{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:P4QSTNRIVE57YYMZ3TKZSDWVYU","short_pith_number":"pith:P4QSTNRI","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"},"canonical_sha256":"7f2129b628a93bfc6199dcd5990ed5c514100d283af03d39dec87baa8dc86b36","source":{"kind":"arxiv","id":"2508.17442","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:P4QSTNRIVE57YYMZ3TKZSDWVYU","target":"record","payload":{"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"},"canonical_sha256":"7f2129b628a93bfc6199dcd5990ed5c514100d283af03d39dec87baa8dc86b36","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"},"source_kind":"arxiv","source_id":"2508.17442","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:58:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4LXiVVw/7DaFOZyyfDgqN0Im219kuwxdoGJ6xJ7jC+bRcx7wrfTAkrAFFbydjSrh+zMx60T44Q2fueI/mT4wDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:59:29.427146Z"},"content_sha256":"6b962d54bbe9150603bd418f1b89944cd490dd22c7cc0f6cda48edd6df17a064","schema_version":"1.0","event_id":"sha256:6b962d54bbe9150603bd418f1b89944cd490dd22c7cc0f6cda48edd6df17a064"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:P4QSTNRIVE57YYMZ3TKZSDWVYU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:58:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"weZCTNCVhpPHyczA3F9L/aRWFvv9JdZodJVUbdUMcvmM1wmWldHkzZCYJoM1gxaS/uhd+HT28CUW02xPAdslDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:59:29.428070Z"},"content_sha256":"57a348336660027778e1ddbd7773f6ca0e6548c49e6f5ba3e812318fbac312b5","schema_version":"1.0","event_id":"sha256:57a348336660027778e1ddbd7773f6ca0e6548c49e6f5ba3e812318fbac312b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU/bundle.json","state_url":"https://pith.science/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T15:59:29Z","links":{"resolver":"https://pith.science/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU","bundle":"https://pith.science/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU/bundle.json","state":"https://pith.science/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P4QSTNRIVE57YYMZ3TKZSDWVYU/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wDTE65gkTQm07/G8VdiluXSnY1dQFq0ICg1eKSA6AXk4vYVdL7a38WnrT74aZM5m0DpKwgmSr1rI6VveMYLECA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:59:29.449041Z","bundle_sha256":"6dfbb5e7f8ab7ecbae71e011c3071685ba3f707cf432927b974645b7d88e4abc"}}