{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:P6D44QBJHXRPYU4NXEW7PQPCJZ","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":"f1e16129b2ce19eee1825be8e40d1d039001b73d8da85514a4e23a212a1dcf22","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:59:45Z","title_canon_sha256":"3592a1a7c5c5fa9cd1e660880d8bca590b4bb2f6749056d5878d61aee4084f48"},"schema_version":"1.0","source":{"id":"2312.00115","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.00115","created_at":"2026-07-05T09:46:43Z"},{"alias_kind":"arxiv_version","alias_value":"2312.00115v2","created_at":"2026-07-05T09:46:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00115","created_at":"2026-07-05T09:46:43Z"},{"alias_kind":"pith_short_12","alias_value":"P6D44QBJHXRP","created_at":"2026-07-05T09:46:43Z"},{"alias_kind":"pith_short_16","alias_value":"P6D44QBJHXRPYU4N","created_at":"2026-07-05T09:46:43Z"},{"alias_kind":"pith_short_8","alias_value":"P6D44QBJ","created_at":"2026-07-05T09:46:43Z"}],"graph_snapshots":[{"event_id":"sha256:b0529147c648e3cde106699793d4a802a52f7c8df2548b3a132ba1e590a3d620","target":"graph","created_at":"2026-07-05T09:46:43Z","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/2312.00115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing long video retrieval systems are trained and tested in the paragraph-to-video retrieval regime, where every long video is described by a single long paragraph. This neglects the richness and variety of possible valid descriptions of a video, which could range anywhere from moment-by-moment detail to a single phrase summary. To provide a more thorough evaluation of the capabilities of long video retrieval systems, we propose a pipeline that leverages state-of-the-art large language models to carefully generate a diverse set of synthetic captions for long videos. We validate this pipeli","authors_text":"Abhinav Shrivastava, Ajay Divakaran, Karan Sikka, Matthew Gwilliam, Meng Ye, Michael Cogswell","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:59:45Z","title":"A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00115","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":"sha256:8c4c7b85066c200bf4d934e9019516320c812fbbc452ae6368b02d0409079cf2","target":"record","created_at":"2026-07-05T09:46:43Z","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":"f1e16129b2ce19eee1825be8e40d1d039001b73d8da85514a4e23a212a1dcf22","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:59:45Z","title_canon_sha256":"3592a1a7c5c5fa9cd1e660880d8bca590b4bb2f6749056d5878d61aee4084f48"},"schema_version":"1.0","source":{"id":"2312.00115","kind":"arxiv","version":2}},"canonical_sha256":"7f87ce40293de2fc538db92df7c1e24e5665310106ae80850162be066be2a760","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f87ce40293de2fc538db92df7c1e24e5665310106ae80850162be066be2a760","first_computed_at":"2026-07-05T09:46:43.760822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:43.760822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zwi6W/Wk0/TcGI2ULlf97ZJgWkNff6L1s8S7ughrhGraa37lKEP0apjWB1U22memsX2jR6jIZcfK3m+tZfn8Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:43.761283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.00115","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c4c7b85066c200bf4d934e9019516320c812fbbc452ae6368b02d0409079cf2","sha256:b0529147c648e3cde106699793d4a802a52f7c8df2548b3a132ba1e590a3d620"],"state_sha256":"bdabe4881d901c442dcfd913a1eeffaaafb9f569288aec869909417b60a2f860"}