{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DXNSS4Q3JWOLIWSAOBVRWX62PS","short_pith_number":"pith:DXNSS4Q3","schema_version":"1.0","canonical_sha256":"1ddb29721b4d9cb45a40706b1b5fda7c89bfe7c4fdc452b6aa812064b49513cd","source":{"kind":"arxiv","id":"2401.10815","version":3},"attestation_state":"computed","paper":{"title":"Exploring scalable medical image encoders beyond text supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton Schwaighofer, Daniel C. Castro, Fernando P\\'erez-Garc\\'ia, Harshita Sharma, Javier Alvarez-Valle, Kenza Bouzid, Maria Teodora Wetscherek, Matthew P. Lungren, Maximilian Ilse, Noel Codella, Ozan Oktay, Sam Bond-Taylor, Shruthi Bannur, Stephanie L. Hyland, Valentina Salvatelli","submitted_at":"2024-01-19T17:02:17Z","abstract_excerpt":"Language-supervised pre-training has proven to be a valuable method for extracting semantically meaningful features from images, serving as a foundational element in multimodal systems within the computer vision and medical imaging domains. However, the computed features are limited by the information contained in the text, which is particularly problematic in medical imaging, where the findings described by radiologists focus on specific observations. This challenge is compounded by the scarcity of paired imaging-text data due to concerns over leakage of personal health information. In this w"},"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":"2401.10815","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T17:02:17Z","cross_cats_sorted":[],"title_canon_sha256":"35ba40d6ac09138d35458643ee360f0764628c1bf1e2d11ac4a2821a8b3766b6","abstract_canon_sha256":"00e0fd7321adf1352054edd68a34593c9f0ae74517b3c2aec4a05a59581b984e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:39.243635Z","signature_b64":"k4HnLB+OYjS8eF6ag4Jt22maOF8aRBNRuqGEkRKyVpYmFLUqiJIcVAxb9QfB7V/P5LZ8YCmZ+ZGsyAqRMSdoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ddb29721b4d9cb45a40706b1b5fda7c89bfe7c4fdc452b6aa812064b49513cd","last_reissued_at":"2026-07-05T10:10:39.243282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:39.243282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring scalable medical image encoders beyond text supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton Schwaighofer, Daniel C. Castro, Fernando P\\'erez-Garc\\'ia, Harshita Sharma, Javier Alvarez-Valle, Kenza Bouzid, Maria Teodora Wetscherek, Matthew P. Lungren, Maximilian Ilse, Noel Codella, Ozan Oktay, Sam Bond-Taylor, Shruthi Bannur, Stephanie L. Hyland, Valentina Salvatelli","submitted_at":"2024-01-19T17:02:17Z","abstract_excerpt":"Language-supervised pre-training has proven to be a valuable method for extracting semantically meaningful features from images, serving as a foundational element in multimodal systems within the computer vision and medical imaging domains. However, the computed features are limited by the information contained in the text, which is particularly problematic in medical imaging, where the findings described by radiologists focus on specific observations. This challenge is compounded by the scarcity of paired imaging-text data due to concerns over leakage of personal health information. In this w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10815","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/2401.10815/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":"2401.10815","created_at":"2026-07-05T10:10:39.243340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.10815v3","created_at":"2026-07-05T10:10:39.243340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10815","created_at":"2026-07-05T10:10:39.243340+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXNSS4Q3JWOL","created_at":"2026-07-05T10:10:39.243340+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXNSS4Q3JWOLIWSA","created_at":"2026-07-05T10:10:39.243340+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXNSS4Q3","created_at":"2026-07-05T10:10:39.243340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08364","citing_title":"Self-Supervised Vision Transformers for CBCT-Based Detection of Temporomandibular Joint Osteoarthritis","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30131","citing_title":"CCS: Clinical Consensus Selection for Radiology Report Generation","ref_index":2,"is_internal_anchor":false},{"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":38,"is_internal_anchor":false},{"citing_arxiv_id":"2504.07415","citing_title":"RA-RRG: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12152","citing_title":"Domain-Specific Latent Representations Improve the Fidelity of Diffusion-Based Medical Image Super-Resolution","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXNSS4Q3JWOLIWSAOBVRWX62PS","json":"https://pith.science/pith/DXNSS4Q3JWOLIWSAOBVRWX62PS.json","graph_json":"https://pith.science/api/pith-number/DXNSS4Q3JWOLIWSAOBVRWX62PS/graph.json","events_json":"https://pith.science/api/pith-number/DXNSS4Q3JWOLIWSAOBVRWX62PS/events.json","paper":"https://pith.science/paper/DXNSS4Q3"},"agent_actions":{"view_html":"https://pith.science/pith/DXNSS4Q3JWOLIWSAOBVRWX62PS","download_json":"https://pith.science/pith/DXNSS4Q3JWOLIWSAOBVRWX62PS.json","view_paper":"https://pith.science/paper/DXNSS4Q3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.10815&json=true","fetch_graph":"https://pith.science/api/pith-number/DXNSS4Q3JWOLIWSAOBVRWX62PS/graph.json","fetch_events":"https://pith.science/api/pith-number/DXNSS4Q3JWOLIWSAOBVRWX62PS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXNSS4Q3JWOLIWSAOBVRWX62PS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXNSS4Q3JWOLIWSAOBVRWX62PS/action/storage_attestation","attest_author":"https://pith.science/pith/DXNSS4Q3JWOLIWSAOBVRWX62PS/action/author_attestation","sign_citation":"https://pith.science/pith/DXNSS4Q3JWOLIWSAOBVRWX62PS/action/citation_signature","submit_replication":"https://pith.science/pith/DXNSS4Q3JWOLIWSAOBVRWX62PS/action/replication_record"}},"created_at":"2026-07-05T10:10:39.243340+00:00","updated_at":"2026-07-05T10:10:39.243340+00:00"}