{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/overcoming-common-flaws-in-the-evaluation-of","title":"Overcoming Common Flaws in the Evaluation of Selective Classification Systems","arxiv_id":"2407.01032","date":"2024-07-01","proceeding":null,"authors":["Jeremias Traub","Till J. Bungert","Carsten T. Lüth","Michael Baumgartner","Klaus H. Maier-Hein","Lena Maier-Hein","Paul F Jaeger"],"abstract":"Selective Classification, wherein models can reject low-confidence predictions, promises reliable translation of machine-learning based classification systems to real-world scenarios such as clinical diagnostics. While current evaluation of these systems typically assumes fixed working points based on pre-defined rejection thresholds, methodological progress requires benchmarking the general performance of systems akin to the $\\mathrm{AUROC}$ in standard classification. In this work, we define 5 requirements for multi-threshold metrics in selective classification regarding task alignment, interpretability, and flexibility, and show how current approaches fail to meet them. We propose the Area under the Generalized Risk Coverage curve ($\\mathrm{AUGRC}$), which meets all requirements and can be directly interpreted as the average risk of undetected failures. We empirically demonstrate the relevance of $\\mathrm{AUGRC}$ on a comprehensive benchmark spanning 6 data sets and 13 confidence scoring functions. We find that the proposed metric substantially changes metric rankings on 5 out of the 6 data sets.","url_abs":"https://arxiv.org/abs/2407.01032v2","url_pdf":"https://arxiv.org/pdf/2407.01032v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"overcoming-common-flaws-in-the-evaluation-of","repo_url":"https://github.com/iml-dkfz/fd-shifts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"classification-1","task_name":"Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.01032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01032"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iml-dkfz/fd-shifts","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"unverified":4},"by_repo_kind":{"official":{"samples":10,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f4a6fa6acd121ea2","entry":"is_external_confid","repo":"iml-dkfz/fd-shifts","repo_kind":"official","path":"fd_shifts/analysis/confid_scores.py","file_url":"https://github.com/iml-dkfz/fd-shifts/blob/HEAD/fd_shifts/analysis/confid_scores.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f4a6fa6acd121ea2"}},{"code_sha256_prefix":"38f5a028942c9ab7","entry":"is_mcd_confid","repo":"iml-dkfz/fd-shifts","repo_kind":"official","path":"fd_shifts/analysis/confid_scores.py","file_url":"https://github.com/iml-dkfz/fd-shifts/blob/HEAD/fd_shifts/analysis/confid_scores.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"38f5a028942c9ab7"}},{"code_sha256_prefix":"8ebc89e8f2cedb7e","entry":"metric_function_exists","repo":"iml-dkfz/fd-shifts","repo_kind":"official","path":"fd_shifts/analysis/metrics.py","file_url":"https://github.com/iml-dkfz/fd-shifts/blob/HEAD/fd_shifts/analysis/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ebc89e8f2cedb7e"}},{"code_sha256_prefix":"e85f35ee8f6d2021","entry":"register_filter_func","repo":"iml-dkfz/fd-shifts","repo_kind":"official","path":"fd_shifts/analysis/studies.py","file_url":"https://github.com/iml-dkfz/fd-shifts/blob/HEAD/fd_shifts/analysis/studies.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e85f35ee8f6d2021"}},{"code_sha256_prefix":"3365918245b238a3","entry":"register_metric_func","repo":"iml-dkfz/fd-shifts","repo_kind":"official","path":"fd_shifts/analysis/metrics.py","file_url":"https://github.com/iml-dkfz/fd-shifts/blob/HEAD/fd_shifts/analysis/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3365918245b238a3"}},{"code_sha256_prefix":"3477de85b6d78104","entry":"register_study_iterator","repo":"iml-dkfz/fd-shifts","repo_kind":"official","path":"fd_shifts/analysis/studies.py","file_url":"https://github.com/iml-dkfz/fd-shifts/blob/HEAD/fd_shifts/analysis/studies.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3477de85b6d78104"}},{"code_sha256_prefix":"066441f2553f8462","entry":"ThresholdPlot","repo":"iml-dkfz/fd-shifts","repo_kind":"official","path":"fd_shifts/analysis/eval_utils.py","file_url":"https://github.com/iml-dkfz/fd-shifts/blob/HEAD/fd_shifts/analysis/eval_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"066441f2553f8462"}},{"code_sha256_prefix":"d9bf6e87cf10bc8f","entry":"get_filter_function","repo":"iml-dkfz/fd-shifts","repo_kind":"official","path":"fd_shifts/analysis/studies.py","file_url":"https://github.com/iml-dkfz/fd-shifts/blob/HEAD/fd_shifts/analysis/studies.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9bf6e87cf10bc8f"}},{"code_sha256_prefix":"ccfe86fd96d96f2a","entry":"may_raise_sklearn_exception","repo":"iml-dkfz/fd-shifts","repo_kind":"official","path":"fd_shifts/analysis/metrics.py","file_url":"https://github.com/iml-dkfz/fd-shifts/blob/HEAD/fd_shifts/analysis/metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ccfe86fd96d96f2a"}},{"code_sha256_prefix":"3ddbd420eb23faf8","entry":"monitor_eval","repo":"iml-dkfz/fd-shifts","repo_kind":"official","path":"fd_shifts/analysis/eval_utils.py","file_url":"https://github.com/iml-dkfz/fd-shifts/blob/HEAD/fd_shifts/analysis/eval_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ddbd420eb23faf8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}