{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XIDGMEXBRK6LH3MXUHJ2DGSSBQ","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":"42ef3392454499e530556d847d19e5248981bdfc3586224623b07aee6704d14d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-11T15:00:11Z","title_canon_sha256":"dcb0066dd84b1f65985f44b3c08a8ab252481bfb2aba2ccf3a19c241b903ca7f"},"schema_version":"1.0","source":{"id":"2307.05314","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.05314","created_at":"2026-07-05T06:29:55Z"},{"alias_kind":"arxiv_version","alias_value":"2307.05314v1","created_at":"2026-07-05T06:29:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05314","created_at":"2026-07-05T06:29:55Z"},{"alias_kind":"pith_short_12","alias_value":"XIDGMEXBRK6L","created_at":"2026-07-05T06:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"XIDGMEXBRK6LH3MX","created_at":"2026-07-05T06:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"XIDGMEXB","created_at":"2026-07-05T06:29:55Z"}],"graph_snapshots":[{"event_id":"sha256:fff449ffa87d37d29e6ac58887b172464cd71d6657d66c433d308e649c38b121","target":"graph","created_at":"2026-07-05T06:29:55Z","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/2307.05314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gang Liu, Jinlong He, Pengfei Li, Shenjun Zhong, Zixu Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-11T15:00:11Z","title":"Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05314","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:eed373213cf0ff9ce83f03cf3073a6a03f5b3c1389c46f096117777a7c693325","target":"record","created_at":"2026-07-05T06:29:55Z","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":"42ef3392454499e530556d847d19e5248981bdfc3586224623b07aee6704d14d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-11T15:00:11Z","title_canon_sha256":"dcb0066dd84b1f65985f44b3c08a8ab252481bfb2aba2ccf3a19c241b903ca7f"},"schema_version":"1.0","source":{"id":"2307.05314","kind":"arxiv","version":1}},"canonical_sha256":"ba066612e18abcb3ed97a1d3a19a520c047937332f9515b27f2da3f60b30b45e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba066612e18abcb3ed97a1d3a19a520c047937332f9515b27f2da3f60b30b45e","first_computed_at":"2026-07-05T06:29:55.717231Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:29:55.717231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R3iuz50KhrIfZd9El7rpIlml6GjXdLr2CyU5nIhLjGQKKg8Q7mE/RhVNv3iWmcpczuw9DHWjGMmBqLoaVECoCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:29:55.717766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.05314","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eed373213cf0ff9ce83f03cf3073a6a03f5b3c1389c46f096117777a7c693325","sha256:fff449ffa87d37d29e6ac58887b172464cd71d6657d66c433d308e649c38b121"],"state_sha256":"0e00ec1d136c225c766fb46c5ffe2147376832044a2d3b9ac557b4085bcee25c"}