{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4Z2HBQNAZ6HT5WOKQB7ZIJUEOO","short_pith_number":"pith:4Z2HBQNA","schema_version":"1.0","canonical_sha256":"e67470c1a0cf8f3ed9ca807f942684738f11ccec15a344154c0e07bb488bc71c","source":{"kind":"arxiv","id":"2010.00747","version":2},"attestation_state":"computed","paper":{"title":"Contrastive Learning of Medical Visual Representations from Paired Images and Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Christopher D. Manning, Curtis P. Langlotz, Hang Jiang, Yasuhide Miura, Yuhao Zhang","submitted_at":"2020-10-02T02:10:18Z","abstract_excerpt":"Learning visual representations of medical images (e.g., X-rays) is core to medical image understanding but its progress has been held back by the scarcity of human annotations. Existing work commonly relies on fine-tuning weights transferred from ImageNet pretraining, which is suboptimal due to drastically different image characteristics, or rule-based label extraction from the textual report data paired with medical images, which is inaccurate and hard to generalize. Meanwhile, several recent studies show exciting results from unsupervised contrastive learning from natural images, but we fin"},"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":"2010.00747","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-02T02:10:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"a7564ea6fa8d9345d654ceaea2cf2961f3a87dc7b5f53286fd472ec79ea0b555","abstract_canon_sha256":"ad7e845dee5e1085c1008a2e5ae19c62d07a7e75b5f21396bb1b2026e854fc0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:51.789974Z","signature_b64":"8rnbxSHX+13hMKUZxR9sIamDC/m1EEfS1+ULrv5+wRvulYzjbOwPe9QQRDxzxaczaqiUt3Ad4BO1HLoZQzxXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e67470c1a0cf8f3ed9ca807f942684738f11ccec15a344154c0e07bb488bc71c","last_reissued_at":"2026-07-05T04:58:51.789553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:51.789553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Learning of Medical Visual Representations from Paired Images and Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Christopher D. Manning, Curtis P. Langlotz, Hang Jiang, Yasuhide Miura, Yuhao Zhang","submitted_at":"2020-10-02T02:10:18Z","abstract_excerpt":"Learning visual representations of medical images (e.g., X-rays) is core to medical image understanding but its progress has been held back by the scarcity of human annotations. Existing work commonly relies on fine-tuning weights transferred from ImageNet pretraining, which is suboptimal due to drastically different image characteristics, or rule-based label extraction from the textual report data paired with medical images, which is inaccurate and hard to generalize. Meanwhile, several recent studies show exciting results from unsupervised contrastive learning from natural images, but we fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.00747","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/2010.00747/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":"2010.00747","created_at":"2026-07-05T04:58:51.789626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.00747v2","created_at":"2026-07-05T04:58:51.789626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.00747","created_at":"2026-07-05T04:58:51.789626+00:00"},{"alias_kind":"pith_short_12","alias_value":"4Z2HBQNAZ6HT","created_at":"2026-07-05T04:58:51.789626+00:00"},{"alias_kind":"pith_short_16","alias_value":"4Z2HBQNAZ6HT5WOK","created_at":"2026-07-05T04:58:51.789626+00:00"},{"alias_kind":"pith_short_8","alias_value":"4Z2HBQNA","created_at":"2026-07-05T04:58:51.789626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08420","citing_title":"CheXanatomy: Anatomy-Aware Vision-Language Modeling for Chest Radiographs","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01537","citing_title":"PaCX-MAE: Physiology-Augmented Chest X-Ray Masked Autoencoder","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18878","citing_title":"Prognostic Value of Lung Ultrasound Biomarkers for Readmission Risk in Congestive Heart Failure: A Pilot Data-Driven Analysis","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16671","citing_title":"Demystifying CLIP Data","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2303.00915","citing_title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02126","citing_title":"Ultrasound Vision-Language Alignment via Contrastive Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2407.07726","citing_title":"PaliGemma: A versatile 3B VLM for transfer","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2204.06125","citing_title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4Z2HBQNAZ6HT5WOKQB7ZIJUEOO","json":"https://pith.science/pith/4Z2HBQNAZ6HT5WOKQB7ZIJUEOO.json","graph_json":"https://pith.science/api/pith-number/4Z2HBQNAZ6HT5WOKQB7ZIJUEOO/graph.json","events_json":"https://pith.science/api/pith-number/4Z2HBQNAZ6HT5WOKQB7ZIJUEOO/events.json","paper":"https://pith.science/paper/4Z2HBQNA"},"agent_actions":{"view_html":"https://pith.science/pith/4Z2HBQNAZ6HT5WOKQB7ZIJUEOO","download_json":"https://pith.science/pith/4Z2HBQNAZ6HT5WOKQB7ZIJUEOO.json","view_paper":"https://pith.science/paper/4Z2HBQNA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.00747&json=true","fetch_graph":"https://pith.science/api/pith-number/4Z2HBQNAZ6HT5WOKQB7ZIJUEOO/graph.json","fetch_events":"https://pith.science/api/pith-number/4Z2HBQNAZ6HT5WOKQB7ZIJUEOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4Z2HBQNAZ6HT5WOKQB7ZIJUEOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4Z2HBQNAZ6HT5WOKQB7ZIJUEOO/action/storage_attestation","attest_author":"https://pith.science/pith/4Z2HBQNAZ6HT5WOKQB7ZIJUEOO/action/author_attestation","sign_citation":"https://pith.science/pith/4Z2HBQNAZ6HT5WOKQB7ZIJUEOO/action/citation_signature","submit_replication":"https://pith.science/pith/4Z2HBQNAZ6HT5WOKQB7ZIJUEOO/action/replication_record"}},"created_at":"2026-07-05T04:58:51.789626+00:00","updated_at":"2026-07-05T04:58:51.789626+00:00"}