{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GYVTSY2KUUHERKLKOXMLMSLPQL","short_pith_number":"pith:GYVTSY2K","schema_version":"1.0","canonical_sha256":"362b39634aa50e48a96a75d8b6496f82c535eeeb6cb7f2fbe66f345699e2e9b2","source":{"kind":"arxiv","id":"2303.01903","version":4},"attestation_state":"computed","paper":{"title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jun Yu, Meng Wang, Xuecheng Ouyang, Zhenwei Shao, Zhou Yu","submitted_at":"2023-03-03T13:05:15Z","abstract_excerpt":"Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question. Early studies retrieve required knowledge from explicit knowledge bases (KBs), which often introduces irrelevant information to the question, hence restricting the performance of their models. Recent works have resorted to using a powerful large language model (LLM) as an implicit knowledge engine to acquire the necessary knowledge for answering. Despite the encouraging results achieved by these methods, we argue that they have not fully activated the capacity of the \\emph{blind"},"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":"2303.01903","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-03T13:05:15Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"0c2438128dc953719105dad529b97086a7ec38cd3aa0803916a6c0144046e1d8","abstract_canon_sha256":"e50ec65d96381ea55a83dab42cd62205a82345d5fb302db407171e20150abf94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:16.066364Z","signature_b64":"r1lzT/cdyqnrFZP4Qg4x3jLXzL+YWp1hqp4mOdXzKy4tHEeDJwTN1g6uiENLlDtFS5RnmFODydlF2eUJ1SDKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"362b39634aa50e48a96a75d8b6496f82c535eeeb6cb7f2fbe66f345699e2e9b2","last_reissued_at":"2026-07-05T10:55:16.065949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:16.065949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jun Yu, Meng Wang, Xuecheng Ouyang, Zhenwei Shao, Zhou Yu","submitted_at":"2023-03-03T13:05:15Z","abstract_excerpt":"Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question. Early studies retrieve required knowledge from explicit knowledge bases (KBs), which often introduces irrelevant information to the question, hence restricting the performance of their models. Recent works have resorted to using a powerful large language model (LLM) as an implicit knowledge engine to acquire the necessary knowledge for answering. Despite the encouraging results achieved by these methods, we argue that they have not fully activated the capacity of the \\emph{blind"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01903","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/2303.01903/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":"2303.01903","created_at":"2026-07-05T10:55:16.066011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.01903v4","created_at":"2026-07-05T10:55:16.066011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01903","created_at":"2026-07-05T10:55:16.066011+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYVTSY2KUUHE","created_at":"2026-07-05T10:55:16.066011+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYVTSY2KUUHERKLK","created_at":"2026-07-05T10:55:16.066011+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYVTSY2K","created_at":"2026-07-05T10:55:16.066011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16300","citing_title":"Large Models in Dialogue for Active Perception and Anomaly Detection","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYVTSY2KUUHERKLKOXMLMSLPQL","json":"https://pith.science/pith/GYVTSY2KUUHERKLKOXMLMSLPQL.json","graph_json":"https://pith.science/api/pith-number/GYVTSY2KUUHERKLKOXMLMSLPQL/graph.json","events_json":"https://pith.science/api/pith-number/GYVTSY2KUUHERKLKOXMLMSLPQL/events.json","paper":"https://pith.science/paper/GYVTSY2K"},"agent_actions":{"view_html":"https://pith.science/pith/GYVTSY2KUUHERKLKOXMLMSLPQL","download_json":"https://pith.science/pith/GYVTSY2KUUHERKLKOXMLMSLPQL.json","view_paper":"https://pith.science/paper/GYVTSY2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.01903&json=true","fetch_graph":"https://pith.science/api/pith-number/GYVTSY2KUUHERKLKOXMLMSLPQL/graph.json","fetch_events":"https://pith.science/api/pith-number/GYVTSY2KUUHERKLKOXMLMSLPQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYVTSY2KUUHERKLKOXMLMSLPQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYVTSY2KUUHERKLKOXMLMSLPQL/action/storage_attestation","attest_author":"https://pith.science/pith/GYVTSY2KUUHERKLKOXMLMSLPQL/action/author_attestation","sign_citation":"https://pith.science/pith/GYVTSY2KUUHERKLKOXMLMSLPQL/action/citation_signature","submit_replication":"https://pith.science/pith/GYVTSY2KUUHERKLKOXMLMSLPQL/action/replication_record"}},"created_at":"2026-07-05T10:55:16.066011+00:00","updated_at":"2026-07-05T10:55:16.066011+00:00"}