{"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/reliably-detecting-model-failures-in","title":"Reliably detecting model failures in deployment without labels","arxiv_id":"2506.05047","date":"2025-06-05","proceeding":null,"authors":["Viet Nguyen","Changjian Shui","Vijay Giri","Siddarth Arya","Amol Verma","Fahad Razak","Rahul G. Krishnan"],"abstract":"The distribution of data changes over time; models operating operating in dynamic environments need retraining. But knowing when to retrain, without access to labels, is an open challenge since some, but not all shifts degrade model performance. This paper formalizes and addresses the problem of post-deployment deterioration (PDD) monitoring. We propose D3M, a practical and efficient monitoring algorithm based on the disagreement of predictive models, achieving low false positive rates under non-deteriorating shifts and provides sample complexity bounds for high true positive rates under deteriorating shifts. Empirical results on both standard benchmark and a real-world large-scale internal medicine dataset demonstrate the effectiveness of the framework and highlight its viability as an alert mechanism for high-stakes machine learning pipelines.","url_abs":"https://arxiv.org/abs/2506.05047v2","url_pdf":"https://arxiv.org/pdf/2506.05047v2.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":"reliably-detecting-model-failures-in","repo_url":"https://github.com/teivng/d3m","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.05047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.05047"}},"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":"deterministic:regex_extraction","url":"https://github.com/teivng/d3m","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/fengliu90/DK-for-TST","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/a7b23/H-Divergence","reach":null}],"summary":{"ran":3,"ran_draft_wrong":4,"ran_fixture":1,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":5,"repositories":1},"found_in_text":{"samples":5,"ran":4,"repositories":2}},"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":2,"samples":[{"code_sha256_prefix":"31b4c586b6c8ab9b","entry":"D3MBayesianMonitor","repo":"teivng/d3m","repo_kind":"official","path":"d3m/monitors/bayesian_monitor.py","file_url":"https://github.com/teivng/d3m/blob/HEAD/d3m/monitors/bayesian_monitor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31b4c586b6c8ab9b"}},{"code_sha256_prefix":"9351e8786754a459","entry":"JSV_Gaussian","repo":"a7b23/H-Divergence","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/a7b23/H-Divergence/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9351e8786754a459"}},{"code_sha256_prefix":"a42e81244edb9510","entry":"JSV_Gaussian_u","repo":"a7b23/H-Divergence","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/a7b23/H-Divergence/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a42e81244edb9510"}},{"code_sha256_prefix":"b2fd0117a1785dcf","entry":"MMDu","repo":"fengliu90/DK-for-TST","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/fengliu90/DK-for-TST/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b2fd0117a1785dcf"}},{"code_sha256_prefix":"e31bb08debb2367d","entry":"TrainConfig","repo":"teivng/d3m","repo_kind":"official","path":"d3m/monitors/bayesian_monitor.py","file_url":"https://github.com/teivng/d3m/blob/HEAD/d3m/monitors/bayesian_monitor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e31bb08debb2367d"}},{"code_sha256_prefix":"24c4d57d39e03345","entry":"get_class_from_string","repo":"teivng/d3m","repo_kind":"official","path":"d3m/monitors/bayesian_monitor.py","file_url":"https://github.com/teivng/d3m/blob/HEAD/d3m/monitors/bayesian_monitor.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24c4d57d39e03345"}},{"code_sha256_prefix":"123d5b309dfd538f","entry":"mmd2_permutations","repo":"fengliu90/DK-for-TST","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/fengliu90/DK-for-TST/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"123d5b309dfd538f"}},{"code_sha256_prefix":"9fcb4375a26ac02b","entry":"sample_from_dataset","repo":"teivng/d3m","repo_kind":"official","path":"d3m/monitors/bayesian_monitor.py","file_url":"https://github.com/teivng/d3m/blob/HEAD/d3m/monitors/bayesian_monitor.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9fcb4375a26ac02b"}},{"code_sha256_prefix":"6688a7f57e8828e0","entry":"temperature_scaling","repo":"teivng/d3m","repo_kind":"official","path":"d3m/monitors/bayesian_monitor.py","file_url":"https://github.com/teivng/d3m/blob/HEAD/d3m/monitors/bayesian_monitor.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6688a7f57e8828e0"}},{"code_sha256_prefix":"745669490b50fd4f","entry":"D3MAbstractModel","repo":"teivng/d3m","repo_kind":"official","path":"d3m/monitors/bayesian_monitor.py","file_url":"https://github.com/teivng/d3m/blob/HEAD/d3m/monitors/bayesian_monitor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"745669490b50fd4f"}},{"code_sha256_prefix":"99a9a8040630f606","entry":"D3MMonitor","repo":"teivng/d3m","repo_kind":"official","path":"d3m/monitors/bayesian_monitor.py","file_url":"https://github.com/teivng/d3m/blob/HEAD/d3m/monitors/bayesian_monitor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"99a9a8040630f606"}},{"code_sha256_prefix":"ec24b4387148fe67","entry":"TST_MMD_u","repo":"fengliu90/DK-for-TST","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/fengliu90/DK-for-TST/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec24b4387148fe67"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}