{"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/trust-regions-for-explanations-via-black-box","title":"Trust Regions for Explanations via Black-Box Probabilistic Certification","arxiv_id":"2402.11168","date":"2024-02-17","proceeding":null,"authors":["Amit Dhurandhar","Swagatam Haldar","Dennis Wei","Karthikeyan Natesan Ramamurthy"],"abstract":"Given the black box nature of machine learning models, a plethora of explainability methods have been developed to decipher the factors behind individual decisions. In this paper, we introduce a novel problem of black box (probabilistic) explanation certification. We ask the question: Given a black box model with only query access, an explanation for an example and a quality metric (viz. fidelity, stability), can we find the largest hypercube (i.e., $\\ell_{\\infty}$ ball) centered at the example such that when the explanation is applied to all examples within the hypercube, (with high probability) a quality criterion is met (viz. fidelity greater than some value)? Being able to efficiently find such a \\emph{trust region} has multiple benefits: i) insight into model behavior in a \\emph{region}, with a \\emph{guarantee}; ii) ascertained \\emph{stability} of the explanation; iii) \\emph{explanation reuse}, which can save time, energy and money by not having to find explanations for every example; and iv) a possible \\emph{meta-metric} to compare explanation methods. Our contributions include formalizing this problem, proposing solutions, providing theoretical guarantees for these solutions that are computable, and experimentally showing their efficacy on synthetic and real data.","url_abs":"https://arxiv.org/abs/2402.11168v3","url_pdf":"https://arxiv.org/pdf/2402.11168v3.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":"trust-regions-for-explanations-via-black-box","repo_url":"https://github.com/Trusted-AI/AIX360","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.11168","atlas_url":"https://app.syntology.ai/?focus=2402.11168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11168"}},"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":"deterministic:regex_extraction","url":"https://github.com/Trusted-AI/AIX360","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_violates":3,"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":"f437c40c8921cd8c","entry":"bb","repo":"trusted-ai/aix360","repo_kind":"official","path":"aix360/algorithms/ecertify/ExpCertifyBB.py","file_url":"https://github.com/trusted-ai/aix360/blob/HEAD/aix360/algorithms/ecertify/ExpCertifyBB.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f437c40c8921cd8c"}},{"code_sha256_prefix":"15ff4533de1a6af8","entry":"e","repo":"trusted-ai/aix360","repo_kind":"official","path":"aix360/algorithms/ecertify/ExpCertifyBB.py","file_url":"https://github.com/trusted-ai/aix360/blob/HEAD/aix360/algorithms/ecertify/ExpCertifyBB.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"15ff4533de1a6af8"}},{"code_sha256_prefix":"6a51d68741d2ae12","entry":"f","repo":"trusted-ai/aix360","repo_kind":"official","path":"aix360/algorithms/ecertify/ExpCertifyBB.py","file_url":"https://github.com/trusted-ai/aix360/blob/HEAD/aix360/algorithms/ecertify/ExpCertifyBB.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a51d68741d2ae12"}},{"code_sha256_prefix":"d269f5f6d592112e","entry":"onehot_encoding","repo":"Trusted-AI/AIX360","repo_kind":"official","path":"aix360/algorithms/cofrnet/utils.py","file_url":"https://github.com/Trusted-AI/AIX360/blob/HEAD/aix360/algorithms/cofrnet/utils.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":"d269f5f6d592112e"}},{"code_sha256_prefix":"6be0ec7a3027f695","entry":"generate_connections","repo":"Trusted-AI/AIX360","repo_kind":"official","path":"aix360/algorithms/cofrnet/utils.py","file_url":"https://github.com/Trusted-AI/AIX360/blob/HEAD/aix360/algorithms/cofrnet/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":"6be0ec7a3027f695"}},{"code_sha256_prefix":"d81355b81c3d33f8","entry":"process_data","repo":"Trusted-AI/AIX360","repo_kind":"official","path":"aix360/algorithms/cofrnet/utils.py","file_url":"https://github.com/Trusted-AI/AIX360/blob/HEAD/aix360/algorithms/cofrnet/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":"d81355b81c3d33f8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}