{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:27VZKU34OVNW73436WUSTFXXCD","short_pith_number":"pith:27VZKU34","canonical_record":{"source":{"id":"1901.07042","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-21T19:01:00Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"24cfb386d9a7373fa8fa9d036b1aa0ee88e836ad71c982b120129e6ecd275082","abstract_canon_sha256":"639dce0f9864968c4a8b6512ba0a98f110bd85dfc65d509a73d3b861224262a9"},"schema_version":"1.0"},"canonical_sha256":"d7eb95537c755b6fef9bf5a92996f710f74d777ac296a0b8b300363a1b3f5af9","source":{"kind":"arxiv","id":"1901.07042","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.07042","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"arxiv_version","alias_value":"1901.07042v5","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07042","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"pith_short_12","alias_value":"27VZKU34OVNW","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"27VZKU34OVNW7343","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"27VZKU34","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:27VZKU34OVNW73436WUSTFXXCD","target":"record","payload":{"canonical_record":{"source":{"id":"1901.07042","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-21T19:01:00Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"24cfb386d9a7373fa8fa9d036b1aa0ee88e836ad71c982b120129e6ecd275082","abstract_canon_sha256":"639dce0f9864968c4a8b6512ba0a98f110bd85dfc65d509a73d3b861224262a9"},"schema_version":"1.0"},"canonical_sha256":"d7eb95537c755b6fef9bf5a92996f710f74d777ac296a0b8b300363a1b3f5af9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:15.154807Z","signature_b64":"L3d9gnf2/DMfu6JEDaQdkPnyWLeyLUzHXoIs9ltxLbkmZYYmuM8XI6wC1IaWVtzRNRHJ1ipH9urbfsMTJ+J7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7eb95537c755b6fef9bf5a92996f710f74d777ac296a0b8b300363a1b3f5af9","last_reissued_at":"2026-05-17T23:38:15.154275Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:15.154275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.07042","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nhpG9rSybUuLp9A3PKIitqsptxRyFP+NptwCOR6q9CDF8tfJqlPW1sQMGmo7kr9png7xpPMLYdEmyry0wbs9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T10:46:58.161120Z"},"content_sha256":"4926033ea86f1d9ce9070fc636284423c39c791d13cc9e379c57a84bbe7f5fe3","schema_version":"1.0","event_id":"sha256:4926033ea86f1d9ce9070fc636284423c39c791d13cc9e379c57a84bbe7f5fe3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:27VZKU34OVNW73436WUSTFXXCD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A large dataset of 377,110 labeled chest x-rays is now publicly available for medical computer vision research.","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Alistair E. W. Johnson, Chih-ying Deng, Matthew P. Lungren, Nathaniel R. Greenbaum, Roger G. Mark, Seth J. Berkowitz, Steven Horng, Tom J. Pollard, Yifan Peng, Zhiyong Lu","submitted_at":"2019-01-21T19:01:00Z","abstract_excerpt":"Chest radiography is an extremely powerful imaging modality, allowing for a detailed inspection of a patient's thorax, but requiring specialized training for proper interpretation. With the advent of high performance general purpose computer vision algorithms, the accurate automated analysis of chest radiographs is becoming increasingly of interest to researchers. However, a key challenge in the development of these techniques is the lack of sufficient data. Here we describe MIMIC-CXR-JPG v2.0.0, a large dataset of 377,110 chest x-rays associated with 227,827 imaging studies sourced from the B"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MIMIC-CXR-JPG v2.0.0 is a large dataset of 377,110 chest x-rays associated with 227,827 imaging studies... Images are provided with 14 labels derived from two natural language processing tools applied to the corresponding free-text radiology reports.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 14 labels produced by the two NLP tools accurately capture the clinical content of the radiology reports and correspond to verifiable findings in the images.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MIMIC-CXR-JPG provides 377,110 labeled chest X-rays derived from MIMIC-CXR with NLP-generated labels and standard splits for medical imaging AI development.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A large dataset of 377,110 labeled chest x-rays is now publicly available for medical computer vision research.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"bea0fbe2f0ce4ffe3f8cf2d3acdf66e289dc94a2c25b0924c537285485575904"},"source":{"id":"1901.07042","kind":"arxiv","version":5},"verdict":{"id":"486278c7-eda1-46a8-b596-84564d1a4cfd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T04:11:25.530810Z","strongest_claim":"MIMIC-CXR-JPG v2.0.0 is a large dataset of 377,110 chest x-rays associated with 227,827 imaging studies... Images are provided with 14 labels derived from two natural language processing tools applied to the corresponding free-text radiology reports.","one_line_summary":"MIMIC-CXR-JPG provides 377,110 labeled chest X-rays derived from MIMIC-CXR with NLP-generated labels and standard splits for medical imaging AI development.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 14 labels produced by the two NLP tools accurately capture the clinical content of the radiology reports and correspond to verifiable findings in the images.","pith_extraction_headline":"A large dataset of 377,110 labeled chest x-rays is now publicly available for medical computer vision research."},"references":{"count":20,"sample":[{"doi":"","year":2015,"title":"The US radiologist workforce: an analysis of temporal and geographic variation by using large national datasets","work_id":"9f15271a-ed7e-4b0e-9a0e-c8130e722f6c","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"A county-level analysis of the US radiologist workforce: physician supply and subspecialty characteristics","work_id":"5fcad9a6-2e73-4864-bf18-81caaac5e278","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Radiologist shortage leaves patient care at risk, warns royal college","work_id":"ed0980c5-0a89-4536-b2fe-7b32c1c74c5a","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Improving Patient Safety: Avoiding Unread Imaging Exams in the National V A Enterprise Electronic Health Record","work_id":"325e2855-6e68-40d5-8b56-d28b655378d1","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Imaging in the land of 1000 hills: Rwanda radiology country report","work_id":"5ac6745c-c94e-4d67-8d08-03d418a86220","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":20,"snapshot_sha256":"80b67c410054b016bbbe27a921a31daac29e7aee35aeb9db462b662cae487411","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"c5e2ea1e29b793a94a9578329f2dd94966b37161a5edfd0f3ef16506b40ee1f3"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"486278c7-eda1-46a8-b596-84564d1a4cfd"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FjDPam/6fqCP4wwBtsbMyKY/dRGNNBmvlkusQKPWxOfdtjRFx8KFiLnTUTVDatzmMA3m96cs6a7f39pR81X5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T10:46:58.162191Z"},"content_sha256":"ebbf6e25a1a699ec7de40b9f01c2af8d43bf72081a099cad9a3a192a4960ac20","schema_version":"1.0","event_id":"sha256:ebbf6e25a1a699ec7de40b9f01c2af8d43bf72081a099cad9a3a192a4960ac20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/27VZKU34OVNW73436WUSTFXXCD/bundle.json","state_url":"https://pith.science/pith/27VZKU34OVNW73436WUSTFXXCD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/27VZKU34OVNW73436WUSTFXXCD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-24T10:46:58Z","links":{"resolver":"https://pith.science/pith/27VZKU34OVNW73436WUSTFXXCD","bundle":"https://pith.science/pith/27VZKU34OVNW73436WUSTFXXCD/bundle.json","state":"https://pith.science/pith/27VZKU34OVNW73436WUSTFXXCD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/27VZKU34OVNW73436WUSTFXXCD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:27VZKU34OVNW73436WUSTFXXCD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"639dce0f9864968c4a8b6512ba0a98f110bd85dfc65d509a73d3b861224262a9","cross_cats_sorted":["cs.LG","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-21T19:01:00Z","title_canon_sha256":"24cfb386d9a7373fa8fa9d036b1aa0ee88e836ad71c982b120129e6ecd275082"},"schema_version":"1.0","source":{"id":"1901.07042","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.07042","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"arxiv_version","alias_value":"1901.07042v5","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07042","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"pith_short_12","alias_value":"27VZKU34OVNW","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"27VZKU34OVNW7343","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"27VZKU34","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:ebbf6e25a1a699ec7de40b9f01c2af8d43bf72081a099cad9a3a192a4960ac20","target":"graph","created_at":"2026-05-17T23:38:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"MIMIC-CXR-JPG v2.0.0 is a large dataset of 377,110 chest x-rays associated with 227,827 imaging studies... Images are provided with 14 labels derived from two natural language processing tools applied to the corresponding free-text radiology reports."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The 14 labels produced by the two NLP tools accurately capture the clinical content of the radiology reports and correspond to verifiable findings in the images."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MIMIC-CXR-JPG provides 377,110 labeled chest X-rays derived from MIMIC-CXR with NLP-generated labels and standard splits for medical imaging AI development."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A large dataset of 377,110 labeled chest x-rays is now publicly available for medical computer vision research."}],"snapshot_sha256":"bea0fbe2f0ce4ffe3f8cf2d3acdf66e289dc94a2c25b0924c537285485575904"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"c5e2ea1e29b793a94a9578329f2dd94966b37161a5edfd0f3ef16506b40ee1f3"},"paper":{"abstract_excerpt":"Chest radiography is an extremely powerful imaging modality, allowing for a detailed inspection of a patient's thorax, but requiring specialized training for proper interpretation. With the advent of high performance general purpose computer vision algorithms, the accurate automated analysis of chest radiographs is becoming increasingly of interest to researchers. However, a key challenge in the development of these techniques is the lack of sufficient data. Here we describe MIMIC-CXR-JPG v2.0.0, a large dataset of 377,110 chest x-rays associated with 227,827 imaging studies sourced from the B","authors_text":"Alistair E. W. Johnson, Chih-ying Deng, Matthew P. Lungren, Nathaniel R. Greenbaum, Roger G. Mark, Seth J. Berkowitz, Steven Horng, Tom J. Pollard, Yifan Peng, Zhiyong Lu","cross_cats":["cs.LG","eess.IV"],"headline":"A large dataset of 377,110 labeled chest x-rays is now publicly available for medical computer vision research.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-21T19:01:00Z","title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs"},"references":{"count":20,"internal_anchors":0,"resolved_work":20,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"The US radiologist workforce: an analysis of temporal and geographic variation by using large national datasets","work_id":"9f15271a-ed7e-4b0e-9a0e-c8130e722f6c","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"A county-level analysis of the US radiologist workforce: physician supply and subspecialty characteristics","work_id":"5fcad9a6-2e73-4864-bf18-81caaac5e278","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Radiologist shortage leaves patient care at risk, warns royal college","work_id":"ed0980c5-0a89-4536-b2fe-7b32c1c74c5a","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Improving Patient Safety: Avoiding Unread Imaging Exams in the National V A Enterprise Electronic Health Record","work_id":"325e2855-6e68-40d5-8b56-d28b655378d1","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Imaging in the land of 1000 hills: Rwanda radiology country report","work_id":"5ac6745c-c94e-4d67-8d08-03d418a86220","year":2015}],"snapshot_sha256":"80b67c410054b016bbbe27a921a31daac29e7aee35aeb9db462b662cae487411"},"source":{"id":"1901.07042","kind":"arxiv","version":5},"verdict":{"created_at":"2026-05-17T04:11:25.530810Z","id":"486278c7-eda1-46a8-b596-84564d1a4cfd","model_set":{"reader":"grok-4.3"},"one_line_summary":"MIMIC-CXR-JPG provides 377,110 labeled chest X-rays derived from MIMIC-CXR with NLP-generated labels and standard splits for medical imaging AI development.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A large dataset of 377,110 labeled chest x-rays is now publicly available for medical computer vision research.","strongest_claim":"MIMIC-CXR-JPG v2.0.0 is a large dataset of 377,110 chest x-rays associated with 227,827 imaging studies... Images are provided with 14 labels derived from two natural language processing tools applied to the corresponding free-text radiology reports.","weakest_assumption":"The 14 labels produced by the two NLP tools accurately capture the clinical content of the radiology reports and correspond to verifiable findings in the images."}},"verdict_id":"486278c7-eda1-46a8-b596-84564d1a4cfd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4926033ea86f1d9ce9070fc636284423c39c791d13cc9e379c57a84bbe7f5fe3","target":"record","created_at":"2026-05-17T23:38:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"639dce0f9864968c4a8b6512ba0a98f110bd85dfc65d509a73d3b861224262a9","cross_cats_sorted":["cs.LG","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-21T19:01:00Z","title_canon_sha256":"24cfb386d9a7373fa8fa9d036b1aa0ee88e836ad71c982b120129e6ecd275082"},"schema_version":"1.0","source":{"id":"1901.07042","kind":"arxiv","version":5}},"canonical_sha256":"d7eb95537c755b6fef9bf5a92996f710f74d777ac296a0b8b300363a1b3f5af9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7eb95537c755b6fef9bf5a92996f710f74d777ac296a0b8b300363a1b3f5af9","first_computed_at":"2026-05-17T23:38:15.154275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:15.154275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L3d9gnf2/DMfu6JEDaQdkPnyWLeyLUzHXoIs9ltxLbkmZYYmuM8XI6wC1IaWVtzRNRHJ1ipH9urbfsMTJ+J7DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:15.154807Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.07042","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4926033ea86f1d9ce9070fc636284423c39c791d13cc9e379c57a84bbe7f5fe3","sha256:ebbf6e25a1a699ec7de40b9f01c2af8d43bf72081a099cad9a3a192a4960ac20"],"state_sha256":"a67e58b26284e7c1ac9cd8623980e85fef1287b5ec1a00bef593cc5dac5eb6e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kl78cIsb79L3tWvm7xrfz5sj0+f60D1Z3UoMUVj1Lg7EY4315W5ZoLCEv23xvNT4+mO2eNGEUjOglT3keNvXAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T10:46:58.166756Z","bundle_sha256":"335e6cb085fc8ab081681a26cd1c8530ffd15cb421365dd0ee5f02dc24817149"}}