{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VBYWOWL5RI7CPSXWWE65A2YFLU","short_pith_number":"pith:VBYWOWL5","schema_version":"1.0","canonical_sha256":"a87167597d8a3e27caf6b13dd06b055d078ff6f326cc0296244c6fb908959141","source":{"kind":"arxiv","id":"2304.06716","version":1},"attestation_state":"computed","paper":{"title":"STU-Net: Scalable and Transferable Medical Image Segmentation Models Empowered by Large-Scale Supervised Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Wang, Hui Sun, Jin Ye, Junjun He, Lixu Gu, Shaoting Zhang, Yanzhou Su, Yun Gu, Yu Qiao, Zhongying Deng, Ziyan Huang","submitted_at":"2023-04-13T17:59:13Z","abstract_excerpt":"Large-scale models pre-trained on large-scale datasets have profoundly advanced the development of deep learning. However, the state-of-the-art models for medical image segmentation are still small-scale, with their parameters only in the tens of millions. Further scaling them up to higher orders of magnitude is rarely explored. An overarching goal of exploring large-scale models is to train them on large-scale medical segmentation datasets for better transfer capacities. In this work, we design a series of Scalable and Transferable U-Net (STU-Net) models, with parameter sizes ranging from 14 "},"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":"2304.06716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-13T17:59:13Z","cross_cats_sorted":[],"title_canon_sha256":"538aec68984b55806d968da75fbe67c4165b1bcaf6137361b02eebf5eb3dbb30","abstract_canon_sha256":"417e4131242f0871c5b73ae4a24d246c7597f2d0fd617245d55ad3459107e60b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:53.042625Z","signature_b64":"bW9qbQgA41Ls8mfeKQx5URTHDHzqrhUz2XfsoDsiJeoFDZQpjcz/nwWHjz5hMBKljwas7BN7fJkTVLIq71mFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a87167597d8a3e27caf6b13dd06b055d078ff6f326cc0296244c6fb908959141","last_reissued_at":"2026-07-05T06:00:53.042211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:53.042211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STU-Net: Scalable and Transferable Medical Image Segmentation Models Empowered by Large-Scale Supervised Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Wang, Hui Sun, Jin Ye, Junjun He, Lixu Gu, Shaoting Zhang, Yanzhou Su, Yun Gu, Yu Qiao, Zhongying Deng, Ziyan Huang","submitted_at":"2023-04-13T17:59:13Z","abstract_excerpt":"Large-scale models pre-trained on large-scale datasets have profoundly advanced the development of deep learning. However, the state-of-the-art models for medical image segmentation are still small-scale, with their parameters only in the tens of millions. Further scaling them up to higher orders of magnitude is rarely explored. An overarching goal of exploring large-scale models is to train them on large-scale medical segmentation datasets for better transfer capacities. In this work, we design a series of Scalable and Transferable U-Net (STU-Net) models, with parameter sizes ranging from 14 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06716","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/2304.06716/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":"2304.06716","created_at":"2026-07-05T06:00:53.042266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.06716v1","created_at":"2026-07-05T06:00:53.042266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06716","created_at":"2026-07-05T06:00:53.042266+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBYWOWL5RI7C","created_at":"2026-07-05T06:00:53.042266+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBYWOWL5RI7CPSXW","created_at":"2026-07-05T06:00:53.042266+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBYWOWL5","created_at":"2026-07-05T06:00:53.042266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24883","citing_title":"BenchX: Benchmarking AI Models for Cancer Detection and Localization with Demographic and Protocol Biases","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04365","citing_title":"Multi-Granularity 3D Kidney Lesion Characterization from CT Volumes","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30108","citing_title":"LETT-NeXt: A Lightweight RECIST-Guided Model for 3D CT Lesion Segmentation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11679","citing_title":"Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2503.01835","citing_title":"Primus: Enforcing Attention Usage for 3D Medical Image Segmentation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22619","citing_title":"GLeVE: Graph-Guided Lesion Grounding with Proposal Verification in 3D CT","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2510.00520","citing_title":"CardioBench: Do Echocardiography Foundation Models Generalize Beyond the Lab?","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16572","citing_title":"TriALS: Triphasic-Aided Liver Lesion Segmentation Benchmark in Non-Contrast CT","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04705","citing_title":"Label-Efficient Cross-Modality Generalization for Liver Segmentation in Multi-Phase MRI","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2401.04722","citing_title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10696","citing_title":"Camyla: Scaling Autonomous Research in Medical Image Segmentation","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11679","citing_title":"Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07999","citing_title":"Benchmarking Deep Learning for Future Liver Remnant Segmentation in Colorectal Liver Metastasis","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VBYWOWL5RI7CPSXWWE65A2YFLU","json":"https://pith.science/pith/VBYWOWL5RI7CPSXWWE65A2YFLU.json","graph_json":"https://pith.science/api/pith-number/VBYWOWL5RI7CPSXWWE65A2YFLU/graph.json","events_json":"https://pith.science/api/pith-number/VBYWOWL5RI7CPSXWWE65A2YFLU/events.json","paper":"https://pith.science/paper/VBYWOWL5"},"agent_actions":{"view_html":"https://pith.science/pith/VBYWOWL5RI7CPSXWWE65A2YFLU","download_json":"https://pith.science/pith/VBYWOWL5RI7CPSXWWE65A2YFLU.json","view_paper":"https://pith.science/paper/VBYWOWL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.06716&json=true","fetch_graph":"https://pith.science/api/pith-number/VBYWOWL5RI7CPSXWWE65A2YFLU/graph.json","fetch_events":"https://pith.science/api/pith-number/VBYWOWL5RI7CPSXWWE65A2YFLU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBYWOWL5RI7CPSXWWE65A2YFLU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBYWOWL5RI7CPSXWWE65A2YFLU/action/storage_attestation","attest_author":"https://pith.science/pith/VBYWOWL5RI7CPSXWWE65A2YFLU/action/author_attestation","sign_citation":"https://pith.science/pith/VBYWOWL5RI7CPSXWWE65A2YFLU/action/citation_signature","submit_replication":"https://pith.science/pith/VBYWOWL5RI7CPSXWWE65A2YFLU/action/replication_record"}},"created_at":"2026-07-05T06:00:53.042266+00:00","updated_at":"2026-07-05T06:00:53.042266+00:00"}