{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RAVMWCCQLGCL42QQHUWRTV7ICH","short_pith_number":"pith:RAVMWCCQ","schema_version":"1.0","canonical_sha256":"882acb08505984be6a103d2d19d7e811c056e26ebb10687b26bda0620a705dbc","source":{"kind":"arxiv","id":"2507.02987","version":3},"attestation_state":"computed","paper":{"title":"Leveraging the Structure of Medical Data for Improved Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alain Ryser, Andrea Agostini, Farhad Nooralahzadeh, Julia E. Vogt, Michael Krauthammer, Moritz Vandenhirtz, Nicolas Deperrois, Samuel Ruiperez-Campillo, Sonia Laguna, Thomas M. Sutter","submitted_at":"2025-07-01T11:14:45Z","abstract_excerpt":"Building generalizable medical AI systems requires pretraining strategies that are data-efficient and domain-aware. Unlike internet-scale corpora, clinical datasets such as MIMIC-CXR offer limited image counts and scarce annotations, but exhibit rich internal structure through multi-view imaging. We propose a self-supervised framework that leverages the inherent structure of medical datasets. Specifically, we treat paired chest X-rays (i.e., frontal and lateral views) as natural positive pairs, learning to reconstruct each view from sparse patches while aligning their latent embeddings. Our me"},"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":"2507.02987","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T11:14:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cc6a23626ea71d3de65eb089743296277c094c50c30ab0420ebcc78e4ecd68a0","abstract_canon_sha256":"b15094af2b15e98d1f6ee535da93a5249656d116005502ebaf3d00cd4135cb56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:31.821929Z","signature_b64":"u5xinp0GvyMuVQOYJvz+sawCTq7CfSwiOFS7t46S81ueJ58ABq4jR5L3oHDBsvo6xMhcKEXwwyFDN+anHE+KCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"882acb08505984be6a103d2d19d7e811c056e26ebb10687b26bda0620a705dbc","last_reissued_at":"2026-07-05T11:42:31.821386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:31.821386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging the Structure of Medical Data for Improved Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alain Ryser, Andrea Agostini, Farhad Nooralahzadeh, Julia E. Vogt, Michael Krauthammer, Moritz Vandenhirtz, Nicolas Deperrois, Samuel Ruiperez-Campillo, Sonia Laguna, Thomas M. Sutter","submitted_at":"2025-07-01T11:14:45Z","abstract_excerpt":"Building generalizable medical AI systems requires pretraining strategies that are data-efficient and domain-aware. Unlike internet-scale corpora, clinical datasets such as MIMIC-CXR offer limited image counts and scarce annotations, but exhibit rich internal structure through multi-view imaging. We propose a self-supervised framework that leverages the inherent structure of medical datasets. Specifically, we treat paired chest X-rays (i.e., frontal and lateral views) as natural positive pairs, learning to reconstruct each view from sparse patches while aligning their latent embeddings. Our me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02987","kind":"arxiv","version":3},"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/2507.02987/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":"2507.02987","created_at":"2026-07-05T11:42:31.821449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02987v3","created_at":"2026-07-05T11:42:31.821449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02987","created_at":"2026-07-05T11:42:31.821449+00:00"},{"alias_kind":"pith_short_12","alias_value":"RAVMWCCQLGCL","created_at":"2026-07-05T11:42:31.821449+00:00"},{"alias_kind":"pith_short_16","alias_value":"RAVMWCCQLGCL42QQ","created_at":"2026-07-05T11:42:31.821449+00:00"},{"alias_kind":"pith_short_8","alias_value":"RAVMWCCQ","created_at":"2026-07-05T11:42:31.821449+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/RAVMWCCQLGCL42QQHUWRTV7ICH","json":"https://pith.science/pith/RAVMWCCQLGCL42QQHUWRTV7ICH.json","graph_json":"https://pith.science/api/pith-number/RAVMWCCQLGCL42QQHUWRTV7ICH/graph.json","events_json":"https://pith.science/api/pith-number/RAVMWCCQLGCL42QQHUWRTV7ICH/events.json","paper":"https://pith.science/paper/RAVMWCCQ"},"agent_actions":{"view_html":"https://pith.science/pith/RAVMWCCQLGCL42QQHUWRTV7ICH","download_json":"https://pith.science/pith/RAVMWCCQLGCL42QQHUWRTV7ICH.json","view_paper":"https://pith.science/paper/RAVMWCCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02987&json=true","fetch_graph":"https://pith.science/api/pith-number/RAVMWCCQLGCL42QQHUWRTV7ICH/graph.json","fetch_events":"https://pith.science/api/pith-number/RAVMWCCQLGCL42QQHUWRTV7ICH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RAVMWCCQLGCL42QQHUWRTV7ICH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RAVMWCCQLGCL42QQHUWRTV7ICH/action/storage_attestation","attest_author":"https://pith.science/pith/RAVMWCCQLGCL42QQHUWRTV7ICH/action/author_attestation","sign_citation":"https://pith.science/pith/RAVMWCCQLGCL42QQHUWRTV7ICH/action/citation_signature","submit_replication":"https://pith.science/pith/RAVMWCCQLGCL42QQHUWRTV7ICH/action/replication_record"}},"created_at":"2026-07-05T11:42:31.821449+00:00","updated_at":"2026-07-05T11:42:31.821449+00:00"}