{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HLNDMTDA3WHPVQVCFOSPBNEFSW","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":"ad9e7f3b2086233afda3b817f95197d8688b7310f43c0019829f8725de7bdb8b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-26T01:14:10Z","title_canon_sha256":"9779c961af538175e66ca26416e8c2893b26caa5a374ad6e5c7008d40000e4ae"},"schema_version":"1.0","source":{"id":"2312.15840","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15840","created_at":"2026-07-05T11:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15840v2","created_at":"2026-07-05T11:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15840","created_at":"2026-07-05T11:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"HLNDMTDA3WHP","created_at":"2026-07-05T11:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"HLNDMTDA3WHPVQVC","created_at":"2026-07-05T11:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"HLNDMTDA","created_at":"2026-07-05T11:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:ede59d54be869669129de110d6fdb9bae9b3344edf2a836f4816d96444d04335","target":"graph","created_at":"2026-07-05T11:05:31Z","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/2312.15840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-modal medical image-report retrieval task plays a significant role in clinical diagnosis and various medical generative tasks. Eliminating heterogeneity between different modalities to enhance semantic consistency is the key challenge of this task. The current Vision-Language Pretraining (VLP) models, with cross-modal contrastive learning and masked reconstruction as joint training tasks, can effectively enhance the performance of cross-modal retrieval. This framework typically employs dual-stream inputs, using unmasked data for cross-modal contrastive learning and masked data for recons","authors_text":"Kai Jin, Xiuzhuang Zhou, Zeqiang Wei","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-26T01:14:10Z","title":"Masked Contrastive Reconstruction for Cross-modal Medical Image-Report Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15840","kind":"arxiv","version":2},"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:f09634f7ade5e1548e91c78cf58363f6b4fdac054d136241229cb8c8c5b405c1","target":"record","created_at":"2026-07-05T11:05:31Z","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":"ad9e7f3b2086233afda3b817f95197d8688b7310f43c0019829f8725de7bdb8b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-26T01:14:10Z","title_canon_sha256":"9779c961af538175e66ca26416e8c2893b26caa5a374ad6e5c7008d40000e4ae"},"schema_version":"1.0","source":{"id":"2312.15840","kind":"arxiv","version":2}},"canonical_sha256":"3ada364c60dd8efac2a22ba4f0b48595962e674cffad0ac580f2dc1ee3aedcc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ada364c60dd8efac2a22ba4f0b48595962e674cffad0ac580f2dc1ee3aedcc1","first_computed_at":"2026-07-05T11:05:31.714589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:31.714589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m9sM2Jcg7gs+2OUhOy9Y8MsRA5rtx7w5RAhzFN4ZdoDfR01FVbAXSDz8htg22aF5Zb1Mu799LELVdBIfoKybCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:31.715090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.15840","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f09634f7ade5e1548e91c78cf58363f6b4fdac054d136241229cb8c8c5b405c1","sha256:ede59d54be869669129de110d6fdb9bae9b3344edf2a836f4816d96444d04335"],"state_sha256":"45f0451624795c26c769c7e846240dd4a4cb8f91ca7e67ed735881ab8b8696a4"}