{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:32R6UWOWKBTTGFNXDYUPZLAW3P","short_pith_number":"pith:32R6UWOW","schema_version":"1.0","canonical_sha256":"dea3ea59d650673315b71e28fcac16dbfcf68e815d4500e2033e5574e451c766","source":{"kind":"arxiv","id":"2503.19009","version":1},"attestation_state":"computed","paper":{"title":"Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Alexander Martin, Andrew Yates, Arun Reddy, Benjamin Van Durme, Celso M. de Melo, Eugene Yang, Kate Sanders, Kenton Murray, Rama Chellappa, Reno Kriz","submitted_at":"2025-03-24T17:51:29Z","abstract_excerpt":"In this work, we tackle the problem of text-to-video retrieval (T2VR). Inspired by the success of late interaction techniques in text-document, text-image, and text-video retrieval, our approach, Video-ColBERT, introduces a simple and efficient mechanism for fine-grained similarity assessment between queries and videos. Video-ColBERT is built upon 3 main components: a fine-grained spatial and temporal token-wise interaction, query and visual expansions, and a dual sigmoid loss during training. We find that this interaction and training paradigm leads to strong individual, yet compatible, repre"},"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":"2503.19009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T17:51:29Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"6dcf8f75338a6107ef47769f47259a779cc8e0f853641a376fc588a3c1f4d36e","abstract_canon_sha256":"d2fa05555a734f9b8f008c7b1e6318aab1f5ab4cde855f5394a66dae202d14ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:42.459874Z","signature_b64":"P/K/OAhtivpPFZlKr0Sw9aUI1vAxzfqHnkFHPbBMPZdGRrFvbdv2znXaWd+6eUYsnSiFZ7Uc2Qy5cAoYWTE/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dea3ea59d650673315b71e28fcac16dbfcf68e815d4500e2033e5574e451c766","last_reissued_at":"2026-07-05T11:18:42.459452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:42.459452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Alexander Martin, Andrew Yates, Arun Reddy, Benjamin Van Durme, Celso M. de Melo, Eugene Yang, Kate Sanders, Kenton Murray, Rama Chellappa, Reno Kriz","submitted_at":"2025-03-24T17:51:29Z","abstract_excerpt":"In this work, we tackle the problem of text-to-video retrieval (T2VR). Inspired by the success of late interaction techniques in text-document, text-image, and text-video retrieval, our approach, Video-ColBERT, introduces a simple and efficient mechanism for fine-grained similarity assessment between queries and videos. Video-ColBERT is built upon 3 main components: a fine-grained spatial and temporal token-wise interaction, query and visual expansions, and a dual sigmoid loss during training. We find that this interaction and training paradigm leads to strong individual, yet compatible, repre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19009","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/2503.19009/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":"2503.19009","created_at":"2026-07-05T11:18:42.459505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19009v1","created_at":"2026-07-05T11:18:42.459505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19009","created_at":"2026-07-05T11:18:42.459505+00:00"},{"alias_kind":"pith_short_12","alias_value":"32R6UWOWKBTT","created_at":"2026-07-05T11:18:42.459505+00:00"},{"alias_kind":"pith_short_16","alias_value":"32R6UWOWKBTTGFNX","created_at":"2026-07-05T11:18:42.459505+00:00"},{"alias_kind":"pith_short_8","alias_value":"32R6UWOW","created_at":"2026-07-05T11:18:42.459505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.08819","citing_title":"Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32R6UWOWKBTTGFNXDYUPZLAW3P","json":"https://pith.science/pith/32R6UWOWKBTTGFNXDYUPZLAW3P.json","graph_json":"https://pith.science/api/pith-number/32R6UWOWKBTTGFNXDYUPZLAW3P/graph.json","events_json":"https://pith.science/api/pith-number/32R6UWOWKBTTGFNXDYUPZLAW3P/events.json","paper":"https://pith.science/paper/32R6UWOW"},"agent_actions":{"view_html":"https://pith.science/pith/32R6UWOWKBTTGFNXDYUPZLAW3P","download_json":"https://pith.science/pith/32R6UWOWKBTTGFNXDYUPZLAW3P.json","view_paper":"https://pith.science/paper/32R6UWOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19009&json=true","fetch_graph":"https://pith.science/api/pith-number/32R6UWOWKBTTGFNXDYUPZLAW3P/graph.json","fetch_events":"https://pith.science/api/pith-number/32R6UWOWKBTTGFNXDYUPZLAW3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32R6UWOWKBTTGFNXDYUPZLAW3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32R6UWOWKBTTGFNXDYUPZLAW3P/action/storage_attestation","attest_author":"https://pith.science/pith/32R6UWOWKBTTGFNXDYUPZLAW3P/action/author_attestation","sign_citation":"https://pith.science/pith/32R6UWOWKBTTGFNXDYUPZLAW3P/action/citation_signature","submit_replication":"https://pith.science/pith/32R6UWOWKBTTGFNXDYUPZLAW3P/action/replication_record"}},"created_at":"2026-07-05T11:18:42.459505+00:00","updated_at":"2026-07-05T11:18:42.459505+00:00"}