","paper":{"title":"ALLVB: All-in-One Long Video Understanding Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fang Liu, Xichen Tan, Yuanjing Luo, Yunfan Ye, Zhiping Cai","submitted_at":"2025-03-10T13:18:05Z","abstract_excerpt":"From image to video understanding, the capabilities of Multi-modal LLMs (MLLMs) are increasingly powerful. However, most existing video understanding benchmarks are relatively short, which makes them inadequate for effectively evaluating the long-sequence modeling capabilities of MLLMs. This highlights the urgent need for a comprehensive and integrated long video understanding benchmark to assess the ability of MLLMs thoroughly. To this end, we propose ALLVB (ALL-in-One Long Video Understanding Benchmark). ALLVB's main contributions include: 1) It integrates 9 major video understanding tasks. "},"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":"2503.07298","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T13:18:05Z","cross_cats_sorted":[],"title_canon_sha256":"1da1d43cbe1bba2905b49dceb6e560321b45df3f740219e4bb3b66206f3aa1f3","abstract_canon_sha256":"7425749e7b277bbbc4c64573b771b0db064c95c23abb251db500147472cb069b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:15.570235Z","signature_b64":"GeMHHwSQkNdVh1/usd3zdch0TgyY+/tpvcIs1BeA3U1h6OUJ1un5Ee/QY8QpHSTnwaKsJYDOpgFBIHijKThWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85e808c45598a07ed934e3829aed067c9a26e519173c91e3143bfc4de168e68f","last_reissued_at":"2026-07-05T10:42:15.569769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:15.569769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALLVB: All-in-One Long Video Understanding Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fang Liu, Xichen Tan, Yuanjing Luo, Yunfan Ye, Zhiping Cai","submitted_at":"2025-03-10T13:18:05Z","abstract_excerpt":"From image to video understanding, the capabilities of Multi-modal LLMs (MLLMs) are increasingly powerful. However, most existing video understanding benchmarks are relatively short, which makes them inadequate for effectively evaluating the long-sequence modeling capabilities of MLLMs. This highlights the urgent need for a comprehensive and integrated long video understanding benchmark to assess the ability of MLLMs thoroughly. To this end, we propose ALLVB (ALL-in-One Long Video Understanding Benchmark). ALLVB's main contributions include: 1) It integrates 9 major video understanding tasks. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07298","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/2503.07298/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":"2503.07298","created_at":"2026-07-05T10:42:15.569829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07298v2","created_at":"2026-07-05T10:42:15.569829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07298","created_at":"2026-07-05T10:42:15.569829+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXUARRCVTCQH","created_at":"2026-07-05T10:42:15.569829+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXUARRCVTCQH5WJU","created_at":"2026-07-05T10:42:15.569829+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXUARRCV","created_at":"2026-07-05T10:42:15.569829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QXUARRCVTCQH5WJU4OBJV3IGPS","json":"https://pith.science/pith/QXUARRCVTCQH5WJU4OBJV3IGPS.json","graph_json":"https://pith.science/api/pith-number/QXUARRCVTCQH5WJU4OBJV3IGPS/graph.json","events_json":"https://pith.science/api/pith-number/QXUARRCVTCQH5WJU4OBJV3IGPS/events.json","paper":"https://pith.science/paper/QXUARRCV"},"agent_actions":{"view_html":"https://pith.science/pith/QXUARRCVTCQH5WJU4OBJV3IGPS","download_json":"https://pith.science/pith/QXUARRCVTCQH5WJU4OBJV3IGPS.json","view_paper":"https://pith.science/paper/QXUARRCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07298&json=true","fetch_graph":"https://pith.science/api/pith-number/QXUARRCVTCQH5WJU4OBJV3IGPS/graph.json","fetch_events":"https://pith.science/api/pith-number/QXUARRCVTCQH5WJU4OBJV3IGPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXUARRCVTCQH5WJU4OBJV3IGPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXUARRCVTCQH5WJU4OBJV3IGPS/action/storage_attestation","attest_author":"https://pith.science/pith/QXUARRCVTCQH5WJU4OBJV3IGPS/action/author_attestation","sign_citation":"https://pith.science/pith/QXUARRCVTCQH5WJU4OBJV3IGPS/action/citation_signature","submit_replication":"https://pith.science/pith/QXUARRCVTCQH5WJU4OBJV3IGPS/action/replication_record"}},"created_at":"2026-07-05T10:42:15.569829+00:00","updated_at":"2026-07-05T10:42:15.569829+00:00"}