{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P6D44QBJHXRPYU4NXEW7PQPCJZ","short_pith_number":"pith:P6D44QBJ","schema_version":"1.0","canonical_sha256":"7f87ce40293de2fc538db92df7c1e24e5665310106ae80850162be066be2a760","source":{"kind":"arxiv","id":"2312.00115","version":2},"attestation_state":"computed","paper":{"title":"A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Ajay Divakaran, Karan Sikka, Matthew Gwilliam, Meng Ye, Michael Cogswell","submitted_at":"2023-11-30T18:59:45Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.00115","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:59:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3592a1a7c5c5fa9cd1e660880d8bca590b4bb2f6749056d5878d61aee4084f48","abstract_canon_sha256":"f1e16129b2ce19eee1825be8e40d1d039001b73d8da85514a4e23a212a1dcf22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:43.761283Z","signature_b64":"Zwi6W/Wk0/TcGI2ULlf97ZJgWkNff6L1s8S7ughrhGraa37lKEP0apjWB1U22memsX2jR6jIZcfK3m+tZfn8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f87ce40293de2fc538db92df7c1e24e5665310106ae80850162be066be2a760","last_reissued_at":"2026-07-05T09:46:43.760822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:43.760822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Ajay Divakaran, Karan Sikka, Matthew Gwilliam, Meng Ye, Michael Cogswell","submitted_at":"2023-11-30T18:59:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00115","kind":"arxiv","version":2},"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/2312.00115/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.00115","created_at":"2026-07-05T09:46:43.760883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.00115v2","created_at":"2026-07-05T09:46:43.760883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00115","created_at":"2026-07-05T09:46:43.760883+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6D44QBJHXRP","created_at":"2026-07-05T09:46:43.760883+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6D44QBJHXRPYU4N","created_at":"2026-07-05T09:46:43.760883+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6D44QBJ","created_at":"2026-07-05T09:46:43.760883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6D44QBJHXRPYU4NXEW7PQPCJZ","json":"https://pith.science/pith/P6D44QBJHXRPYU4NXEW7PQPCJZ.json","graph_json":"https://pith.science/api/pith-number/P6D44QBJHXRPYU4NXEW7PQPCJZ/graph.json","events_json":"https://pith.science/api/pith-number/P6D44QBJHXRPYU4NXEW7PQPCJZ/events.json","paper":"https://pith.science/paper/P6D44QBJ"},"agent_actions":{"view_html":"https://pith.science/pith/P6D44QBJHXRPYU4NXEW7PQPCJZ","download_json":"https://pith.science/pith/P6D44QBJHXRPYU4NXEW7PQPCJZ.json","view_paper":"https://pith.science/paper/P6D44QBJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.00115&json=true","fetch_graph":"https://pith.science/api/pith-number/P6D44QBJHXRPYU4NXEW7PQPCJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/P6D44QBJHXRPYU4NXEW7PQPCJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6D44QBJHXRPYU4NXEW7PQPCJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6D44QBJHXRPYU4NXEW7PQPCJZ/action/storage_attestation","attest_author":"https://pith.science/pith/P6D44QBJHXRPYU4NXEW7PQPCJZ/action/author_attestation","sign_citation":"https://pith.science/pith/P6D44QBJHXRPYU4NXEW7PQPCJZ/action/citation_signature","submit_replication":"https://pith.science/pith/P6D44QBJHXRPYU4NXEW7PQPCJZ/action/replication_record"}},"created_at":"2026-07-05T09:46:43.760883+00:00","updated_at":"2026-07-05T09:46:43.760883+00:00"}