{"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/counterfactual-explanations-without-opening","title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR","arxiv_id":"1711.00399","date":"2017-11-01","proceeding":null,"authors":["Sandra Wachter","Brent Mittelstadt","Chris Russell"],"abstract":"There has been much discussion of the right to explanation in the EU General\nData Protection Regulation, and its existence, merits, and disadvantages.\nImplementing a right to explanation that opens the black box of algorithmic\ndecision-making faces major legal and technical barriers. Explaining the\nfunctionality of complex algorithmic decision-making systems and their\nrationale in specific cases is a technically challenging problem. Some\nexplanations may offer little meaningful information to data subjects, raising\nquestions around their value. Explanations of automated decisions need not\nhinge on the general public understanding how algorithmic systems function.\nEven though such interpretability is of great importance and should be pursued,\nexplanations can, in principle, be offered without opening the black box.\nLooking at explanations as a means to help a data subject act rather than\nmerely understand, one could gauge the scope and content of explanations\naccording to the specific goal or action they are intended to support. From the\nperspective of individuals affected by automated decision-making, we propose\nthree aims for explanations: (1) to inform and help the individual understand\nwhy a particular decision was reached, (2) to provide grounds to contest the\ndecision if the outcome is undesired, and (3) to understand what would need to\nchange in order to receive a desired result in the future, based on the current\ndecision-making model. We assess how each of these goals finds support in the\nGDPR. We suggest data controllers should offer a particular type of\nexplanation, unconditional counterfactual explanations, to support these three\naims. These counterfactual explanations describe the smallest change to the\nworld that can be made to obtain a desirable outcome, or to arrive at the\nclosest possible world, without needing to explain the internal logic of the\nsystem.","url_abs":"http://arxiv.org/abs/1711.00399v3","url_pdf":"http://arxiv.org/pdf/1711.00399v3.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":"counterfactual-explanations-without-opening","repo_url":"https://github.com/interpretml/DiCE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"counterfactual-explanations-without-opening","repo_url":"https://github.com/wangyongjie-ntu/CFAI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"counterfactual-explanations-without-opening","repo_url":"https://github.com/wangyongjie-ntu/Counterfactual-Explanations-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"counterfactual-explanations-without-opening","repo_url":"https://github.com/carla-recourse/CARLA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":"counterfactuals","method_name":"Counterfactuals"},{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[{"slug":"counterfactuals","name":"Counterfactuals","full_name":"Counterfactuals Explanations"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.00399","atlas_url":"https://app.syntology.ai/?focus=1711.00399","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":"1711.00399"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1711.00399\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1711.00399"},"call":"get_concepts_for_paper(arxiv_id=\"1711.00399\")"}],"by_repo":[{"repo":"interpretml/DiCE","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"wangyongjie-ntu/CFAI","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"wangyongjie-ntu/Counterfactual-Explanations-Pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"carla-recourse/CARLA","kind":"listed","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":"b1f81f8f82e956b56f9d0f1748ff0145251eba0ed6e210b3771667680c30c8a2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}