{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TAABGNYYDM7NUUXAYTILWCQF4F","short_pith_number":"pith:TAABGNYY","schema_version":"1.0","canonical_sha256":"98001337181b3eda52e0c4d0bb0a05e1588efec6b730ad535e8a9bac76e45a21","source":{"kind":"arxiv","id":"2411.03670","version":2},"attestation_state":"computed","paper":{"title":"Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Afshin Bozorgpour, Alan L. Yuille, Andrea Cavalli, Bo Zhao, Constantin Ulrich, Daguang Xu, Dorit Merhof, Fabian Isensee, Fan Bai, Hanxue Gu, Hao Chen, Haonan Wang, Haoyu Dong, Holger Roth, Jianpeng Zhang, Jiaxin Zhuang, Jichen Yang, Jieneng Chen, Jin Ye, Junjun He, Klaus H. Maier-Hein, Lei Zhu, Linshan Wu, Maciej A. Mazurowski, Matthew B. Blaschko, Maximilian Rokuss, Michael Baumgartner, Paul Jaeger, Pedro R. A. S. Bassi, Pengcheng Shi, Pratibha Kumari, Reza Azad, Saikat Roy, Saumya Gupta, Sergio Decherchi, Tassilo Wald, Tiejun Huang, Ting Ma, Wenxuan Li, Xiaomeng Li, Yannick Kirchhoff, Yiwen Ye, Yong Xia, Yousef Sadegheih, Yu-Cheng Chou, Yucheng Tang, Yutong Xie, Yuxin Du, Zhaohu Xing, Zifu Wang, Ziyang Chen, Ziyan Huang, Zongwei Zhou","submitted_at":"2024-11-06T05:09:34Z","abstract_excerpt":"How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans fr"},"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":"2411.03670","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-06T05:09:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"12c016f9343a30e7830b52e31cc4a8fc739319aa7c394561a6ccc86ca18e02c3","abstract_canon_sha256":"8ff4c32fa90c2cb5fe6b6973f860c0f67bebe6668838a68f64f9575de260ea16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:54.432452Z","signature_b64":"xE3R/DqcaMy0UC0lEgcnoPZ5nMjBkke74dwA0Mk1OuUN3AICbvr7a2zxGHiuEG6rEwlhmr44da+bMI2uEMc4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98001337181b3eda52e0c4d0bb0a05e1588efec6b730ad535e8a9bac76e45a21","last_reissued_at":"2026-07-05T10:02:54.431945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:54.431945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Afshin Bozorgpour, Alan L. Yuille, Andrea Cavalli, Bo Zhao, Constantin Ulrich, Daguang Xu, Dorit Merhof, Fabian Isensee, Fan Bai, Hanxue Gu, Hao Chen, Haonan Wang, Haoyu Dong, Holger Roth, Jianpeng Zhang, Jiaxin Zhuang, Jichen Yang, Jieneng Chen, Jin Ye, Junjun He, Klaus H. Maier-Hein, Lei Zhu, Linshan Wu, Maciej A. Mazurowski, Matthew B. Blaschko, Maximilian Rokuss, Michael Baumgartner, Paul Jaeger, Pedro R. A. S. Bassi, Pengcheng Shi, Pratibha Kumari, Reza Azad, Saikat Roy, Saumya Gupta, Sergio Decherchi, Tassilo Wald, Tiejun Huang, Ting Ma, Wenxuan Li, Xiaomeng Li, Yannick Kirchhoff, Yiwen Ye, Yong Xia, Yousef Sadegheih, Yu-Cheng Chou, Yucheng Tang, Yutong Xie, Yuxin Du, Zhaohu Xing, Zifu Wang, Ziyang Chen, Ziyan Huang, Zongwei Zhou","submitted_at":"2024-11-06T05:09:34Z","abstract_excerpt":"How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03670","kind":"arxiv","version":2},"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/2411.03670/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":"2411.03670","created_at":"2026-07-05T10:02:54.432010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03670v2","created_at":"2026-07-05T10:02:54.432010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03670","created_at":"2026-07-05T10:02:54.432010+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAABGNYYDM7N","created_at":"2026-07-05T10:02:54.432010+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAABGNYYDM7NUUXA","created_at":"2026-07-05T10:02:54.432010+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAABGNYY","created_at":"2026-07-05T10:02:54.432010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.01835","citing_title":"Primus: Enforcing Attention Usage for 3D Medical Image Segmentation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TAABGNYYDM7NUUXAYTILWCQF4F","json":"https://pith.science/pith/TAABGNYYDM7NUUXAYTILWCQF4F.json","graph_json":"https://pith.science/api/pith-number/TAABGNYYDM7NUUXAYTILWCQF4F/graph.json","events_json":"https://pith.science/api/pith-number/TAABGNYYDM7NUUXAYTILWCQF4F/events.json","paper":"https://pith.science/paper/TAABGNYY"},"agent_actions":{"view_html":"https://pith.science/pith/TAABGNYYDM7NUUXAYTILWCQF4F","download_json":"https://pith.science/pith/TAABGNYYDM7NUUXAYTILWCQF4F.json","view_paper":"https://pith.science/paper/TAABGNYY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03670&json=true","fetch_graph":"https://pith.science/api/pith-number/TAABGNYYDM7NUUXAYTILWCQF4F/graph.json","fetch_events":"https://pith.science/api/pith-number/TAABGNYYDM7NUUXAYTILWCQF4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAABGNYYDM7NUUXAYTILWCQF4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAABGNYYDM7NUUXAYTILWCQF4F/action/storage_attestation","attest_author":"https://pith.science/pith/TAABGNYYDM7NUUXAYTILWCQF4F/action/author_attestation","sign_citation":"https://pith.science/pith/TAABGNYYDM7NUUXAYTILWCQF4F/action/citation_signature","submit_replication":"https://pith.science/pith/TAABGNYYDM7NUUXAYTILWCQF4F/action/replication_record"}},"created_at":"2026-07-05T10:02:54.432010+00:00","updated_at":"2026-07-05T10:02:54.432010+00:00"}