{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6BEXOVSC6ZTTAEFQBUMQB52F64","short_pith_number":"pith:6BEXOVSC","schema_version":"1.0","canonical_sha256":"f049775642f6673010b00d1900f745f701c988203818b3a7c1fb4fde3a3877d0","source":{"kind":"arxiv","id":"2407.12277","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Reranking for Knowledge-Intensive Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Hauptmann, Hamed Zamani, Haoyang Wen, Honglei Zhuang, Michael Bendersky","submitted_at":"2024-07-17T02:58:52Z","abstract_excerpt":"Knowledge-intensive visual question answering requires models to effectively use external knowledge to help answer visual questions. A typical pipeline includes a knowledge retriever and an answer generator. However, a retriever that utilizes local information, such as an image patch, may not provide reliable question-candidate relevance scores. Besides, the two-tower architecture also limits the relevance score modeling of a retriever to select top candidates for answer generator reasoning. In this paper, we introduce an additional module, a multi-modal reranker, to improve the ranking qualit"},"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":"2407.12277","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T02:58:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c60e4fb1f7749cdc98180f03331f6190e202129b325cea542d7a85955a34b90","abstract_canon_sha256":"0839c85869fda719d3f7ad5804a2242ce38d967b2be14397343339f953a5a5ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:02.414201Z","signature_b64":"Ox2P56PpBbLTWHvoPJR2kUYuQmWXX+DifAAUgsZ0DOwwvg7NBOnS/ySsa4Mf4gJ5HDYPKGSMHWNTdSmTx0ztCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f049775642f6673010b00d1900f745f701c988203818b3a7c1fb4fde3a3877d0","last_reissued_at":"2026-07-05T08:45:02.413789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:02.413789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Reranking for Knowledge-Intensive Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Hauptmann, Hamed Zamani, Haoyang Wen, Honglei Zhuang, Michael Bendersky","submitted_at":"2024-07-17T02:58:52Z","abstract_excerpt":"Knowledge-intensive visual question answering requires models to effectively use external knowledge to help answer visual questions. A typical pipeline includes a knowledge retriever and an answer generator. However, a retriever that utilizes local information, such as an image patch, may not provide reliable question-candidate relevance scores. Besides, the two-tower architecture also limits the relevance score modeling of a retriever to select top candidates for answer generator reasoning. In this paper, we introduce an additional module, a multi-modal reranker, to improve the ranking qualit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12277","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/2407.12277/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":"2407.12277","created_at":"2026-07-05T08:45:02.413847+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12277v1","created_at":"2026-07-05T08:45:02.413847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12277","created_at":"2026-07-05T08:45:02.413847+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BEXOVSC6ZTT","created_at":"2026-07-05T08:45:02.413847+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BEXOVSC6ZTTAEFQ","created_at":"2026-07-05T08:45:02.413847+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BEXOVSC","created_at":"2026-07-05T08:45:02.413847+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/6BEXOVSC6ZTTAEFQBUMQB52F64","json":"https://pith.science/pith/6BEXOVSC6ZTTAEFQBUMQB52F64.json","graph_json":"https://pith.science/api/pith-number/6BEXOVSC6ZTTAEFQBUMQB52F64/graph.json","events_json":"https://pith.science/api/pith-number/6BEXOVSC6ZTTAEFQBUMQB52F64/events.json","paper":"https://pith.science/paper/6BEXOVSC"},"agent_actions":{"view_html":"https://pith.science/pith/6BEXOVSC6ZTTAEFQBUMQB52F64","download_json":"https://pith.science/pith/6BEXOVSC6ZTTAEFQBUMQB52F64.json","view_paper":"https://pith.science/paper/6BEXOVSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12277&json=true","fetch_graph":"https://pith.science/api/pith-number/6BEXOVSC6ZTTAEFQBUMQB52F64/graph.json","fetch_events":"https://pith.science/api/pith-number/6BEXOVSC6ZTTAEFQBUMQB52F64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BEXOVSC6ZTTAEFQBUMQB52F64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BEXOVSC6ZTTAEFQBUMQB52F64/action/storage_attestation","attest_author":"https://pith.science/pith/6BEXOVSC6ZTTAEFQBUMQB52F64/action/author_attestation","sign_citation":"https://pith.science/pith/6BEXOVSC6ZTTAEFQBUMQB52F64/action/citation_signature","submit_replication":"https://pith.science/pith/6BEXOVSC6ZTTAEFQBUMQB52F64/action/replication_record"}},"created_at":"2026-07-05T08:45:02.413847+00:00","updated_at":"2026-07-05T08:45:02.413847+00:00"}