{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TGGUM6YRPECROWGKHUDLSHYJ4P","short_pith_number":"pith:TGGUM6YR","schema_version":"1.0","canonical_sha256":"998d467b1179051758ca3d06b91f09e3ff20083d930bb2082897a247c5b5261c","source":{"kind":"arxiv","id":"2309.11080","version":1},"attestation_state":"computed","paper":{"title":"Visual Question Answering in the Medical Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arcot Sowmya, Louisa Canepa, Sonit Singh","submitted_at":"2023-09-20T06:06:10Z","abstract_excerpt":"Medical visual question answering (Med-VQA) is a machine learning task that aims to create a system that can answer natural language questions based on given medical images. Although there has been rapid progress on the general VQA task, less progress has been made on Med-VQA due to the lack of large-scale annotated datasets. In this paper, we present domain-specific pre-training strategies, including a novel contrastive learning pretraining method, to mitigate the problem of small datasets for the Med-VQA task. We find that the model benefits from components that use fewer parameters. We also"},"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":"2309.11080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-20T06:06:10Z","cross_cats_sorted":[],"title_canon_sha256":"64a4de3ce20c5609811325479fd4c3df8788022e10c3c025e19d4a5bf057dcf3","abstract_canon_sha256":"038eb79bb567080815a67c5bca00544ad641326b8c76342c628a5a2f88080558"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:30.898201Z","signature_b64":"giBI94BgybEGyYIFu3zHYwgzq82PeZRCkKaMG6GQEJFRuNI/r2AAooai75QqOOHw6blztOyH8WkLH4GruGDMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"998d467b1179051758ca3d06b91f09e3ff20083d930bb2082897a247c5b5261c","last_reissued_at":"2026-07-05T06:52:30.897805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:30.897805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Question Answering in the Medical Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arcot Sowmya, Louisa Canepa, Sonit Singh","submitted_at":"2023-09-20T06:06:10Z","abstract_excerpt":"Medical visual question answering (Med-VQA) is a machine learning task that aims to create a system that can answer natural language questions based on given medical images. Although there has been rapid progress on the general VQA task, less progress has been made on Med-VQA due to the lack of large-scale annotated datasets. In this paper, we present domain-specific pre-training strategies, including a novel contrastive learning pretraining method, to mitigate the problem of small datasets for the Med-VQA task. We find that the model benefits from components that use fewer parameters. We also"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11080","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/2309.11080/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":"2309.11080","created_at":"2026-07-05T06:52:30.897860+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.11080v1","created_at":"2026-07-05T06:52:30.897860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11080","created_at":"2026-07-05T06:52:30.897860+00:00"},{"alias_kind":"pith_short_12","alias_value":"TGGUM6YRPECR","created_at":"2026-07-05T06:52:30.897860+00:00"},{"alias_kind":"pith_short_16","alias_value":"TGGUM6YRPECROWGK","created_at":"2026-07-05T06:52:30.897860+00:00"},{"alias_kind":"pith_short_8","alias_value":"TGGUM6YR","created_at":"2026-07-05T06:52:30.897860+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24792","citing_title":"Parameter-Efficient VLMs for Gastrointestinal Endoscopy: Medical Image Generation and Clinical Visual Question Answering","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TGGUM6YRPECROWGKHUDLSHYJ4P","json":"https://pith.science/pith/TGGUM6YRPECROWGKHUDLSHYJ4P.json","graph_json":"https://pith.science/api/pith-number/TGGUM6YRPECROWGKHUDLSHYJ4P/graph.json","events_json":"https://pith.science/api/pith-number/TGGUM6YRPECROWGKHUDLSHYJ4P/events.json","paper":"https://pith.science/paper/TGGUM6YR"},"agent_actions":{"view_html":"https://pith.science/pith/TGGUM6YRPECROWGKHUDLSHYJ4P","download_json":"https://pith.science/pith/TGGUM6YRPECROWGKHUDLSHYJ4P.json","view_paper":"https://pith.science/paper/TGGUM6YR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.11080&json=true","fetch_graph":"https://pith.science/api/pith-number/TGGUM6YRPECROWGKHUDLSHYJ4P/graph.json","fetch_events":"https://pith.science/api/pith-number/TGGUM6YRPECROWGKHUDLSHYJ4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TGGUM6YRPECROWGKHUDLSHYJ4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TGGUM6YRPECROWGKHUDLSHYJ4P/action/storage_attestation","attest_author":"https://pith.science/pith/TGGUM6YRPECROWGKHUDLSHYJ4P/action/author_attestation","sign_citation":"https://pith.science/pith/TGGUM6YRPECROWGKHUDLSHYJ4P/action/citation_signature","submit_replication":"https://pith.science/pith/TGGUM6YRPECROWGKHUDLSHYJ4P/action/replication_record"}},"created_at":"2026-07-05T06:52:30.897860+00:00","updated_at":"2026-07-05T06:52:30.897860+00:00"}