{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:O67UTB4N457FP4RNGRCOKWWGIC","short_pith_number":"pith:O67UTB4N","schema_version":"1.0","canonical_sha256":"77bf49878de77e57f22d3444e55ac64081d830c62c5d5d886e2d90eb1a909726","source":{"kind":"arxiv","id":"2209.07098","version":1},"attestation_state":"computed","paper":{"title":"Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Guanbin Li, Jinpeng Hu, Tsung-Hui Chang, Xiang Wan, Yang Liu, Yuhao Du, Zhihong Chen","submitted_at":"2022-09-15T07:26:43Z","abstract_excerpt":"Medical vision-and-language pre-training provides a feasible solution to extract effective vision-and-language representations from medical images and texts. However, few studies have been dedicated to this field to facilitate medical vision-and-language understanding. In this paper, we propose a self-supervised learning paradigm with multi-modal masked autoencoders (M$^3$AE), which learn cross-modal domain knowledge by reconstructing missing pixels and tokens from randomly masked images and texts. There are three key designs to make this simple approach work. First, considering the different "},"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":"2209.07098","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-15T07:26:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dc19e99c13fe32ae4cdea9bb07ab1a0883ef6b6121b8ae2ba5a0694503b7944c","abstract_canon_sha256":"dc0b834c2b35f885ee184f4149569542e92c6c58043b62db6d48446b9cf72da8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:51.545779Z","signature_b64":"5FvQNyIewGHN9RGO2Pwn1jeCNausRRkTISUCTItWgg9BKS2xvzNmfBThpuXgARTsQo/8c/EGLnb9C9H9N779Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77bf49878de77e57f22d3444e55ac64081d830c62c5d5d886e2d90eb1a909726","last_reissued_at":"2026-07-05T04:57:51.545342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:51.545342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Guanbin Li, Jinpeng Hu, Tsung-Hui Chang, Xiang Wan, Yang Liu, Yuhao Du, Zhihong Chen","submitted_at":"2022-09-15T07:26:43Z","abstract_excerpt":"Medical vision-and-language pre-training provides a feasible solution to extract effective vision-and-language representations from medical images and texts. However, few studies have been dedicated to this field to facilitate medical vision-and-language understanding. In this paper, we propose a self-supervised learning paradigm with multi-modal masked autoencoders (M$^3$AE), which learn cross-modal domain knowledge by reconstructing missing pixels and tokens from randomly masked images and texts. There are three key designs to make this simple approach work. First, considering the different "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07098","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/2209.07098/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":"2209.07098","created_at":"2026-07-05T04:57:51.545402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.07098v1","created_at":"2026-07-05T04:57:51.545402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07098","created_at":"2026-07-05T04:57:51.545402+00:00"},{"alias_kind":"pith_short_12","alias_value":"O67UTB4N457F","created_at":"2026-07-05T04:57:51.545402+00:00"},{"alias_kind":"pith_short_16","alias_value":"O67UTB4N457FP4RN","created_at":"2026-07-05T04:57:51.545402+00:00"},{"alias_kind":"pith_short_8","alias_value":"O67UTB4N","created_at":"2026-07-05T04:57:51.545402+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06959","citing_title":"CheXPO: Preference Optimization for Chest X-ray VLMs with Counterfactual Rationale","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O67UTB4N457FP4RNGRCOKWWGIC","json":"https://pith.science/pith/O67UTB4N457FP4RNGRCOKWWGIC.json","graph_json":"https://pith.science/api/pith-number/O67UTB4N457FP4RNGRCOKWWGIC/graph.json","events_json":"https://pith.science/api/pith-number/O67UTB4N457FP4RNGRCOKWWGIC/events.json","paper":"https://pith.science/paper/O67UTB4N"},"agent_actions":{"view_html":"https://pith.science/pith/O67UTB4N457FP4RNGRCOKWWGIC","download_json":"https://pith.science/pith/O67UTB4N457FP4RNGRCOKWWGIC.json","view_paper":"https://pith.science/paper/O67UTB4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.07098&json=true","fetch_graph":"https://pith.science/api/pith-number/O67UTB4N457FP4RNGRCOKWWGIC/graph.json","fetch_events":"https://pith.science/api/pith-number/O67UTB4N457FP4RNGRCOKWWGIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O67UTB4N457FP4RNGRCOKWWGIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O67UTB4N457FP4RNGRCOKWWGIC/action/storage_attestation","attest_author":"https://pith.science/pith/O67UTB4N457FP4RNGRCOKWWGIC/action/author_attestation","sign_citation":"https://pith.science/pith/O67UTB4N457FP4RNGRCOKWWGIC/action/citation_signature","submit_replication":"https://pith.science/pith/O67UTB4N457FP4RNGRCOKWWGIC/action/replication_record"}},"created_at":"2026-07-05T04:57:51.545402+00:00","updated_at":"2026-07-05T04:57:51.545402+00:00"}