{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VXBDTJFM56FLON2PN3SMLI7MK7","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":"e2fc37d2d9cc56988e298e7a22ca14904359d190eba0e6e4ee419855567de2bd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-24T13:31:56Z","title_canon_sha256":"37cf56ee9c58580b6bfa8dc5a816dda50a6bb14ed1b629c83687dfb03028cf49"},"schema_version":"1.0","source":{"id":"2211.13594","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.13594","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2211.13594v1","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13594","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"VXBDTJFM56FL","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"VXBDTJFM56FLON2P","created_at":"2026-07-05T05:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"VXBDTJFM","created_at":"2026-07-05T05:19:24Z"}],"graph_snapshots":[{"event_id":"sha256:17a219c0b267c96078fcc9f612e4c9c33cee17db0bc72dbdd238bed7001d66fc","target":"graph","created_at":"2026-07-05T05:19:24Z","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/2211.13594/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gang Liu, Jinying Liao, Lin Tan, Pengfei Li, Shenjun Zhong","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-24T13:31:56Z","title":"Self-supervised vision-language pretraining for Medical visual question answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13594","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":"sha256:246b663c1ef3a395db3e87464817e5ed83f120f287c5a3f35548e65454203219","target":"record","created_at":"2026-07-05T05:19:24Z","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":"e2fc37d2d9cc56988e298e7a22ca14904359d190eba0e6e4ee419855567de2bd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-24T13:31:56Z","title_canon_sha256":"37cf56ee9c58580b6bfa8dc5a816dda50a6bb14ed1b629c83687dfb03028cf49"},"schema_version":"1.0","source":{"id":"2211.13594","kind":"arxiv","version":1}},"canonical_sha256":"adc239a4acef8ab7374f6ee4c5a3ec57d17067b6b04ac561fdcde2685e88077d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adc239a4acef8ab7374f6ee4c5a3ec57d17067b6b04ac561fdcde2685e88077d","first_computed_at":"2026-07-05T05:19:24.141780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:24.141780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"neTL7O/yf57Xn95zlz5ynr0iBdaFs6zNQH+LbXxFOfvJUnLIMeq8svapDXebHm3H8QmcAVDUEd8PImDzsK7xBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:24.142186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.13594","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:246b663c1ef3a395db3e87464817e5ed83f120f287c5a3f35548e65454203219","sha256:17a219c0b267c96078fcc9f612e4c9c33cee17db0bc72dbdd238bed7001d66fc"],"state_sha256":"df0608d5df13d5f1b0097ab275fd12591b2ba7f088ecba9dde3fdd78b597e232"}