{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W2QGSKBVMX4FH5YS4SMWTYIHSA","short_pith_number":"pith:W2QGSKBV","schema_version":"1.0","canonical_sha256":"b6a069283565f853f712e49969e1079039573cfc6732b618b68b43cfd6c01fbe","source":{"kind":"arxiv","id":"2301.02228","version":3},"attestation_state":"computed","paper":{"title":"MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"eess.IV","authors_text":"Chaoyi Wu, Weidi Xie, Xiaoman Zhang, Yanfeng Wang, Ya Zhang","submitted_at":"2023-01-05T18:55:09Z","abstract_excerpt":"In this paper, we consider enhancing medical visual-language pre-training (VLP) with domain-specific knowledge, by exploiting the paired image-text reports from the radiological daily practice. In particular, we make the following contributions: First, unlike existing works that directly process the raw reports, we adopt a novel triplet extraction module to extract the medical-related information, avoiding unnecessary complexity from language grammar and enhancing the supervision signals; Second, we propose a novel triplet encoding module with entity translation by querying a knowledge base, t"},"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":"2301.02228","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2023-01-05T18:55:09Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"442ea4f4b6d25b6be9c9d90d8e91102e9aec50a2482e01dd346c45fadc70a06f","abstract_canon_sha256":"51d6d2001ad4ac139863f515d9e634d00053c50fed66be692a07583f38b4d3f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:15.378633Z","signature_b64":"uBDPNOAcZP3Wo2Nf9axZ1jXMgAa+yGoGYkqK9WoYERFYZgwynjtJKEJVXoF0PIXeDAPVaTa6aJ+OnLL7QcsGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6a069283565f853f712e49969e1079039573cfc6732b618b68b43cfd6c01fbe","last_reissued_at":"2026-07-05T05:57:15.378168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:15.378168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"eess.IV","authors_text":"Chaoyi Wu, Weidi Xie, Xiaoman Zhang, Yanfeng Wang, Ya Zhang","submitted_at":"2023-01-05T18:55:09Z","abstract_excerpt":"In this paper, we consider enhancing medical visual-language pre-training (VLP) with domain-specific knowledge, by exploiting the paired image-text reports from the radiological daily practice. In particular, we make the following contributions: First, unlike existing works that directly process the raw reports, we adopt a novel triplet extraction module to extract the medical-related information, avoiding unnecessary complexity from language grammar and enhancing the supervision signals; Second, we propose a novel triplet encoding module with entity translation by querying a knowledge base, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02228","kind":"arxiv","version":3},"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/2301.02228/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":"2301.02228","created_at":"2026-07-05T05:57:15.378227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.02228v3","created_at":"2026-07-05T05:57:15.378227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02228","created_at":"2026-07-05T05:57:15.378227+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2QGSKBVMX4F","created_at":"2026-07-05T05:57:15.378227+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2QGSKBVMX4FH5YS","created_at":"2026-07-05T05:57:15.378227+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2QGSKBV","created_at":"2026-07-05T05:57:15.378227+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26691","citing_title":"Mind the Tool Failures: Achieving Synergistic Tool Gains for Medical Agents","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05810","citing_title":"CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W2QGSKBVMX4FH5YS4SMWTYIHSA","json":"https://pith.science/pith/W2QGSKBVMX4FH5YS4SMWTYIHSA.json","graph_json":"https://pith.science/api/pith-number/W2QGSKBVMX4FH5YS4SMWTYIHSA/graph.json","events_json":"https://pith.science/api/pith-number/W2QGSKBVMX4FH5YS4SMWTYIHSA/events.json","paper":"https://pith.science/paper/W2QGSKBV"},"agent_actions":{"view_html":"https://pith.science/pith/W2QGSKBVMX4FH5YS4SMWTYIHSA","download_json":"https://pith.science/pith/W2QGSKBVMX4FH5YS4SMWTYIHSA.json","view_paper":"https://pith.science/paper/W2QGSKBV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.02228&json=true","fetch_graph":"https://pith.science/api/pith-number/W2QGSKBVMX4FH5YS4SMWTYIHSA/graph.json","fetch_events":"https://pith.science/api/pith-number/W2QGSKBVMX4FH5YS4SMWTYIHSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2QGSKBVMX4FH5YS4SMWTYIHSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2QGSKBVMX4FH5YS4SMWTYIHSA/action/storage_attestation","attest_author":"https://pith.science/pith/W2QGSKBVMX4FH5YS4SMWTYIHSA/action/author_attestation","sign_citation":"https://pith.science/pith/W2QGSKBVMX4FH5YS4SMWTYIHSA/action/citation_signature","submit_replication":"https://pith.science/pith/W2QGSKBVMX4FH5YS4SMWTYIHSA/action/replication_record"}},"created_at":"2026-07-05T05:57:15.378227+00:00","updated_at":"2026-07-05T05:57:15.378227+00:00"}