{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ASHVMAQ32FJF7HCHTAPNBIQ7QY","short_pith_number":"pith:ASHVMAQ3","schema_version":"1.0","canonical_sha256":"048f56021bd1525f9c47981ed0a21f862474c5ebb8d9e96f3c04662ace1ce7c7","source":{"kind":"arxiv","id":"2309.17133","version":2},"attestation_state":"computed","paper":{"title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Alexandru Coca, Bill Byrne, Jingbiao Mei, Jinghong Chen, Weizhe Lin","submitted_at":"2023-09-29T10:54:10Z","abstract_excerpt":"Knowledge-based Visual Question Answering (KB-VQA) requires VQA systems to utilize knowledge from external knowledge bases to answer visually-grounded questions. Retrieval-Augmented Visual Question Answering (RA-VQA), a strong framework to tackle KB-VQA, first retrieves related documents with Dense Passage Retrieval (DPR) and then uses them to answer questions. This paper proposes Fine-grained Late-interaction Multi-modal Retrieval (FLMR) which significantly improves knowledge retrieval in RA-VQA. FLMR addresses two major limitations in RA-VQA's retriever: (1) the image representations obtaine"},"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":"2309.17133","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-29T10:54:10Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"05402d6c76f96fc55de50fef6fb3e9627de492f5ac8f4b073c43828d0d5bead0","abstract_canon_sha256":"3f9318232b8f6389036a992e56ffc23dd16706e909b236e0b2113727f51f3a99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:34.722044Z","signature_b64":"AhbrXluH55NjRrHKOphkJugcM3o9HG9YHdQzOSb/kc44ZahatUunlgLcbLdFdoZq8UBQqc2mz0CtLi9KhtDGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"048f56021bd1525f9c47981ed0a21f862474c5ebb8d9e96f3c04662ace1ce7c7","last_reissued_at":"2026-07-05T07:06:34.721593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:34.721593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Alexandru Coca, Bill Byrne, Jingbiao Mei, Jinghong Chen, Weizhe Lin","submitted_at":"2023-09-29T10:54:10Z","abstract_excerpt":"Knowledge-based Visual Question Answering (KB-VQA) requires VQA systems to utilize knowledge from external knowledge bases to answer visually-grounded questions. Retrieval-Augmented Visual Question Answering (RA-VQA), a strong framework to tackle KB-VQA, first retrieves related documents with Dense Passage Retrieval (DPR) and then uses them to answer questions. This paper proposes Fine-grained Late-interaction Multi-modal Retrieval (FLMR) which significantly improves knowledge retrieval in RA-VQA. FLMR addresses two major limitations in RA-VQA's retriever: (1) the image representations obtaine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17133","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/2309.17133/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":"2309.17133","created_at":"2026-07-05T07:06:34.721655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.17133v2","created_at":"2026-07-05T07:06:34.721655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17133","created_at":"2026-07-05T07:06:34.721655+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASHVMAQ32FJF","created_at":"2026-07-05T07:06:34.721655+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASHVMAQ32FJF7HCH","created_at":"2026-07-05T07:06:34.721655+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASHVMAQ3","created_at":"2026-07-05T07:06:34.721655+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/ASHVMAQ32FJF7HCHTAPNBIQ7QY","json":"https://pith.science/pith/ASHVMAQ32FJF7HCHTAPNBIQ7QY.json","graph_json":"https://pith.science/api/pith-number/ASHVMAQ32FJF7HCHTAPNBIQ7QY/graph.json","events_json":"https://pith.science/api/pith-number/ASHVMAQ32FJF7HCHTAPNBIQ7QY/events.json","paper":"https://pith.science/paper/ASHVMAQ3"},"agent_actions":{"view_html":"https://pith.science/pith/ASHVMAQ32FJF7HCHTAPNBIQ7QY","download_json":"https://pith.science/pith/ASHVMAQ32FJF7HCHTAPNBIQ7QY.json","view_paper":"https://pith.science/paper/ASHVMAQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.17133&json=true","fetch_graph":"https://pith.science/api/pith-number/ASHVMAQ32FJF7HCHTAPNBIQ7QY/graph.json","fetch_events":"https://pith.science/api/pith-number/ASHVMAQ32FJF7HCHTAPNBIQ7QY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASHVMAQ32FJF7HCHTAPNBIQ7QY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASHVMAQ32FJF7HCHTAPNBIQ7QY/action/storage_attestation","attest_author":"https://pith.science/pith/ASHVMAQ32FJF7HCHTAPNBIQ7QY/action/author_attestation","sign_citation":"https://pith.science/pith/ASHVMAQ32FJF7HCHTAPNBIQ7QY/action/citation_signature","submit_replication":"https://pith.science/pith/ASHVMAQ32FJF7HCHTAPNBIQ7QY/action/replication_record"}},"created_at":"2026-07-05T07:06:34.721655+00:00","updated_at":"2026-07-05T07:06:34.721655+00:00"}