{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RXJCXQ7VPLZEB42ZEBXHIYI37N","short_pith_number":"pith:RXJCXQ7V","schema_version":"1.0","canonical_sha256":"8dd22bc3f57af240f359206e74611bfb7e888d37e10dd6c30fd18e96e5688c7a","source":{"kind":"arxiv","id":"2410.08593","version":1},"attestation_state":"computed","paper":{"title":"VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Huang, Hong Chen, Houlun Chen, Jia Jia, Wei Feng, Wenwu Zhu, Xin Wang, Zeyang Zhang","submitted_at":"2024-10-11T07:42:36Z","abstract_excerpt":"Existing Video Corpus Moment Retrieval (VCMR) is limited to coarse-grained understanding, which hinders precise video moment localization when given fine-grained queries. In this paper, we propose a more challenging fine-grained VCMR benchmark requiring methods to localize the best-matched moment from the corpus with other partially matched candidates. To improve the dataset construction efficiency and guarantee high-quality data annotations, we propose VERIFIED, an automatic \\underline{V}id\\underline{E}o-text annotation pipeline to generate captions with \\underline{R}el\\underline{I}able \\unde"},"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":"2410.08593","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-11T07:42:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9f9d347eb9c4e62e061f5812d6ca9f667fbc9b930bd499a22a3803062098f206","abstract_canon_sha256":"f742f4484d42d25f8b414f14c9af8f65888f0e37206599e0d5de8ded9c19e7ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:14.760217Z","signature_b64":"zOUvatQYtyaDkUs3Qo7AgLdG/O5VAsOTavyb8ZeyquUPfHxvc/vlb4O7/pua8TrSPIWASEYXiWwqPJK5mM5+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dd22bc3f57af240f359206e74611bfb7e888d37e10dd6c30fd18e96e5688c7a","last_reissued_at":"2026-07-05T09:19:14.759725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:14.759725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Huang, Hong Chen, Houlun Chen, Jia Jia, Wei Feng, Wenwu Zhu, Xin Wang, Zeyang Zhang","submitted_at":"2024-10-11T07:42:36Z","abstract_excerpt":"Existing Video Corpus Moment Retrieval (VCMR) is limited to coarse-grained understanding, which hinders precise video moment localization when given fine-grained queries. In this paper, we propose a more challenging fine-grained VCMR benchmark requiring methods to localize the best-matched moment from the corpus with other partially matched candidates. To improve the dataset construction efficiency and guarantee high-quality data annotations, we propose VERIFIED, an automatic \\underline{V}id\\underline{E}o-text annotation pipeline to generate captions with \\underline{R}el\\underline{I}able \\unde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08593","kind":"arxiv","version":1},"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/2410.08593/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":"2410.08593","created_at":"2026-07-05T09:19:14.759786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08593v1","created_at":"2026-07-05T09:19:14.759786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08593","created_at":"2026-07-05T09:19:14.759786+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXJCXQ7VPLZE","created_at":"2026-07-05T09:19:14.759786+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXJCXQ7VPLZEB42Z","created_at":"2026-07-05T09:19:14.759786+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXJCXQ7V","created_at":"2026-07-05T09:19:14.759786+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10922","citing_title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","ref_index":96,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXJCXQ7VPLZEB42ZEBXHIYI37N","json":"https://pith.science/pith/RXJCXQ7VPLZEB42ZEBXHIYI37N.json","graph_json":"https://pith.science/api/pith-number/RXJCXQ7VPLZEB42ZEBXHIYI37N/graph.json","events_json":"https://pith.science/api/pith-number/RXJCXQ7VPLZEB42ZEBXHIYI37N/events.json","paper":"https://pith.science/paper/RXJCXQ7V"},"agent_actions":{"view_html":"https://pith.science/pith/RXJCXQ7VPLZEB42ZEBXHIYI37N","download_json":"https://pith.science/pith/RXJCXQ7VPLZEB42ZEBXHIYI37N.json","view_paper":"https://pith.science/paper/RXJCXQ7V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08593&json=true","fetch_graph":"https://pith.science/api/pith-number/RXJCXQ7VPLZEB42ZEBXHIYI37N/graph.json","fetch_events":"https://pith.science/api/pith-number/RXJCXQ7VPLZEB42ZEBXHIYI37N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXJCXQ7VPLZEB42ZEBXHIYI37N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXJCXQ7VPLZEB42ZEBXHIYI37N/action/storage_attestation","attest_author":"https://pith.science/pith/RXJCXQ7VPLZEB42ZEBXHIYI37N/action/author_attestation","sign_citation":"https://pith.science/pith/RXJCXQ7VPLZEB42ZEBXHIYI37N/action/citation_signature","submit_replication":"https://pith.science/pith/RXJCXQ7VPLZEB42ZEBXHIYI37N/action/replication_record"}},"created_at":"2026-07-05T09:19:14.759786+00:00","updated_at":"2026-07-05T09:19:14.759786+00:00"}