{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DZBM52HBBKZSQIE5SPLMMRMWDC","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":"e6360c2bf01ddd506900d156de972db67bee5ae656b471216e5897b18270c29a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T06:43:06Z","title_canon_sha256":"8a30724bb9fd8547258fa6c6488c20ffb8c5c3df7a5ac32469e960d0312038a9"},"schema_version":"1.0","source":{"id":"2412.13543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13543","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13543v1","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13543","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"pith_short_12","alias_value":"DZBM52HBBKZS","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"pith_short_16","alias_value":"DZBM52HBBKZSQIE5","created_at":"2026-07-05T09:51:03Z"},{"alias_kind":"pith_short_8","alias_value":"DZBM52HB","created_at":"2026-07-05T09:51:03Z"}],"graph_snapshots":[{"event_id":"sha256:fd766551582b56905f828fe4bea9f7aeb651e02fbf00bbe63ba155b0340cc411","target":"graph","created_at":"2026-07-05T09:51:03Z","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/2412.13543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video has emerged as a favored multimedia format on the internet. To better gain video contents, a new topic HIREST is presented, including video retrieval, moment retrieval, moment segmentation, and step-captioning. The pioneering work chooses the pre-trained CLIP-based model for video retrieval, and leverages it as a feature extractor for other three challenging tasks solved in a multi-task learning paradigm. Nevertheless, this work struggles to learn the comprehensive cognition of user-preferred content, due to disregarding the hierarchies and association relations across modalities. In thi","authors_text":"Liang Li, Li Su, Qingming Huang, Yunbin Tu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T06:43:06Z","title":"Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13543","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":"sha256:37acb0dfd9caed4d1f6333d7274ebbe5205deaa7209fc8a8d56d94e67c2b6ce5","target":"record","created_at":"2026-07-05T09:51:03Z","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":"e6360c2bf01ddd506900d156de972db67bee5ae656b471216e5897b18270c29a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T06:43:06Z","title_canon_sha256":"8a30724bb9fd8547258fa6c6488c20ffb8c5c3df7a5ac32469e960d0312038a9"},"schema_version":"1.0","source":{"id":"2412.13543","kind":"arxiv","version":1}},"canonical_sha256":"1e42cee8e10ab328209d93d6c645961897dd33b84b108bfe5d5d6b55f96cd8e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e42cee8e10ab328209d93d6c645961897dd33b84b108bfe5d5d6b55f96cd8e2","first_computed_at":"2026-07-05T09:51:03.663831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:03.663831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D+44xFcnvC8cOedAqaMNXFDRCCQZRcI7/GyeJasrK23Y/JGHxxjqVCWd93yPz/i4TYBSfkQv5QykI9QJoO/NAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:03.664449Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37acb0dfd9caed4d1f6333d7274ebbe5205deaa7209fc8a8d56d94e67c2b6ce5","sha256:fd766551582b56905f828fe4bea9f7aeb651e02fbf00bbe63ba155b0340cc411"],"state_sha256":"b48ae8a5be6a76aabe6ae7b758712cb894498441852978167eab01d9c0944fd1"}