{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LLTCWY4CN2DIL24Y275DV443PM","short_pith_number":"pith:LLTCWY4C","schema_version":"1.0","canonical_sha256":"5ae62b63826e8685eb98d7fa3af39b7b247b42f32eb3d4c1b63038f094f08752","source":{"kind":"arxiv","id":"2111.10056","version":3},"attestation_state":"computed","paper":{"title":"Medical Visual Question Answering: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Danli Shi, Donghao Zhang, Gholamreza Haffari, Mingguang He, Qingyi Tao, Qi Wu, Zhihong Lin, Zongyuan Ge","submitted_at":"2021-11-19T05:55:15Z","abstract_excerpt":"Medical Visual Question Answering~(VQA) is a combination of medical artificial intelligence and popular VQA challenges. Given a medical image and a clinically relevant question in natural language, the medical VQA system is expected to predict a plausible and convincing answer. Although the general-domain VQA has been extensively studied, the medical VQA still needs specific investigation and exploration due to its task features. In the first part of this survey, we collect and discuss the publicly available medical VQA datasets up-to-date about the data source, data quantity, and task feature"},"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":"2111.10056","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-19T05:55:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"24731fa0e1d94968265b835e01e20c44e7ab75780408a0989afb91672ca9533e","abstract_canon_sha256":"0d664918dc954b3ddc4b143e9be704aac1970acbc158ea34ef9d913af63c36e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:58.361834Z","signature_b64":"sVAkT1igKTRfUywEV6fHtWdRsYFFgLEp7bgsxdUJHEvM+YpLnWYwJDP0lYypRuRwB5+oVWFBbwcleCMsVFdICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ae62b63826e8685eb98d7fa3af39b7b247b42f32eb3d4c1b63038f094f08752","last_reissued_at":"2026-07-05T06:18:58.361343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:58.361343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Medical Visual Question Answering: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Danli Shi, Donghao Zhang, Gholamreza Haffari, Mingguang He, Qingyi Tao, Qi Wu, Zhihong Lin, Zongyuan Ge","submitted_at":"2021-11-19T05:55:15Z","abstract_excerpt":"Medical Visual Question Answering~(VQA) is a combination of medical artificial intelligence and popular VQA challenges. Given a medical image and a clinically relevant question in natural language, the medical VQA system is expected to predict a plausible and convincing answer. Although the general-domain VQA has been extensively studied, the medical VQA still needs specific investigation and exploration due to its task features. In the first part of this survey, we collect and discuss the publicly available medical VQA datasets up-to-date about the data source, data quantity, and task feature"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10056","kind":"arxiv","version":3},"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/2111.10056/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":"2111.10056","created_at":"2026-07-05T06:18:58.361398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.10056v3","created_at":"2026-07-05T06:18:58.361398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10056","created_at":"2026-07-05T06:18:58.361398+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLTCWY4CN2DI","created_at":"2026-07-05T06:18:58.361398+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLTCWY4CN2DIL24Y","created_at":"2026-07-05T06:18:58.361398+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLTCWY4C","created_at":"2026-07-05T06:18:58.361398+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.10415","citing_title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LLTCWY4CN2DIL24Y275DV443PM","json":"https://pith.science/pith/LLTCWY4CN2DIL24Y275DV443PM.json","graph_json":"https://pith.science/api/pith-number/LLTCWY4CN2DIL24Y275DV443PM/graph.json","events_json":"https://pith.science/api/pith-number/LLTCWY4CN2DIL24Y275DV443PM/events.json","paper":"https://pith.science/paper/LLTCWY4C"},"agent_actions":{"view_html":"https://pith.science/pith/LLTCWY4CN2DIL24Y275DV443PM","download_json":"https://pith.science/pith/LLTCWY4CN2DIL24Y275DV443PM.json","view_paper":"https://pith.science/paper/LLTCWY4C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.10056&json=true","fetch_graph":"https://pith.science/api/pith-number/LLTCWY4CN2DIL24Y275DV443PM/graph.json","fetch_events":"https://pith.science/api/pith-number/LLTCWY4CN2DIL24Y275DV443PM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLTCWY4CN2DIL24Y275DV443PM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLTCWY4CN2DIL24Y275DV443PM/action/storage_attestation","attest_author":"https://pith.science/pith/LLTCWY4CN2DIL24Y275DV443PM/action/author_attestation","sign_citation":"https://pith.science/pith/LLTCWY4CN2DIL24Y275DV443PM/action/citation_signature","submit_replication":"https://pith.science/pith/LLTCWY4CN2DIL24Y275DV443PM/action/replication_record"}},"created_at":"2026-07-05T06:18:58.361398+00:00","updated_at":"2026-07-05T06:18:58.361398+00:00"}