{"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/to-trust-or-not-to-trust-a-classifier","title":"To Trust Or Not To Trust A Classifier","arxiv_id":"1805.11783","date":"2018-05-30","proceeding":"NeurIPS 2018 12","authors":["Heinrich Jiang","Been Kim","Melody Y. Guan","Maya Gupta"],"abstract":"Knowing when a classifier's prediction can be trusted is useful in many\napplications and critical for safely using AI. While the bulk of the effort in\nmachine learning research has been towards improving classifier performance,\nunderstanding when a classifier's predictions should and should not be trusted\nhas received far less attention. The standard approach is to use the\nclassifier's discriminant or confidence score; however, we show there exists an\nalternative that is more effective in many situations. We propose a new score,\ncalled the trust score, which measures the agreement between the classifier and\na modified nearest-neighbor classifier on the testing example. We show\nempirically that high (low) trust scores produce surprisingly high precision at\nidentifying correctly (incorrectly) classified examples, consistently\noutperforming the classifier's confidence score as well as many other\nbaselines. Further, under some mild distributional assumptions, we show that if\nthe trust score for an example is high (low), the classifier will likely agree\n(disagree) with the Bayes-optimal classifier. Our guarantees consist of\nnon-asymptotic rates of statistical consistency under various nonparametric\nsettings and build on recent developments in topological data analysis.","url_abs":"http://arxiv.org/abs/1805.11783v2","url_pdf":"http://arxiv.org/pdf/1805.11783v2.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":"to-trust-or-not-to-trust-a-classifier","repo_url":"https://github.com/google/TrustScore","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"topological-data-analysis","task_name":"Topological Data Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.11783","atlas_url":"https://app.syntology.ai/?focus=1805.11783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.11783"}},"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/google/TrustScore","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":"2b461b9210d198bc","entry":"run_linear_svc","repo":"google/TrustScore","repo_kind":"official","path":"trustscore/trustscore_evaluation.py","file_url":"https://github.com/google/TrustScore/blob/HEAD/trustscore/trustscore_evaluation.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":"2b461b9210d198bc"}},{"code_sha256_prefix":"f452e830d26150ef","entry":"run_logistic","repo":"google/TrustScore","repo_kind":"official","path":"trustscore/trustscore_evaluation.py","file_url":"https://github.com/google/TrustScore/blob/HEAD/trustscore/trustscore_evaluation.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":"f452e830d26150ef"}},{"code_sha256_prefix":"40cb566dcc905a26","entry":"run_random_forest","repo":"google/TrustScore","repo_kind":"official","path":"trustscore/trustscore_evaluation.py","file_url":"https://github.com/google/TrustScore/blob/HEAD/trustscore/trustscore_evaluation.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":"40cb566dcc905a26"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}