{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TF2WOOUEEOWUBDFAIQBBORQWNQ","short_pith_number":"pith:TF2WOOUE","schema_version":"1.0","canonical_sha256":"9975673a8423ad408ca044021746166c3742f900bb7628b2c294b1278982a63a","source":{"kind":"arxiv","id":"2303.07034","version":3},"attestation_state":"computed","paper":{"title":"Pretrained ViTs Yield Versatile Representations For Medical Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Matsoukas, Johan Fredin Haslum, Kevin Smith, Magnus S\\\"oderberg, Moein Sorkhei","submitted_at":"2023-03-13T11:53:40Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis, pushing the state-of-the-art in classification, detection and segmentation tasks. Over the last years, vision transformers (ViTs) have appeared as a competitive alternative to CNNs, yielding impressive levels of performance in the natural image domain, while possessing several interesting properties that could prove beneficial for medical imaging tasks. In this work, we explore the benefits and drawbacks of transformer-based models for medical image classification. We c"},"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":"2303.07034","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T11:53:40Z","cross_cats_sorted":[],"title_canon_sha256":"ff894daeb64167677e59824b85ba9e5c6f5598794867bdf97432c88e56205849","abstract_canon_sha256":"bc58e6993fcd5d522a9d4e699080a0fb37f705a1105d4a4574a16275cfbf3fc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:45.705148Z","signature_b64":"QyXGhnTlsy6my9TYlHievz530ouIRPfUEL/HjWxkkxiCxeykLe1NqdGCK46evuM2pAebS9jGD/hUIwFUU2ARAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9975673a8423ad408ca044021746166c3742f900bb7628b2c294b1278982a63a","last_reissued_at":"2026-07-05T09:35:45.704686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:45.704686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pretrained ViTs Yield Versatile Representations For Medical Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Matsoukas, Johan Fredin Haslum, Kevin Smith, Magnus S\\\"oderberg, Moein Sorkhei","submitted_at":"2023-03-13T11:53:40Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis, pushing the state-of-the-art in classification, detection and segmentation tasks. Over the last years, vision transformers (ViTs) have appeared as a competitive alternative to CNNs, yielding impressive levels of performance in the natural image domain, while possessing several interesting properties that could prove beneficial for medical imaging tasks. In this work, we explore the benefits and drawbacks of transformer-based models for medical image classification. We c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07034","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/2303.07034/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":"2303.07034","created_at":"2026-07-05T09:35:45.704743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.07034v3","created_at":"2026-07-05T09:35:45.704743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07034","created_at":"2026-07-05T09:35:45.704743+00:00"},{"alias_kind":"pith_short_12","alias_value":"TF2WOOUEEOWU","created_at":"2026-07-05T09:35:45.704743+00:00"},{"alias_kind":"pith_short_16","alias_value":"TF2WOOUEEOWUBDFA","created_at":"2026-07-05T09:35:45.704743+00:00"},{"alias_kind":"pith_short_8","alias_value":"TF2WOOUE","created_at":"2026-07-05T09:35:45.704743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16393","citing_title":"Vision Transformer-Conditioned UNet for Domain-Adaptive Semantic Segmentation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22557","citing_title":"Are Natural-Domain Foundation Models Effective for Accelerated Cardiac MRI Reconstruction?","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TF2WOOUEEOWUBDFAIQBBORQWNQ","json":"https://pith.science/pith/TF2WOOUEEOWUBDFAIQBBORQWNQ.json","graph_json":"https://pith.science/api/pith-number/TF2WOOUEEOWUBDFAIQBBORQWNQ/graph.json","events_json":"https://pith.science/api/pith-number/TF2WOOUEEOWUBDFAIQBBORQWNQ/events.json","paper":"https://pith.science/paper/TF2WOOUE"},"agent_actions":{"view_html":"https://pith.science/pith/TF2WOOUEEOWUBDFAIQBBORQWNQ","download_json":"https://pith.science/pith/TF2WOOUEEOWUBDFAIQBBORQWNQ.json","view_paper":"https://pith.science/paper/TF2WOOUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.07034&json=true","fetch_graph":"https://pith.science/api/pith-number/TF2WOOUEEOWUBDFAIQBBORQWNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TF2WOOUEEOWUBDFAIQBBORQWNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TF2WOOUEEOWUBDFAIQBBORQWNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TF2WOOUEEOWUBDFAIQBBORQWNQ/action/storage_attestation","attest_author":"https://pith.science/pith/TF2WOOUEEOWUBDFAIQBBORQWNQ/action/author_attestation","sign_citation":"https://pith.science/pith/TF2WOOUEEOWUBDFAIQBBORQWNQ/action/citation_signature","submit_replication":"https://pith.science/pith/TF2WOOUEEOWUBDFAIQBBORQWNQ/action/replication_record"}},"created_at":"2026-07-05T09:35:45.704743+00:00","updated_at":"2026-07-05T09:35:45.704743+00:00"}