{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4KWEHCEUPV7W5CFB2KTHJPXZNL","short_pith_number":"pith:4KWEHCEU","schema_version":"1.0","canonical_sha256":"e2ac4388947d7f6e88a1d2a674bef96afc7ed46bb0a5eb8b2b173ce599b53123","source":{"kind":"arxiv","id":"2304.01611","version":2},"attestation_state":"computed","paper":{"title":"Q2ATransformer: Improving Medical VQA via an Answer Querying Decoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dong Xu, Luping Zhou, Yunyi Liu, Zhanyu Wang","submitted_at":"2023-04-04T08:06:40Z","abstract_excerpt":"Medical Visual Question Answering (VQA) systems play a supporting role to understand clinic-relevant information carried by medical images. The questions to a medical image include two categories: close-end (such as Yes/No question) and open-end. To obtain answers, the majority of the existing medical VQA methods relies on classification approaches, while a few works attempt to use generation approaches or a mixture of the two. The classification approaches are relatively simple but perform poorly on long open-end questions. To bridge this gap, in this paper, we propose a new Transformer based"},"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":"2304.01611","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-04T08:06:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9d863918b8aaf0861e573428564cc8566dc0dfc24a770f7281cd1a8a758cc952","abstract_canon_sha256":"18bd70331df3f901c36ae798a87dec3ee7d7f067f92bfe2102de69b3ebcc4437"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:05.987067Z","signature_b64":"QhD+bsc2MMt99jg3zQX7cxSf9KGeMT0cin98X0I4/JgaZkrPPD4yTx09812ooPR5HInniAA0UPdCK29xwKWTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2ac4388947d7f6e88a1d2a674bef96afc7ed46bb0a5eb8b2b173ce599b53123","last_reissued_at":"2026-07-05T06:17:05.986654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:05.986654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q2ATransformer: Improving Medical VQA via an Answer Querying Decoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dong Xu, Luping Zhou, Yunyi Liu, Zhanyu Wang","submitted_at":"2023-04-04T08:06:40Z","abstract_excerpt":"Medical Visual Question Answering (VQA) systems play a supporting role to understand clinic-relevant information carried by medical images. The questions to a medical image include two categories: close-end (such as Yes/No question) and open-end. To obtain answers, the majority of the existing medical VQA methods relies on classification approaches, while a few works attempt to use generation approaches or a mixture of the two. The classification approaches are relatively simple but perform poorly on long open-end questions. To bridge this gap, in this paper, we propose a new Transformer based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01611","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/2304.01611/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":"2304.01611","created_at":"2026-07-05T06:17:05.986710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.01611v2","created_at":"2026-07-05T06:17:05.986710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01611","created_at":"2026-07-05T06:17:05.986710+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KWEHCEUPV7W","created_at":"2026-07-05T06:17:05.986710+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KWEHCEUPV7W5CFB","created_at":"2026-07-05T06:17:05.986710+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KWEHCEU","created_at":"2026-07-05T06:17:05.986710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2306.00890","citing_title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4KWEHCEUPV7W5CFB2KTHJPXZNL","json":"https://pith.science/pith/4KWEHCEUPV7W5CFB2KTHJPXZNL.json","graph_json":"https://pith.science/api/pith-number/4KWEHCEUPV7W5CFB2KTHJPXZNL/graph.json","events_json":"https://pith.science/api/pith-number/4KWEHCEUPV7W5CFB2KTHJPXZNL/events.json","paper":"https://pith.science/paper/4KWEHCEU"},"agent_actions":{"view_html":"https://pith.science/pith/4KWEHCEUPV7W5CFB2KTHJPXZNL","download_json":"https://pith.science/pith/4KWEHCEUPV7W5CFB2KTHJPXZNL.json","view_paper":"https://pith.science/paper/4KWEHCEU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.01611&json=true","fetch_graph":"https://pith.science/api/pith-number/4KWEHCEUPV7W5CFB2KTHJPXZNL/graph.json","fetch_events":"https://pith.science/api/pith-number/4KWEHCEUPV7W5CFB2KTHJPXZNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KWEHCEUPV7W5CFB2KTHJPXZNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KWEHCEUPV7W5CFB2KTHJPXZNL/action/storage_attestation","attest_author":"https://pith.science/pith/4KWEHCEUPV7W5CFB2KTHJPXZNL/action/author_attestation","sign_citation":"https://pith.science/pith/4KWEHCEUPV7W5CFB2KTHJPXZNL/action/citation_signature","submit_replication":"https://pith.science/pith/4KWEHCEUPV7W5CFB2KTHJPXZNL/action/replication_record"}},"created_at":"2026-07-05T06:17:05.986710+00:00","updated_at":"2026-07-05T06:17:05.986710+00:00"}