{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WVECNU5SE7MYFSLQD2PUCHPNAN","short_pith_number":"pith:WVECNU5S","schema_version":"1.0","canonical_sha256":"b54826d3b227d982c9701e9f411ded034a2bf89638d5001df15bfd672e4172cd","source":{"kind":"arxiv","id":"2303.09975","version":5},"attestation_state":"computed","paper":{"title":"MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Constantin Ulrich, Fabian Isensee, Gregor Koehler, Jens Petersen, Klaus Maier-Hein, Michael Baumgartner, Paul F. Jaeger, Saikat Roy","submitted_at":"2023-03-17T13:48:17Z","abstract_excerpt":"There has been exploding interest in embracing Transformer-based architectures for medical image segmentation. However, the lack of large-scale annotated medical datasets make achieving performances equivalent to those in natural images challenging. Convolutional networks, in contrast, have higher inductive biases and consequently, are easily trainable to high performance. Recently, the ConvNeXt architecture attempted to modernize the standard ConvNet by mirroring Transformer blocks. In this work, we improve upon this to design a modernized and scalable convolutional architecture customized to"},"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":"2303.09975","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2023-03-17T13:48:17Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"b9f69fd987e5b58fbb953950893133afbe9956fd584a25e39fddf48207e9eac3","abstract_canon_sha256":"290d66659d8d324f0f81010a0b8c4a7c920161d1e874af6efe7fafb200d559fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:11.029517Z","signature_b64":"FQM17dZ9rNLK/XsQ8STMdhKbkurKKugetOz8h64uF/Z8DgfNUJt4WB738ue+SJvlZJSYuze1QsMoIKGSKkzcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b54826d3b227d982c9701e9f411ded034a2bf89638d5001df15bfd672e4172cd","last_reissued_at":"2026-07-05T08:26:11.029013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:11.029013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Constantin Ulrich, Fabian Isensee, Gregor Koehler, Jens Petersen, Klaus Maier-Hein, Michael Baumgartner, Paul F. Jaeger, Saikat Roy","submitted_at":"2023-03-17T13:48:17Z","abstract_excerpt":"There has been exploding interest in embracing Transformer-based architectures for medical image segmentation. However, the lack of large-scale annotated medical datasets make achieving performances equivalent to those in natural images challenging. Convolutional networks, in contrast, have higher inductive biases and consequently, are easily trainable to high performance. Recently, the ConvNeXt architecture attempted to modernize the standard ConvNet by mirroring Transformer blocks. In this work, we improve upon this to design a modernized and scalable convolutional architecture customized to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09975","kind":"arxiv","version":5},"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/2303.09975/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":"2303.09975","created_at":"2026-07-05T08:26:11.029070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09975v5","created_at":"2026-07-05T08:26:11.029070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09975","created_at":"2026-07-05T08:26:11.029070+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVECNU5SE7MY","created_at":"2026-07-05T08:26:11.029070+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVECNU5SE7MYFSLQ","created_at":"2026-07-05T08:26:11.029070+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVECNU5S","created_at":"2026-07-05T08:26:11.029070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05515","citing_title":"Geometrical Cross-Attention and Nonvoid Voxelization for Efficient 3D Medical Image Segmentation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WVECNU5SE7MYFSLQD2PUCHPNAN","json":"https://pith.science/pith/WVECNU5SE7MYFSLQD2PUCHPNAN.json","graph_json":"https://pith.science/api/pith-number/WVECNU5SE7MYFSLQD2PUCHPNAN/graph.json","events_json":"https://pith.science/api/pith-number/WVECNU5SE7MYFSLQD2PUCHPNAN/events.json","paper":"https://pith.science/paper/WVECNU5S"},"agent_actions":{"view_html":"https://pith.science/pith/WVECNU5SE7MYFSLQD2PUCHPNAN","download_json":"https://pith.science/pith/WVECNU5SE7MYFSLQD2PUCHPNAN.json","view_paper":"https://pith.science/paper/WVECNU5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09975&json=true","fetch_graph":"https://pith.science/api/pith-number/WVECNU5SE7MYFSLQD2PUCHPNAN/graph.json","fetch_events":"https://pith.science/api/pith-number/WVECNU5SE7MYFSLQD2PUCHPNAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVECNU5SE7MYFSLQD2PUCHPNAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVECNU5SE7MYFSLQD2PUCHPNAN/action/storage_attestation","attest_author":"https://pith.science/pith/WVECNU5SE7MYFSLQD2PUCHPNAN/action/author_attestation","sign_citation":"https://pith.science/pith/WVECNU5SE7MYFSLQD2PUCHPNAN/action/citation_signature","submit_replication":"https://pith.science/pith/WVECNU5SE7MYFSLQD2PUCHPNAN/action/replication_record"}},"created_at":"2026-07-05T08:26:11.029070+00:00","updated_at":"2026-07-05T08:26:11.029070+00:00"}