{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JYBNPV73DWR3G7ZO76PTFT3Y33","short_pith_number":"pith:JYBNPV73","schema_version":"1.0","canonical_sha256":"4e02d7d7fb1da3b37f2eff9f32cf78def4a37e75b63c90b5b75f9fe5bea84c5f","source":{"kind":"arxiv","id":"2108.09038","version":1},"attestation_state":"computed","paper":{"title":"Is it Time to Replace CNNs with Transformers for Medical Images?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Christos Matsoukas, Johan Fredin Haslum, Kevin Smith, Magnus S\\\"oderberg","submitted_at":"2021-08-20T08:01:19Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis. Recently, vision transformers (ViTs) have appeared as a competitive alternative to CNNs, yielding similar levels of performance while possessing several interesting properties that could prove beneficial for medical imaging tasks. In this work, we explore whether it is time to move to transformer-based models or if we should keep working with CNNs - can we trivially switch to transformers? If so, what are the advantages and drawbacks of switching to ViTs for medical ima"},"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":"2108.09038","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-20T08:01:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"953c96e41a77a214ef2305209829fb14eb37025db515154bf5ef682f19551050","abstract_canon_sha256":"f8be7e84953b939f39b3aa6641c9d1b7d9ffdc46979a8fcce65a183a3b7c6de4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:33.252143Z","signature_b64":"Cgd2wPsWXE2c4h21Bl07kdNEW187YEO6+nQCq+gwnIS0cSmf6MUj4HQKWkFwldKSf7534L2w8Seh3u7h029aBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e02d7d7fb1da3b37f2eff9f32cf78def4a37e75b63c90b5b75f9fe5bea84c5f","last_reissued_at":"2026-07-05T03:07:33.251677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:33.251677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is it Time to Replace CNNs with Transformers for Medical Images?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Christos Matsoukas, Johan Fredin Haslum, Kevin Smith, Magnus S\\\"oderberg","submitted_at":"2021-08-20T08:01:19Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis. Recently, vision transformers (ViTs) have appeared as a competitive alternative to CNNs, yielding similar levels of performance while possessing several interesting properties that could prove beneficial for medical imaging tasks. In this work, we explore whether it is time to move to transformer-based models or if we should keep working with CNNs - can we trivially switch to transformers? If so, what are the advantages and drawbacks of switching to ViTs for medical ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.09038","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/2108.09038/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":"2108.09038","created_at":"2026-07-05T03:07:33.251730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.09038v1","created_at":"2026-07-05T03:07:33.251730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.09038","created_at":"2026-07-05T03:07:33.251730+00:00"},{"alias_kind":"pith_short_12","alias_value":"JYBNPV73DWR3","created_at":"2026-07-05T03:07:33.251730+00:00"},{"alias_kind":"pith_short_16","alias_value":"JYBNPV73DWR3G7ZO","created_at":"2026-07-05T03:07:33.251730+00:00"},{"alias_kind":"pith_short_8","alias_value":"JYBNPV73","created_at":"2026-07-05T03:07:33.251730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05522","citing_title":"Tumor-aware augmentation with task-guided attention analysis improves rectal cancer segmentation from magnetic resonance images","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05522","citing_title":"Tumor-aware augmentation with task-guided attention analysis improves rectal cancer segmentation from magnetic resonance images","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JYBNPV73DWR3G7ZO76PTFT3Y33","json":"https://pith.science/pith/JYBNPV73DWR3G7ZO76PTFT3Y33.json","graph_json":"https://pith.science/api/pith-number/JYBNPV73DWR3G7ZO76PTFT3Y33/graph.json","events_json":"https://pith.science/api/pith-number/JYBNPV73DWR3G7ZO76PTFT3Y33/events.json","paper":"https://pith.science/paper/JYBNPV73"},"agent_actions":{"view_html":"https://pith.science/pith/JYBNPV73DWR3G7ZO76PTFT3Y33","download_json":"https://pith.science/pith/JYBNPV73DWR3G7ZO76PTFT3Y33.json","view_paper":"https://pith.science/paper/JYBNPV73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.09038&json=true","fetch_graph":"https://pith.science/api/pith-number/JYBNPV73DWR3G7ZO76PTFT3Y33/graph.json","fetch_events":"https://pith.science/api/pith-number/JYBNPV73DWR3G7ZO76PTFT3Y33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JYBNPV73DWR3G7ZO76PTFT3Y33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JYBNPV73DWR3G7ZO76PTFT3Y33/action/storage_attestation","attest_author":"https://pith.science/pith/JYBNPV73DWR3G7ZO76PTFT3Y33/action/author_attestation","sign_citation":"https://pith.science/pith/JYBNPV73DWR3G7ZO76PTFT3Y33/action/citation_signature","submit_replication":"https://pith.science/pith/JYBNPV73DWR3G7ZO76PTFT3Y33/action/replication_record"}},"created_at":"2026-07-05T03:07:33.251730+00:00","updated_at":"2026-07-05T03:07:33.251730+00:00"}