{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2CHUESDIPZYPCMLZMAXQ32HFI2","short_pith_number":"pith:2CHUESDI","schema_version":"1.0","canonical_sha256":"d08f4248687e70f13179602f0de8e546b314005ea91e49a265dc1853e39eb357","source":{"kind":"arxiv","id":"2303.07240","version":1},"attestation_state":"computed","paper":{"title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chaoyi Wu, Weidi Xie, Weixiong Lin, Xiaoman Zhang, Yanfeng Wang, Ya Zhang, Ziheng Zhao","submitted_at":"2023-03-13T16:13:16Z","abstract_excerpt":"Foundation models trained on large-scale dataset gain a recent surge in CV and NLP. In contrast, development in biomedical domain lags far behind due to data scarcity. To address this issue, we build and release PMC-OA, a biomedical dataset with 1.6M image-caption pairs collected from PubMedCentral's OpenAccess subset, which is 8 times larger than before. PMC-OA covers diverse modalities or diseases, with majority of the image-caption samples aligned at finer-grained level, i.e., subfigure and subcaption. While pretraining a CLIP-style model on PMC-OA, our model named PMC-CLIP achieves state-o"},"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":"2303.07240","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T16:13:16Z","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"2948edaab19b4607eab65f9ef1ce4d318d2afa22fd0654bd24048bebba38dcea","abstract_canon_sha256":"6e47ad1babc1aefe70fff813522f22fd02a67b193ed58b3dba548781df4ebc18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:34.142968Z","signature_b64":"QBoibWo2QC05hThg+u8YcGN82kmEV7nxjs1jn4aG8iyagTN7rWmw6ah6jbh7MNx8zolXNeiWpOkzvwa6CSJVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d08f4248687e70f13179602f0de8e546b314005ea91e49a265dc1853e39eb357","last_reissued_at":"2026-07-05T05:50:34.142535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:34.142535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chaoyi Wu, Weidi Xie, Weixiong Lin, Xiaoman Zhang, Yanfeng Wang, Ya Zhang, Ziheng Zhao","submitted_at":"2023-03-13T16:13:16Z","abstract_excerpt":"Foundation models trained on large-scale dataset gain a recent surge in CV and NLP. In contrast, development in biomedical domain lags far behind due to data scarcity. To address this issue, we build and release PMC-OA, a biomedical dataset with 1.6M image-caption pairs collected from PubMedCentral's OpenAccess subset, which is 8 times larger than before. PMC-OA covers diverse modalities or diseases, with majority of the image-caption samples aligned at finer-grained level, i.e., subfigure and subcaption. While pretraining a CLIP-style model on PMC-OA, our model named PMC-CLIP achieves state-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07240","kind":"arxiv","version":1},"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/2303.07240/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":"2303.07240","created_at":"2026-07-05T05:50:34.142599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.07240v1","created_at":"2026-07-05T05:50:34.142599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07240","created_at":"2026-07-05T05:50:34.142599+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CHUESDIPZYP","created_at":"2026-07-05T05:50:34.142599+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CHUESDIPZYPCMLZ","created_at":"2026-07-05T05:50:34.142599+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CHUESDI","created_at":"2026-07-05T05:50:34.142599+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19522","citing_title":"REVEAL++: Differentiable Phenotypic Grouping for Vision-Language Retinal Modeling of Alzheimer's Disease Risk","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02458","citing_title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15561","citing_title":"RoiMAM: Region-of-Interest Medical Attention Model for Efficient Vision-Language Understanding","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15736","citing_title":"BiomedAP: A Vision-Informed Dual-Anchor Framework with Gated Cross-Modal Fusion for Robust Medical Vision-Language Adaptation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19359","citing_title":"MAM-CLIP: Vision-Language Pretraining on Mammography Atlases for BI-RADS Classification","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09622","citing_title":"Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18757","citing_title":"REVEAL: Multimodal Vision-Language Alignment of Retinal Morphometry and Clinical Risks for Incident AD and Dementia Prediction","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04447","citing_title":"Deep Reprogramming Distillation for Medical Foundation Models","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CHUESDIPZYPCMLZMAXQ32HFI2","json":"https://pith.science/pith/2CHUESDIPZYPCMLZMAXQ32HFI2.json","graph_json":"https://pith.science/api/pith-number/2CHUESDIPZYPCMLZMAXQ32HFI2/graph.json","events_json":"https://pith.science/api/pith-number/2CHUESDIPZYPCMLZMAXQ32HFI2/events.json","paper":"https://pith.science/paper/2CHUESDI"},"agent_actions":{"view_html":"https://pith.science/pith/2CHUESDIPZYPCMLZMAXQ32HFI2","download_json":"https://pith.science/pith/2CHUESDIPZYPCMLZMAXQ32HFI2.json","view_paper":"https://pith.science/paper/2CHUESDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.07240&json=true","fetch_graph":"https://pith.science/api/pith-number/2CHUESDIPZYPCMLZMAXQ32HFI2/graph.json","fetch_events":"https://pith.science/api/pith-number/2CHUESDIPZYPCMLZMAXQ32HFI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CHUESDIPZYPCMLZMAXQ32HFI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CHUESDIPZYPCMLZMAXQ32HFI2/action/storage_attestation","attest_author":"https://pith.science/pith/2CHUESDIPZYPCMLZMAXQ32HFI2/action/author_attestation","sign_citation":"https://pith.science/pith/2CHUESDIPZYPCMLZMAXQ32HFI2/action/citation_signature","submit_replication":"https://pith.science/pith/2CHUESDIPZYPCMLZMAXQ32HFI2/action/replication_record"}},"created_at":"2026-07-05T05:50:34.142599+00:00","updated_at":"2026-07-05T05:50:34.142599+00:00"}