{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H6X6TFTAAPBDRUVJ5PDFJOOSAW","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":"2811450cc209310e20db7af4acaffdd6b713f0d88239ed18e644b313ca0adb6f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T18:58:54Z","title_canon_sha256":"e02869ecb1f52996a295bc2a647898b1b8c5669fdf0f981f4d94447220c89075"},"schema_version":"1.0","source":{"id":"2402.13250","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13250","created_at":"2026-07-05T08:19:58Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13250v6","created_at":"2026-07-05T08:19:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13250","created_at":"2026-07-05T08:19:58Z"},{"alias_kind":"pith_short_12","alias_value":"H6X6TFTAAPBD","created_at":"2026-07-05T08:19:58Z"},{"alias_kind":"pith_short_16","alias_value":"H6X6TFTAAPBDRUVJ","created_at":"2026-07-05T08:19:58Z"},{"alias_kind":"pith_short_8","alias_value":"H6X6TFTA","created_at":"2026-07-05T08:19:58Z"}],"graph_snapshots":[{"event_id":"sha256:27df5bbde72dcdebb873e7f5473d37181c59843711b1eb3ba6616237d5a60fff","target":"graph","created_at":"2026-07-05T08:19:58Z","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/2402.13250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most video captioning models are designed to process short video clips of few seconds and output text describing low-level visual concepts (e.g., objects, scenes, atomic actions). However, most real-world videos last for minutes or hours and have a complex hierarchical structure spanning different temporal granularities. We propose Video ReCap, a recursive video captioning model that can process video inputs of dramatically different lengths (from 1 second to 2 hours) and output video captions at multiple hierarchy levels. The recursive video-language architecture exploits the synergy between ","authors_text":"Gedas Bertasius, Lorenzo Torresani, Md Mohaiminul Islam, Ngan Ho, Tushar Nagarajan, Xitong Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T18:58:54Z","title":"Video ReCap: Recursive Captioning of Hour-Long Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13250","kind":"arxiv","version":6},"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":"sha256:25953eeaa41a43ca960b9fc6a156d685dfd8ead515fed1ae23b17277808d52a3","target":"record","created_at":"2026-07-05T08:19:58Z","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":"2811450cc209310e20db7af4acaffdd6b713f0d88239ed18e644b313ca0adb6f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T18:58:54Z","title_canon_sha256":"e02869ecb1f52996a295bc2a647898b1b8c5669fdf0f981f4d94447220c89075"},"schema_version":"1.0","source":{"id":"2402.13250","kind":"arxiv","version":6}},"canonical_sha256":"3fafe9966003c238d2a9ebc654b9d205916ee8025f595a44dcae3952f9dba532","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fafe9966003c238d2a9ebc654b9d205916ee8025f595a44dcae3952f9dba532","first_computed_at":"2026-07-05T08:19:58.104912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:58.104912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8oUFYscVZkhv90uvhX/u6YZKJ6tRhQmkEQU6Xgv7Q6h4HL8EDLYVsk++u3f+nJrCDqI4k/6lF1754LVdHmkUDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:58.105392Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13250","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25953eeaa41a43ca960b9fc6a156d685dfd8ead515fed1ae23b17277808d52a3","sha256:27df5bbde72dcdebb873e7f5473d37181c59843711b1eb3ba6616237d5a60fff"],"state_sha256":"d0f587d257a10562460e48b49121271134f2a4d26ee921ce5a8e76bc0afbfa2d"}