{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/defining-locality-for-surrogates-in-post-hoc","title":"Defining Locality for Surrogates in Post-hoc Interpretablity","arxiv_id":"1806.07498","date":"2018-06-19","proceeding":null,"authors":["Thibault Laugel","Xavier Renard","Marie-Jeanne Lesot","Christophe Marsala","Marcin Detyniecki"],"abstract":"Local surrogate models, to approximate the local decision boundary of a\nblack-box classifier, constitute one approach to generate explanations for the\nrationale behind an individual prediction made by the back-box. This paper\nhighlights the importance of defining the right locality, the neighborhood on\nwhich a local surrogate is trained, in order to approximate accurately the\nlocal black-box decision boundary. Unfortunately, as shown in this paper, this\nissue is not only a parameter or sampling distribution challenge and has a\nmajor impact on the relevance and quality of the approximation of the local\nblack-box decision boundary and thus on the meaning and accuracy of the\ngenerated explanation. To overcome the identified problems, quantified with an\nadapted measure and procedure, we propose to generate surrogate-based\nexplanations for individual predictions based on a sampling centered on\nparticular place of the decision boundary, relevant for the prediction to be\nexplained, rather than on the prediction itself as it is classically done. We\nevaluate the novel approach compared to state-of-the-art methods and a\nstraightforward improvement thereof on four UCI datasets.","url_abs":"http://arxiv.org/abs/1806.07498v1","url_pdf":"http://arxiv.org/pdf/1806.07498v1.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":"defining-locality-for-surrogates-in-post-hoc","repo_url":"https://github.com/axadil/locality-interpretable-surrogate","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.07498","atlas_url":"https://app.syntology.ai/?focus=1806.07498","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1806.07498"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1806.07498\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1806.07498"},"call":"get_concepts_for_paper(arxiv_id=\"1806.07498\")"}],"by_repo":[{"repo":"axadil/locality-interpretable-surrogate","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"2a6a7c7c2daaca5d25384b3a00a5eb126f55af4b3eba587fea5b973c7c6abfee","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}