{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RGDC7DJQQZFGPLH75MZYSF4MG6","short_pith_number":"pith:RGDC7DJQ","schema_version":"1.0","canonical_sha256":"89862f8d30864a67acffeb3389178c37900f12bbb2a95e0324cefb058b25037e","source":{"kind":"arxiv","id":"1901.07031","version":1},"attestation_state":"computed","paper":{"title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Andrew Y. Ng, Behzad Haghgoo, Bhavik N. Patel, Chris Chute, Curtis P. Langlotz, David A. Mong, David B. Larson, Henrik Marklund, Jayne Seekins, Jeremy Irvin, Jesse K. Sandberg, Katie Shpanskaya, Matthew P. Lungren, Michael Ko, Pranav Rajpurkar, Ricky Jones, Robyn Ball, Safwan S. Halabi, Silviana Ciurea-Ilcus, Yifan Yu","submitted_at":"2019-01-21T18:41:59Z","abstract_excerpt":"Large, labeled datasets have driven deep learning methods to achieve expert-level performance on a variety of medical imaging tasks. We present CheXpert, a large dataset that contains 224,316 chest radiographs of 65,240 patients. We design a labeler to automatically detect the presence of 14 observations in radiology reports, capturing uncertainties inherent in radiograph interpretation. We investigate different approaches to using the uncertainty labels for training convolutional neural networks that output the probability of these observations given the available frontal and lateral radiogra"},"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":"1901.07031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-01-21T18:41:59Z","cross_cats_sorted":["cs.AI","cs.LG","eess.IV"],"title_canon_sha256":"59fd0857006a2abdc544370132242ec4a28858a9136d94775a854b4534cccfd5","abstract_canon_sha256":"c66780679ecfe89b2f8ba0cb626cb375c764c8bcbe45c7f5919fc0e723d08421"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:48.344043Z","signature_b64":"oWrEhR/TTwCiRVc2hM9nbAfGPhIbtFTz3vPXLDElPK8oZ5N09lOYSMmndXIHhKd7Ec/hBG2PpB70wi7sic7BDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89862f8d30864a67acffeb3389178c37900f12bbb2a95e0324cefb058b25037e","last_reissued_at":"2026-05-17T23:55:48.343528Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:48.343528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Andrew Y. Ng, Behzad Haghgoo, Bhavik N. Patel, Chris Chute, Curtis P. Langlotz, David A. Mong, David B. Larson, Henrik Marklund, Jayne Seekins, Jeremy Irvin, Jesse K. Sandberg, Katie Shpanskaya, Matthew P. Lungren, Michael Ko, Pranav Rajpurkar, Ricky Jones, Robyn Ball, Safwan S. Halabi, Silviana Ciurea-Ilcus, Yifan Yu","submitted_at":"2019-01-21T18:41:59Z","abstract_excerpt":"Large, labeled datasets have driven deep learning methods to achieve expert-level performance on a variety of medical imaging tasks. We present CheXpert, a large dataset that contains 224,316 chest radiographs of 65,240 patients. We design a labeler to automatically detect the presence of 14 observations in radiology reports, capturing uncertainties inherent in radiograph interpretation. We investigate different approaches to using the uncertainty labels for training convolutional neural networks that output the probability of these observations given the available frontal and lateral radiogra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07031","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":""},"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":"1901.07031","created_at":"2026-05-17T23:55:48.343614+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.07031v1","created_at":"2026-05-17T23:55:48.343614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07031","created_at":"2026-05-17T23:55:48.343614+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGDC7DJQQZFG","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGDC7DJQQZFGPLH7","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGDC7DJQ","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.09085","citing_title":"Automatic Radiology Report Generation based on Multi-view Image Fusion and Medical Concept Enrichment","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2408.16213","citing_title":"M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretation","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19201","citing_title":"On-Device Continual Learning with Dual-Stage Buffer and Dynamic Loss for Point-of-Care Pneumonia Diagnosis","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11304","citing_title":"CheXTemporal: A Dataset for Temporally-Grounded Reasoning in Chest Radiography","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10142","citing_title":"Scaling Vision Models Does Not Consistently Improve Localisation-Based Explanation Quality","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26288","citing_title":"CheXthought: A global multimodal dataset of clinical chain-of-thought reasoning and visual attention for chest X-ray interpretation","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RGDC7DJQQZFGPLH75MZYSF4MG6","json":"https://pith.science/pith/RGDC7DJQQZFGPLH75MZYSF4MG6.json","graph_json":"https://pith.science/api/pith-number/RGDC7DJQQZFGPLH75MZYSF4MG6/graph.json","events_json":"https://pith.science/api/pith-number/RGDC7DJQQZFGPLH75MZYSF4MG6/events.json","paper":"https://pith.science/paper/RGDC7DJQ"},"agent_actions":{"view_html":"https://pith.science/pith/RGDC7DJQQZFGPLH75MZYSF4MG6","download_json":"https://pith.science/pith/RGDC7DJQQZFGPLH75MZYSF4MG6.json","view_paper":"https://pith.science/paper/RGDC7DJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.07031&json=true","fetch_graph":"https://pith.science/api/pith-number/RGDC7DJQQZFGPLH75MZYSF4MG6/graph.json","fetch_events":"https://pith.science/api/pith-number/RGDC7DJQQZFGPLH75MZYSF4MG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGDC7DJQQZFGPLH75MZYSF4MG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGDC7DJQQZFGPLH75MZYSF4MG6/action/storage_attestation","attest_author":"https://pith.science/pith/RGDC7DJQQZFGPLH75MZYSF4MG6/action/author_attestation","sign_citation":"https://pith.science/pith/RGDC7DJQQZFGPLH75MZYSF4MG6/action/citation_signature","submit_replication":"https://pith.science/pith/RGDC7DJQQZFGPLH75MZYSF4MG6/action/replication_record"}},"created_at":"2026-05-17T23:55:48.343614+00:00","updated_at":"2026-05-17T23:55:48.343614+00:00"}