{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VXBDTJFM56FLON2PN3SMLI7MK7","short_pith_number":"pith:VXBDTJFM","schema_version":"1.0","canonical_sha256":"adc239a4acef8ab7374f6ee4c5a3ec57d17067b6b04ac561fdcde2685e88077d","source":{"kind":"arxiv","id":"2211.13594","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised vision-language pretraining 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, Jinying Liao, Lin Tan, Pengfei Li, Shenjun Zhong","submitted_at":"2022-11-24T13:31:56Z","abstract_excerpt":"Medical image visual question answering (VQA) is a task to answer clinical questions, given a radiographic image, which is a challenging problem that requires a model to integrate both vision and language information. To solve medical VQA problems with a limited number of training data, pretrain-finetune paradigm is widely used to improve the model generalization. In this paper, we propose a self-supervised method that applies Masked image modeling, Masked language modeling, Image text matching and Image text alignment via contrastive learning (M2I2) for pretraining on medical image caption da"},"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":"2211.13594","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-24T13:31:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"37cf56ee9c58580b6bfa8dc5a816dda50a6bb14ed1b629c83687dfb03028cf49","abstract_canon_sha256":"e2fc37d2d9cc56988e298e7a22ca14904359d190eba0e6e4ee419855567de2bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:24.142186Z","signature_b64":"neTL7O/yf57Xn95zlz5ynr0iBdaFs6zNQH+LbXxFOfvJUnLIMeq8svapDXebHm3H8QmcAVDUEd8PImDzsK7xBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adc239a4acef8ab7374f6ee4c5a3ec57d17067b6b04ac561fdcde2685e88077d","last_reissued_at":"2026-07-05T05:19:24.141780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:24.141780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised vision-language pretraining 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, Jinying Liao, Lin Tan, Pengfei Li, Shenjun Zhong","submitted_at":"2022-11-24T13:31:56Z","abstract_excerpt":"Medical image visual question answering (VQA) is a task to answer clinical questions, given a radiographic image, which is a challenging problem that requires a model to integrate both vision and language information. To solve medical VQA problems with a limited number of training data, pretrain-finetune paradigm is widely used to improve the model generalization. In this paper, we propose a self-supervised method that applies Masked image modeling, Masked language modeling, Image text matching and Image text alignment via contrastive learning (M2I2) for pretraining on medical image caption da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13594","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/2211.13594/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":"2211.13594","created_at":"2026-07-05T05:19:24.141836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.13594v1","created_at":"2026-07-05T05:19:24.141836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13594","created_at":"2026-07-05T05:19:24.141836+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXBDTJFM56FL","created_at":"2026-07-05T05:19:24.141836+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXBDTJFM56FLON2P","created_at":"2026-07-05T05:19:24.141836+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXBDTJFM","created_at":"2026-07-05T05:19:24.141836+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":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VXBDTJFM56FLON2PN3SMLI7MK7","json":"https://pith.science/pith/VXBDTJFM56FLON2PN3SMLI7MK7.json","graph_json":"https://pith.science/api/pith-number/VXBDTJFM56FLON2PN3SMLI7MK7/graph.json","events_json":"https://pith.science/api/pith-number/VXBDTJFM56FLON2PN3SMLI7MK7/events.json","paper":"https://pith.science/paper/VXBDTJFM"},"agent_actions":{"view_html":"https://pith.science/pith/VXBDTJFM56FLON2PN3SMLI7MK7","download_json":"https://pith.science/pith/VXBDTJFM56FLON2PN3SMLI7MK7.json","view_paper":"https://pith.science/paper/VXBDTJFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.13594&json=true","fetch_graph":"https://pith.science/api/pith-number/VXBDTJFM56FLON2PN3SMLI7MK7/graph.json","fetch_events":"https://pith.science/api/pith-number/VXBDTJFM56FLON2PN3SMLI7MK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXBDTJFM56FLON2PN3SMLI7MK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXBDTJFM56FLON2PN3SMLI7MK7/action/storage_attestation","attest_author":"https://pith.science/pith/VXBDTJFM56FLON2PN3SMLI7MK7/action/author_attestation","sign_citation":"https://pith.science/pith/VXBDTJFM56FLON2PN3SMLI7MK7/action/citation_signature","submit_replication":"https://pith.science/pith/VXBDTJFM56FLON2PN3SMLI7MK7/action/replication_record"}},"created_at":"2026-07-05T05:19:24.141836+00:00","updated_at":"2026-07-05T05:19:24.141836+00:00"}