{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P4QSTNRIVE57YYMZ3TKZSDWVYU","short_pith_number":"pith:P4QSTNRI","schema_version":"1.0","canonical_sha256":"7f2129b628a93bfc6199dcd5990ed5c514100d283af03d39dec87baa8dc86b36","source":{"kind":"arxiv","id":"2508.17442","version":1},"attestation_state":"computed","paper":{"title":"Multi-Level LVLM Guidance for Untrimmed Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liyang Peng, Sihan Zhu, Yunjie Guo","submitted_at":"2025-08-24T16:45:21Z","abstract_excerpt":"Action recognition and localization in complex, untrimmed videos remain a formidable challenge in computer vision, largely due to the limitations of existing methods in capturing fine-grained actions, long-term temporal dependencies, and high-level semantic information from low-level visual features. This paper introduces the Event-Contextualized Video Transformer (ECVT), a novel architecture that leverages the advanced semantic understanding capabilities of Large Vision-Language Models (LVLMs) to bridge this gap. ECVT employs a dual-branch design, comprising a Video Encoding Branch for spatio"},"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":"2508.17442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-24T16:45:21Z","cross_cats_sorted":[],"title_canon_sha256":"b43ca6ca4b8120486f17f4b974c14fe0ea2b97c6c25d6b3b7e2f78b749874f73","abstract_canon_sha256":"fa032e42385f989e21450bcba9263ce5d0712022339039970a04bbedff5684b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:41.498745Z","signature_b64":"pV9epUQvqHTNOIk5Fm5hZUrEadMTIRXFSW/kBkmOrL5twW7msISvx9ZIBcxZyqRcj0dmvDfplIeQA50n+vgCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f2129b628a93bfc6199dcd5990ed5c514100d283af03d39dec87baa8dc86b36","last_reissued_at":"2026-07-05T11:58:41.498309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:41.498309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Level LVLM Guidance for Untrimmed Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liyang Peng, Sihan Zhu, Yunjie Guo","submitted_at":"2025-08-24T16:45:21Z","abstract_excerpt":"Action recognition and localization in complex, untrimmed videos remain a formidable challenge in computer vision, largely due to the limitations of existing methods in capturing fine-grained actions, long-term temporal dependencies, and high-level semantic information from low-level visual features. This paper introduces the Event-Contextualized Video Transformer (ECVT), a novel architecture that leverages the advanced semantic understanding capabilities of Large Vision-Language Models (LVLMs) to bridge this gap. ECVT employs a dual-branch design, comprising a Video Encoding Branch for spatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17442","kind":"arxiv","version":1},"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/2508.17442/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":"2508.17442","created_at":"2026-07-05T11:58:41.498381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.17442v1","created_at":"2026-07-05T11:58:41.498381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17442","created_at":"2026-07-05T11:58:41.498381+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4QSTNRIVE57","created_at":"2026-07-05T11:58:41.498381+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4QSTNRIVE57YYMZ","created_at":"2026-07-05T11:58:41.498381+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4QSTNRI","created_at":"2026-07-05T11:58:41.498381+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/P4QSTNRIVE57YYMZ3TKZSDWVYU","json":"https://pith.science/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU.json","graph_json":"https://pith.science/api/pith-number/P4QSTNRIVE57YYMZ3TKZSDWVYU/graph.json","events_json":"https://pith.science/api/pith-number/P4QSTNRIVE57YYMZ3TKZSDWVYU/events.json","paper":"https://pith.science/paper/P4QSTNRI"},"agent_actions":{"view_html":"https://pith.science/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU","download_json":"https://pith.science/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU.json","view_paper":"https://pith.science/paper/P4QSTNRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.17442&json=true","fetch_graph":"https://pith.science/api/pith-number/P4QSTNRIVE57YYMZ3TKZSDWVYU/graph.json","fetch_events":"https://pith.science/api/pith-number/P4QSTNRIVE57YYMZ3TKZSDWVYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU/action/storage_attestation","attest_author":"https://pith.science/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU/action/author_attestation","sign_citation":"https://pith.science/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU/action/citation_signature","submit_replication":"https://pith.science/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU/action/replication_record"}},"created_at":"2026-07-05T11:58:41.498381+00:00","updated_at":"2026-07-05T11:58:41.498381+00:00"}