{"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/x-hacking-the-threat-of-misguided-automl","title":"X Hacking: The Threat of Misguided AutoML","arxiv_id":"2401.08513","date":"2024-01-16","proceeding":null,"authors":["Rahul Sharma","Sergey Redyuk","Sumantrak Mukherjee","Andrea Sipka","Sebastian Vollmer","David Selby"],"abstract":"Explainable AI (XAI) and interpretable machine learning methods help to build trust in model predictions and derived insights, yet also present a perverse incentive for analysts to manipulate XAI metrics to support pre-specified conclusions. This paper introduces the concept of X-hacking, a form of p-hacking applied to XAI metrics such as Shap values. We show how an automated machine learning pipeline can be used to search for 'defensible' models that produce a desired explanation while maintaining superior predictive performance to a common baseline. We formulate the trade-off between explanation and accuracy as a multi-objective optimization problem and illustrate the feasibility and severity of X-hacking empirically on familiar real-world datasets. Finally, we suggest possible methods for detection and prevention, and discuss ethical implications for the credibility and reproducibility of XAI research.","url_abs":"https://arxiv.org/abs/2401.08513v2","url_pdf":"https://arxiv.org/pdf/2401.08513v2.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":"x-hacking-the-threat-of-misguided-automl","repo_url":"https://github.com/selbosh/p-hacking","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"automl","task_name":"AutoML"},{"task_slug":"interpretable-machine-learning","task_name":"Interpretable Machine Learning"}],"methods":[{"method_slug":"shap","method_name":"SHAP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.08513","atlas_url":"https://app.syntology.ai/?focus=2401.08513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08513"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/selbosh/p-hacking","reach":{"status":"ok"}}],"summary":{"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":2,"samples":[{"code_sha256_prefix":"b8e95809ca2c17c9","entry":"sigmoid","repo":"selbosh/p-hacking","repo_kind":"official","path":"src/rahulsStuff/experiments/source/graphs.py","file_url":"https://github.com/selbosh/p-hacking/blob/HEAD/src/rahulsStuff/experiments/source/graphs.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b8e95809ca2c17c9"}},{"code_sha256_prefix":"e749726defb2cb03","entry":"plot_subgraphs","repo":"selbosh/p-hacking","repo_kind":"official","path":"src/rahulsStuff/experiments/source/graphs.py","file_url":"https://github.com/selbosh/p-hacking/blob/HEAD/src/rahulsStuff/experiments/source/graphs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e749726defb2cb03"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}