{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:X7DWTPN4PIVHXPH2V2PWDO7ZAP","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":"2b9690903cd2bfc3808eb9e5c4830caf5664e6cae43b75abb6302ed58e6545dd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-23T22:11:43Z","title_canon_sha256":"39aa9024e87a9625297697dfed1a1b039d2d767269e845e01246e20bc12d6b6d"},"schema_version":"1.0","source":{"id":"2203.12745","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.12745","created_at":"2026-07-05T04:08:43Z"},{"alias_kind":"arxiv_version","alias_value":"2203.12745v2","created_at":"2026-07-05T04:08:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12745","created_at":"2026-07-05T04:08:43Z"},{"alias_kind":"pith_short_12","alias_value":"X7DWTPN4PIVH","created_at":"2026-07-05T04:08:43Z"},{"alias_kind":"pith_short_16","alias_value":"X7DWTPN4PIVHXPH2","created_at":"2026-07-05T04:08:43Z"},{"alias_kind":"pith_short_8","alias_value":"X7DWTPN4","created_at":"2026-07-05T04:08:43Z"}],"graph_snapshots":[{"event_id":"sha256:5dd8a409fa5725043ae16e70c92ab8b33958ebd766f85d11b504b7741d6a7d4d","target":"graph","created_at":"2026-07-05T04:08:43Z","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/2203.12745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finding relevant moments and highlights in videos according to natural language queries is a natural and highly valuable common need in the current video content explosion era. Nevertheless, jointly conducting moment retrieval and highlight detection is an emerging research topic, even though its component problems and some related tasks have already been studied for a while. In this paper, we present the first unified framework, named Unified Multi-modal Transformers (UMT), capable of realizing such joint optimization while can also be easily degenerated for solving individual problems. As fa","authors_text":"Chang Wen Chen, Siyuan Li, Xiaohu Qie, Yang Wu, Ye Liu, Ying Shan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-23T22:11:43Z","title":"UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12745","kind":"arxiv","version":2},"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":"sha256:7ac8a69ce019a9b6fc20c7b39de13be3303208e91893897884adae31411260e5","target":"record","created_at":"2026-07-05T04:08:43Z","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":"2b9690903cd2bfc3808eb9e5c4830caf5664e6cae43b75abb6302ed58e6545dd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-23T22:11:43Z","title_canon_sha256":"39aa9024e87a9625297697dfed1a1b039d2d767269e845e01246e20bc12d6b6d"},"schema_version":"1.0","source":{"id":"2203.12745","kind":"arxiv","version":2}},"canonical_sha256":"bfc769bdbc7a2a7bbcfaae9f61bbf903efd36d7afeb824ad9bb5442fa8b2c6ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfc769bdbc7a2a7bbcfaae9f61bbf903efd36d7afeb824ad9bb5442fa8b2c6ff","first_computed_at":"2026-07-05T04:08:43.560142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:43.560142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HKCDws0tDv7e0gemqH6RiLe/E9b1GbbYHtdqPJ3bEXDISulok9B2WS/iENaHtdUQaJXoAT4hkoxAz3VI82s9BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:43.560593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.12745","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ac8a69ce019a9b6fc20c7b39de13be3303208e91893897884adae31411260e5","sha256:5dd8a409fa5725043ae16e70c92ab8b33958ebd766f85d11b504b7741d6a7d4d"],"state_sha256":"6df86796f9fd953058a7fba05b7add6b51da2224e6a7d9466e6ec727c2542707"}