{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YJU2QJ6IBXAXLHRARFTYSNSWCG","short_pith_number":"pith:YJU2QJ6I","schema_version":"1.0","canonical_sha256":"c269a827c80dc1759e2089678936561190e6b1f6245e61cafb0bd1edf3d9ffc6","source":{"kind":"arxiv","id":"2305.08017","version":1},"attestation_state":"computed","paper":{"title":"How to Train Your CheXDragon: Training Chest X-Ray Models for Transfer to Novel Tasks and Healthcare Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Ng, Cara Van Uden, Curtis Langlotz, Jason Carr, Jeremy Irvin, Mars Huang, Nathan Dean","submitted_at":"2023-05-13T22:33:09Z","abstract_excerpt":"Self-supervised learning (SSL) enables label efficient training for machine learning models. This is essential for domains such as medical imaging, where labels are costly and time-consuming to curate. However, the most effective supervised or SSL strategy for transferring models to different healthcare systems or novel tasks is not well understood. In this work, we systematically experiment with a variety of supervised and self-supervised pretraining strategies using multimodal datasets of medical images (chest X-rays) and text (radiology reports). We then evaluate their performance on data f"},"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":"2305.08017","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-13T22:33:09Z","cross_cats_sorted":[],"title_canon_sha256":"7151a45d13bfcd0d2a5c744b7625fa9959ca1e5304c8d2353e170279cda07f22","abstract_canon_sha256":"150e7eb86a9351122979b9adbc623c0124ce514fc10fc17a976021dfb2c8a0bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:57.035199Z","signature_b64":"VC9NyocHMbVGmGgJ4cH+n1tTjIfDNmI7SSg2pRwD/rWjCQkl4i7EsR5lq2slxZqBgsMJ+DqgYefFCchEyt01BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c269a827c80dc1759e2089678936561190e6b1f6245e61cafb0bd1edf3d9ffc6","last_reissued_at":"2026-07-05T06:09:57.034780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:57.034780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Train Your CheXDragon: Training Chest X-Ray Models for Transfer to Novel Tasks and Healthcare Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Ng, Cara Van Uden, Curtis Langlotz, Jason Carr, Jeremy Irvin, Mars Huang, Nathan Dean","submitted_at":"2023-05-13T22:33:09Z","abstract_excerpt":"Self-supervised learning (SSL) enables label efficient training for machine learning models. This is essential for domains such as medical imaging, where labels are costly and time-consuming to curate. However, the most effective supervised or SSL strategy for transferring models to different healthcare systems or novel tasks is not well understood. In this work, we systematically experiment with a variety of supervised and self-supervised pretraining strategies using multimodal datasets of medical images (chest X-rays) and text (radiology reports). We then evaluate their performance on data f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08017","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/2305.08017/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":"2305.08017","created_at":"2026-07-05T06:09:57.034834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.08017v1","created_at":"2026-07-05T06:09:57.034834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08017","created_at":"2026-07-05T06:09:57.034834+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJU2QJ6IBXAX","created_at":"2026-07-05T06:09:57.034834+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJU2QJ6IBXAXLHRA","created_at":"2026-07-05T06:09:57.034834+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJU2QJ6I","created_at":"2026-07-05T06:09:57.034834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJU2QJ6IBXAXLHRARFTYSNSWCG","json":"https://pith.science/pith/YJU2QJ6IBXAXLHRARFTYSNSWCG.json","graph_json":"https://pith.science/api/pith-number/YJU2QJ6IBXAXLHRARFTYSNSWCG/graph.json","events_json":"https://pith.science/api/pith-number/YJU2QJ6IBXAXLHRARFTYSNSWCG/events.json","paper":"https://pith.science/paper/YJU2QJ6I"},"agent_actions":{"view_html":"https://pith.science/pith/YJU2QJ6IBXAXLHRARFTYSNSWCG","download_json":"https://pith.science/pith/YJU2QJ6IBXAXLHRARFTYSNSWCG.json","view_paper":"https://pith.science/paper/YJU2QJ6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.08017&json=true","fetch_graph":"https://pith.science/api/pith-number/YJU2QJ6IBXAXLHRARFTYSNSWCG/graph.json","fetch_events":"https://pith.science/api/pith-number/YJU2QJ6IBXAXLHRARFTYSNSWCG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJU2QJ6IBXAXLHRARFTYSNSWCG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJU2QJ6IBXAXLHRARFTYSNSWCG/action/storage_attestation","attest_author":"https://pith.science/pith/YJU2QJ6IBXAXLHRARFTYSNSWCG/action/author_attestation","sign_citation":"https://pith.science/pith/YJU2QJ6IBXAXLHRARFTYSNSWCG/action/citation_signature","submit_replication":"https://pith.science/pith/YJU2QJ6IBXAXLHRARFTYSNSWCG/action/replication_record"}},"created_at":"2026-07-05T06:09:57.034834+00:00","updated_at":"2026-07-05T06:09:57.034834+00:00"}