{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XIDGMEXBRK6LH3MXUHJ2DGSSBQ","short_pith_number":"pith:XIDGMEXB","schema_version":"1.0","canonical_sha256":"ba066612e18abcb3ed97a1d3a19a520c047937332f9515b27f2da3f60b30b45e","source":{"kind":"arxiv","id":"2307.05314","version":1},"attestation_state":"computed","paper":{"title":"Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gang Liu, Jinlong He, Pengfei Li, Shenjun Zhong, Zixu Zhao","submitted_at":"2023-07-11T15:00:11Z","abstract_excerpt":"Medical visual question answering (VQA) is a challenging task that requires answering clinical questions of a given medical image, by taking consider of both visual and language information. However, due to the small scale of training data for medical VQA, pre-training fine-tuning paradigms have been a commonly used solution to improve model generalization performance. In this paper, we present a novel self-supervised approach that learns unimodal and multimodal feature representations of input images and text using medical image caption datasets, by leveraging both unimodal and multimodal con"},"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":"2307.05314","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-11T15:00:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dcb0066dd84b1f65985f44b3c08a8ab252481bfb2aba2ccf3a19c241b903ca7f","abstract_canon_sha256":"42ef3392454499e530556d847d19e5248981bdfc3586224623b07aee6704d14d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:55.717766Z","signature_b64":"R3iuz50KhrIfZd9El7rpIlml6GjXdLr2CyU5nIhLjGQKKg8Q7mE/RhVNv3iWmcpczuw9DHWjGMmBqLoaVECoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba066612e18abcb3ed97a1d3a19a520c047937332f9515b27f2da3f60b30b45e","last_reissued_at":"2026-07-05T06:29:55.717231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:55.717231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gang Liu, Jinlong He, Pengfei Li, Shenjun Zhong, Zixu Zhao","submitted_at":"2023-07-11T15:00:11Z","abstract_excerpt":"Medical visual question answering (VQA) is a challenging task that requires answering clinical questions of a given medical image, by taking consider of both visual and language information. However, due to the small scale of training data for medical VQA, pre-training fine-tuning paradigms have been a commonly used solution to improve model generalization performance. In this paper, we present a novel self-supervised approach that learns unimodal and multimodal feature representations of input images and text using medical image caption datasets, by leveraging both unimodal and multimodal con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05314","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/2307.05314/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":"2307.05314","created_at":"2026-07-05T06:29:55.717292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.05314v1","created_at":"2026-07-05T06:29:55.717292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05314","created_at":"2026-07-05T06:29:55.717292+00:00"},{"alias_kind":"pith_short_12","alias_value":"XIDGMEXBRK6L","created_at":"2026-07-05T06:29:55.717292+00:00"},{"alias_kind":"pith_short_16","alias_value":"XIDGMEXBRK6LH3MX","created_at":"2026-07-05T06:29:55.717292+00:00"},{"alias_kind":"pith_short_8","alias_value":"XIDGMEXB","created_at":"2026-07-05T06:29:55.717292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09209","citing_title":"Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XIDGMEXBRK6LH3MXUHJ2DGSSBQ","json":"https://pith.science/pith/XIDGMEXBRK6LH3MXUHJ2DGSSBQ.json","graph_json":"https://pith.science/api/pith-number/XIDGMEXBRK6LH3MXUHJ2DGSSBQ/graph.json","events_json":"https://pith.science/api/pith-number/XIDGMEXBRK6LH3MXUHJ2DGSSBQ/events.json","paper":"https://pith.science/paper/XIDGMEXB"},"agent_actions":{"view_html":"https://pith.science/pith/XIDGMEXBRK6LH3MXUHJ2DGSSBQ","download_json":"https://pith.science/pith/XIDGMEXBRK6LH3MXUHJ2DGSSBQ.json","view_paper":"https://pith.science/paper/XIDGMEXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.05314&json=true","fetch_graph":"https://pith.science/api/pith-number/XIDGMEXBRK6LH3MXUHJ2DGSSBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XIDGMEXBRK6LH3MXUHJ2DGSSBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XIDGMEXBRK6LH3MXUHJ2DGSSBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XIDGMEXBRK6LH3MXUHJ2DGSSBQ/action/storage_attestation","attest_author":"https://pith.science/pith/XIDGMEXBRK6LH3MXUHJ2DGSSBQ/action/author_attestation","sign_citation":"https://pith.science/pith/XIDGMEXBRK6LH3MXUHJ2DGSSBQ/action/citation_signature","submit_replication":"https://pith.science/pith/XIDGMEXBRK6LH3MXUHJ2DGSSBQ/action/replication_record"}},"created_at":"2026-07-05T06:29:55.717292+00:00","updated_at":"2026-07-05T06:29:55.717292+00:00"}