{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P4QSTNRIVE57YYMZ3TKZSDWVYU","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":"fa032e42385f989e21450bcba9263ce5d0712022339039970a04bbedff5684b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-24T16:45:21Z","title_canon_sha256":"b43ca6ca4b8120486f17f4b974c14fe0ea2b97c6c25d6b3b7e2f78b749874f73"},"schema_version":"1.0","source":{"id":"2508.17442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17442","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17442v1","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17442","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_12","alias_value":"P4QSTNRIVE57","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_16","alias_value":"P4QSTNRIVE57YYMZ","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_8","alias_value":"P4QSTNRI","created_at":"2026-07-05T11:58:41Z"}],"graph_snapshots":[{"event_id":"sha256:57a348336660027778e1ddbd7773f6ca0e6548c49e6f5ba3e812318fbac312b5","target":"graph","created_at":"2026-07-05T11:58:41Z","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/2508.17442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Liyang Peng, Sihan Zhu, Yunjie Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-24T16:45:21Z","title":"Multi-Level LVLM Guidance for Untrimmed Video Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17442","kind":"arxiv","version":1},"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":"sha256:6b962d54bbe9150603bd418f1b89944cd490dd22c7cc0f6cda48edd6df17a064","target":"record","created_at":"2026-07-05T11:58:41Z","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":"fa032e42385f989e21450bcba9263ce5d0712022339039970a04bbedff5684b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-24T16:45:21Z","title_canon_sha256":"b43ca6ca4b8120486f17f4b974c14fe0ea2b97c6c25d6b3b7e2f78b749874f73"},"schema_version":"1.0","source":{"id":"2508.17442","kind":"arxiv","version":1}},"canonical_sha256":"7f2129b628a93bfc6199dcd5990ed5c514100d283af03d39dec87baa8dc86b36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f2129b628a93bfc6199dcd5990ed5c514100d283af03d39dec87baa8dc86b36","first_computed_at":"2026-07-05T11:58:41.498309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:41.498309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pV9epUQvqHTNOIk5Fm5hZUrEadMTIRXFSW/kBkmOrL5twW7msISvx9ZIBcxZyqRcj0dmvDfplIeQA50n+vgCBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:41.498745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.17442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b962d54bbe9150603bd418f1b89944cd490dd22c7cc0f6cda48edd6df17a064","sha256:57a348336660027778e1ddbd7773f6ca0e6548c49e6f5ba3e812318fbac312b5"],"state_sha256":"966aec8e046e710fe8c65b7e938372f654bd6a16786ef751f23c06e183b9804b"}