{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NBE7FLHWOCUKGPV66US6LDKEEQ","short_pith_number":"pith:NBE7FLHW","schema_version":"1.0","canonical_sha256":"6849f2acf670a8a33ebef525e58d44243a03c54af3224a379212628605123bd0","source":{"kind":"arxiv","id":"2505.00228","version":2},"attestation_state":"computed","paper":{"title":"ReXGradient-160K: A Large-Scale Publicly Available Dataset of Chest Radiographs with Free-text Reports","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Josh Miller, Juli\\'an N. Acosta, Ouwen Huang, Pranav Rajpurkar, Xiaoman Zhang","submitted_at":"2025-05-01T00:29:50Z","abstract_excerpt":"We present ReXGradient-160K, representing the largest publicly available chest X-ray dataset to date in terms of the number of patients. This dataset contains 160,000 chest X-ray studies with paired radiological reports from 109,487 unique patients across 3 U.S. health systems (79 medical sites). This comprehensive dataset includes multiple images per study and detailed radiology reports, making it particularly valuable for the development and evaluation of AI systems for medical imaging and automated report generation models. The dataset is divided into training (140,000 studies), validation "},"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":"2505.00228","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2025-05-01T00:29:50Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"177e1ed2ff9f4eaadc1d6ad18bfd258ba46c3fa6c6293516a0d8af3e485eb739","abstract_canon_sha256":"c4b832d0e1bfe55d2f25d371c92209c5deea68967c4b21295b2d7efefb55e5f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:04.673012Z","signature_b64":"1QlQmaqC73Y+6Hjp2hbG5NvPJdQHyNCvvdLW1301RCK0PPVe6uxXWz7ciK7ulLj3sCd3FE/V5gaZl0M3SfAVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6849f2acf670a8a33ebef525e58d44243a03c54af3224a379212628605123bd0","last_reissued_at":"2026-07-05T11:01:04.672509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:04.672509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReXGradient-160K: A Large-Scale Publicly Available Dataset of Chest Radiographs with Free-text Reports","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Josh Miller, Juli\\'an N. Acosta, Ouwen Huang, Pranav Rajpurkar, Xiaoman Zhang","submitted_at":"2025-05-01T00:29:50Z","abstract_excerpt":"We present ReXGradient-160K, representing the largest publicly available chest X-ray dataset to date in terms of the number of patients. This dataset contains 160,000 chest X-ray studies with paired radiological reports from 109,487 unique patients across 3 U.S. health systems (79 medical sites). This comprehensive dataset includes multiple images per study and detailed radiology reports, making it particularly valuable for the development and evaluation of AI systems for medical imaging and automated report generation models. The dataset is divided into training (140,000 studies), validation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00228","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/2505.00228/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":"2505.00228","created_at":"2026-07-05T11:01:04.672565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00228v2","created_at":"2026-07-05T11:01:04.672565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00228","created_at":"2026-07-05T11:01:04.672565+00:00"},{"alias_kind":"pith_short_12","alias_value":"NBE7FLHWOCUK","created_at":"2026-07-05T11:01:04.672565+00:00"},{"alias_kind":"pith_short_16","alias_value":"NBE7FLHWOCUKGPV6","created_at":"2026-07-05T11:01:04.672565+00:00"},{"alias_kind":"pith_short_8","alias_value":"NBE7FLHW","created_at":"2026-07-05T11:01:04.672565+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05880","citing_title":"Harrison.Rad 1.5 Technical Report: A radiology foundation model that can draft reports from images, priors and clinical context","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19460","citing_title":"Scaling Generative Foundation Models for Chest Radiography with Rectified Flow Transformers","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28393","citing_title":"Transition-Aware best-of-N sampling for Longitudinal Chest X-ray Reports","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00440","citing_title":"SDR: Set-Distance Rewards for Radiology Report Generation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09450","citing_title":"ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11304","citing_title":"CheXTemporal: A Dataset for Temporally-Grounded Reasoning in Chest Radiography","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05810","citing_title":"CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09887","citing_title":"SemEnrich: Self-Supervised Semantic Enrichment of Radiology Reports for Vision-Language Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09450","citing_title":"ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04563","citing_title":"Temporal Inversion for Learning Interval Change in Chest X-Rays","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NBE7FLHWOCUKGPV66US6LDKEEQ","json":"https://pith.science/pith/NBE7FLHWOCUKGPV66US6LDKEEQ.json","graph_json":"https://pith.science/api/pith-number/NBE7FLHWOCUKGPV66US6LDKEEQ/graph.json","events_json":"https://pith.science/api/pith-number/NBE7FLHWOCUKGPV66US6LDKEEQ/events.json","paper":"https://pith.science/paper/NBE7FLHW"},"agent_actions":{"view_html":"https://pith.science/pith/NBE7FLHWOCUKGPV66US6LDKEEQ","download_json":"https://pith.science/pith/NBE7FLHWOCUKGPV66US6LDKEEQ.json","view_paper":"https://pith.science/paper/NBE7FLHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00228&json=true","fetch_graph":"https://pith.science/api/pith-number/NBE7FLHWOCUKGPV66US6LDKEEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NBE7FLHWOCUKGPV66US6LDKEEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NBE7FLHWOCUKGPV66US6LDKEEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NBE7FLHWOCUKGPV66US6LDKEEQ/action/storage_attestation","attest_author":"https://pith.science/pith/NBE7FLHWOCUKGPV66US6LDKEEQ/action/author_attestation","sign_citation":"https://pith.science/pith/NBE7FLHWOCUKGPV66US6LDKEEQ/action/citation_signature","submit_replication":"https://pith.science/pith/NBE7FLHWOCUKGPV66US6LDKEEQ/action/replication_record"}},"created_at":"2026-07-05T11:01:04.672565+00:00","updated_at":"2026-07-05T11:01:04.672565+00:00"}