{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RZMHCSDY2IMRL7TT4RJCDJMXQV","short_pith_number":"pith:RZMHCSDY","schema_version":"1.0","canonical_sha256":"8e58714878d21915fe73e45221a59785758e90079f1292470bf27467783cafa3","source":{"kind":"arxiv","id":"2503.05186","version":4},"attestation_state":"computed","paper":{"title":"Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chan Hur, Dabin Kang, Dong-Hun Lee, Hyeyoung Park, Jeong-hun Hong, Sang-hyo Park, Semin Myeong","submitted_at":"2025-03-07T07:15:06Z","abstract_excerpt":"In recent text-video retrieval, the use of additional captions from vision-language models has shown promising effects on the performance. However, existing models using additional captions often have struggled to capture the rich semantics, including temporal changes, inherent in the video. In addition, incorrect information caused by generative models can lead to inaccurate retrieval. To address these issues, we propose a new framework, Narrating the Video (NarVid), which strategically leverages the comprehensive information available from frame-level captions, the narration. The proposed Na"},"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":"2503.05186","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-07T07:15:06Z","cross_cats_sorted":[],"title_canon_sha256":"aefd73ae38081cd6d4a07986072a13327660e1db7a5d4e711437d0e200175b1c","abstract_canon_sha256":"760b4ede439046e644cc38990723334ff1dde3eb6c787adb653e5fca3182c3f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:26.738420Z","signature_b64":"Ft224iy2YOWJpm3Wrx4UKFc1d0eIh3hgn28CbJFA4xlGDaL1H2FMPEz5Ab+nJnh8Ao6C/OqPE5c7l7pBo5C7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e58714878d21915fe73e45221a59785758e90079f1292470bf27467783cafa3","last_reissued_at":"2026-07-05T10:39:26.738000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:26.738000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chan Hur, Dabin Kang, Dong-Hun Lee, Hyeyoung Park, Jeong-hun Hong, Sang-hyo Park, Semin Myeong","submitted_at":"2025-03-07T07:15:06Z","abstract_excerpt":"In recent text-video retrieval, the use of additional captions from vision-language models has shown promising effects on the performance. However, existing models using additional captions often have struggled to capture the rich semantics, including temporal changes, inherent in the video. In addition, incorrect information caused by generative models can lead to inaccurate retrieval. To address these issues, we propose a new framework, Narrating the Video (NarVid), which strategically leverages the comprehensive information available from frame-level captions, the narration. The proposed Na"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05186","kind":"arxiv","version":4},"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/2503.05186/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":"2503.05186","created_at":"2026-07-05T10:39:26.738059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.05186v4","created_at":"2026-07-05T10:39:26.738059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05186","created_at":"2026-07-05T10:39:26.738059+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZMHCSDY2IMR","created_at":"2026-07-05T10:39:26.738059+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZMHCSDY2IMRL7TT","created_at":"2026-07-05T10:39:26.738059+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZMHCSDY","created_at":"2026-07-05T10:39:26.738059+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/RZMHCSDY2IMRL7TT4RJCDJMXQV","json":"https://pith.science/pith/RZMHCSDY2IMRL7TT4RJCDJMXQV.json","graph_json":"https://pith.science/api/pith-number/RZMHCSDY2IMRL7TT4RJCDJMXQV/graph.json","events_json":"https://pith.science/api/pith-number/RZMHCSDY2IMRL7TT4RJCDJMXQV/events.json","paper":"https://pith.science/paper/RZMHCSDY"},"agent_actions":{"view_html":"https://pith.science/pith/RZMHCSDY2IMRL7TT4RJCDJMXQV","download_json":"https://pith.science/pith/RZMHCSDY2IMRL7TT4RJCDJMXQV.json","view_paper":"https://pith.science/paper/RZMHCSDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.05186&json=true","fetch_graph":"https://pith.science/api/pith-number/RZMHCSDY2IMRL7TT4RJCDJMXQV/graph.json","fetch_events":"https://pith.science/api/pith-number/RZMHCSDY2IMRL7TT4RJCDJMXQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZMHCSDY2IMRL7TT4RJCDJMXQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZMHCSDY2IMRL7TT4RJCDJMXQV/action/storage_attestation","attest_author":"https://pith.science/pith/RZMHCSDY2IMRL7TT4RJCDJMXQV/action/author_attestation","sign_citation":"https://pith.science/pith/RZMHCSDY2IMRL7TT4RJCDJMXQV/action/citation_signature","submit_replication":"https://pith.science/pith/RZMHCSDY2IMRL7TT4RJCDJMXQV/action/replication_record"}},"created_at":"2026-07-05T10:39:26.738059+00:00","updated_at":"2026-07-05T10:39:26.738059+00:00"}