{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O67UTB4N457FP4RNGRCOKWWGIC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dc0b834c2b35f885ee184f4149569542e92c6c58043b62db6d48446b9cf72da8","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-15T07:26:43Z","title_canon_sha256":"dc19e99c13fe32ae4cdea9bb07ab1a0883ef6b6121b8ae2ba5a0694503b7944c"},"schema_version":"1.0","source":{"id":"2209.07098","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.07098","created_at":"2026-07-05T04:57:51Z"},{"alias_kind":"arxiv_version","alias_value":"2209.07098v1","created_at":"2026-07-05T04:57:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07098","created_at":"2026-07-05T04:57:51Z"},{"alias_kind":"pith_short_12","alias_value":"O67UTB4N457F","created_at":"2026-07-05T04:57:51Z"},{"alias_kind":"pith_short_16","alias_value":"O67UTB4N457FP4RN","created_at":"2026-07-05T04:57:51Z"},{"alias_kind":"pith_short_8","alias_value":"O67UTB4N","created_at":"2026-07-05T04:57:51Z"}],"graph_snapshots":[{"event_id":"sha256:c6c486cfbbc0b7d554a39271f6ea68cdd944a09fc8a2eabfa6dcce1f9cd9812b","target":"graph","created_at":"2026-07-05T04:57:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2209.07098/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Guanbin Li, Jinpeng Hu, Tsung-Hui Chang, Xiang Wan, Yang Liu, Yuhao Du, Zhihong Chen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-15T07:26:43Z","title":"Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07098","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:de318f16bb101b9dc5bbb2517d43662bf4e9a0d6e849b16fcb3832c9c8014747","target":"record","created_at":"2026-07-05T04:57:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dc0b834c2b35f885ee184f4149569542e92c6c58043b62db6d48446b9cf72da8","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-15T07:26:43Z","title_canon_sha256":"dc19e99c13fe32ae4cdea9bb07ab1a0883ef6b6121b8ae2ba5a0694503b7944c"},"schema_version":"1.0","source":{"id":"2209.07098","kind":"arxiv","version":1}},"canonical_sha256":"77bf49878de77e57f22d3444e55ac64081d830c62c5d5d886e2d90eb1a909726","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77bf49878de77e57f22d3444e55ac64081d830c62c5d5d886e2d90eb1a909726","first_computed_at":"2026-07-05T04:57:51.545342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:57:51.545342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5FvQNyIewGHN9RGO2Pwn1jeCNausRRkTISUCTItWgg9BKS2xvzNmfBThpuXgARTsQo/8c/EGLnb9C9H9N779Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:57:51.545779Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.07098","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de318f16bb101b9dc5bbb2517d43662bf4e9a0d6e849b16fcb3832c9c8014747","sha256:c6c486cfbbc0b7d554a39271f6ea68cdd944a09fc8a2eabfa6dcce1f9cd9812b"],"state_sha256":"e91f62d9c80a3b8c520ffac788f07f7425ed592b2eb8f5fbaf06049defb65921"}