{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HLNDMTDA3WHPVQVCFOSPBNEFSW","short_pith_number":"pith:HLNDMTDA","schema_version":"1.0","canonical_sha256":"3ada364c60dd8efac2a22ba4f0b48595962e674cffad0ac580f2dc1ee3aedcc1","source":{"kind":"arxiv","id":"2312.15840","version":2},"attestation_state":"computed","paper":{"title":"Masked Contrastive Reconstruction for Cross-modal Medical Image-Report Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kai Jin, Xiuzhuang Zhou, Zeqiang Wei","submitted_at":"2023-12-26T01:14:10Z","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"},"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":"2312.15840","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-26T01:14:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9779c961af538175e66ca26416e8c2893b26caa5a374ad6e5c7008d40000e4ae","abstract_canon_sha256":"ad9e7f3b2086233afda3b817f95197d8688b7310f43c0019829f8725de7bdb8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:31.715090Z","signature_b64":"m9sM2Jcg7gs+2OUhOy9Y8MsRA5rtx7w5RAhzFN4ZdoDfR01FVbAXSDz8htg22aF5Zb1Mu799LELVdBIfoKybCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ada364c60dd8efac2a22ba4f0b48595962e674cffad0ac580f2dc1ee3aedcc1","last_reissued_at":"2026-07-05T11:05:31.714589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:31.714589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Contrastive Reconstruction for Cross-modal Medical Image-Report Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kai Jin, Xiuzhuang Zhou, Zeqiang Wei","submitted_at":"2023-12-26T01:14:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15840","kind":"arxiv","version":2},"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/2312.15840/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":"2312.15840","created_at":"2026-07-05T11:05:31.714656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.15840v2","created_at":"2026-07-05T11:05:31.714656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15840","created_at":"2026-07-05T11:05:31.714656+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLNDMTDA3WHP","created_at":"2026-07-05T11:05:31.714656+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLNDMTDA3WHPVQVC","created_at":"2026-07-05T11:05:31.714656+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLNDMTDA","created_at":"2026-07-05T11:05:31.714656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03492","citing_title":"Quality Versus Sparsity in Image Recovery by Dictionary Learning Using Iterative Shrinkage","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HLNDMTDA3WHPVQVCFOSPBNEFSW","json":"https://pith.science/pith/HLNDMTDA3WHPVQVCFOSPBNEFSW.json","graph_json":"https://pith.science/api/pith-number/HLNDMTDA3WHPVQVCFOSPBNEFSW/graph.json","events_json":"https://pith.science/api/pith-number/HLNDMTDA3WHPVQVCFOSPBNEFSW/events.json","paper":"https://pith.science/paper/HLNDMTDA"},"agent_actions":{"view_html":"https://pith.science/pith/HLNDMTDA3WHPVQVCFOSPBNEFSW","download_json":"https://pith.science/pith/HLNDMTDA3WHPVQVCFOSPBNEFSW.json","view_paper":"https://pith.science/paper/HLNDMTDA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.15840&json=true","fetch_graph":"https://pith.science/api/pith-number/HLNDMTDA3WHPVQVCFOSPBNEFSW/graph.json","fetch_events":"https://pith.science/api/pith-number/HLNDMTDA3WHPVQVCFOSPBNEFSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLNDMTDA3WHPVQVCFOSPBNEFSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLNDMTDA3WHPVQVCFOSPBNEFSW/action/storage_attestation","attest_author":"https://pith.science/pith/HLNDMTDA3WHPVQVCFOSPBNEFSW/action/author_attestation","sign_citation":"https://pith.science/pith/HLNDMTDA3WHPVQVCFOSPBNEFSW/action/citation_signature","submit_replication":"https://pith.science/pith/HLNDMTDA3WHPVQVCFOSPBNEFSW/action/replication_record"}},"created_at":"2026-07-05T11:05:31.714656+00:00","updated_at":"2026-07-05T11:05:31.714656+00:00"}