{"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/explanations-based-on-the-missing-towards","title":"Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives","arxiv_id":"1802.07623","date":"2018-02-21","proceeding":"NeurIPS 2018 12","authors":["Amit Dhurandhar","Pin-Yu Chen","Ronny Luss","Chun-Chen Tu","Pai-Shun Ting","Karthikeyan Shanmugam","Payel Das"],"abstract":"In this paper we propose a novel method that provides contrastive\nexplanations justifying the classification of an input by a black box\nclassifier such as a deep neural network. Given an input we find what should be\n%necessarily and minimally and sufficiently present (viz. important object\npixels in an image) to justify its classification and analogously what should\nbe minimally and necessarily \\emph{absent} (viz. certain background pixels). We\nargue that such explanations are natural for humans and are used commonly in\ndomains such as health care and criminology. What is minimally but critically\n\\emph{absent} is an important part of an explanation, which to the best of our\nknowledge, has not been explicitly identified by current explanation methods\nthat explain predictions of neural networks. We validate our approach on three\nreal datasets obtained from diverse domains; namely, a handwritten digits\ndataset MNIST, a large procurement fraud dataset and a brain activity strength\ndataset. In all three cases, we witness the power of our approach in generating\nprecise explanations that are also easy for human experts to understand and\nevaluate.","url_abs":"http://arxiv.org/abs/1802.07623v2","url_pdf":"http://arxiv.org/pdf/1802.07623v2.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":"explanations-based-on-the-missing-towards","repo_url":"https://github.com/IBM/Contrastive-Explanation-Method","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"explanations-based-on-the-missing-towards","repo_url":"https://github.com/carla-recourse/CARLA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"explanations-based-on-the-missing-towards","repo_url":"https://github.com/dailab/maxi-xai-lib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"explanations-based-on-the-missing-towards","repo_url":"https://github.com/SeldonIO/alibi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.07623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.07623"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/dailab/maxi-xai-lib","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/carla-recourse/CARLA","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SeldonIO/alibi","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IBM/Contrastive-Explanation-Method","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":"86c9fa246614e9a9","entry":"extract_data","repo":"IBM/Contrastive-Explanation-Method","repo_kind":"official","path":"setup_mnist.py","file_url":"https://github.com/IBM/Contrastive-Explanation-Method/blob/HEAD/setup_mnist.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86c9fa246614e9a9"}},{"code_sha256_prefix":"a0cf6bb81ff7819e","entry":"extract_labels","repo":"IBM/Contrastive-Explanation-Method","repo_kind":"official","path":"setup_mnist.py","file_url":"https://github.com/IBM/Contrastive-Explanation-Method/blob/HEAD/setup_mnist.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a0cf6bb81ff7819e"}},{"code_sha256_prefix":"f8fb91c06db9efe1","entry":"generate_data","repo":"IBM/Contrastive-Explanation-Method","repo_kind":"official","path":"Utils.py","file_url":"https://github.com/IBM/Contrastive-Explanation-Method/blob/HEAD/Utils.py","link_basis":"harvester_set","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":"f8fb91c06db9efe1"}},{"code_sha256_prefix":"d6d05eebf4a4b6e9","entry":"load_AE","repo":"IBM/Contrastive-Explanation-Method","repo_kind":"official","path":"Utils.py","file_url":"https://github.com/IBM/Contrastive-Explanation-Method/blob/HEAD/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":"d6d05eebf4a4b6e9"}},{"code_sha256_prefix":"b02a81555adb2686","entry":"model_prediction","repo":"IBM/Contrastive-Explanation-Method","repo_kind":"official","path":"Utils.py","file_url":"https://github.com/IBM/Contrastive-Explanation-Method/blob/HEAD/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":"b02a81555adb2686"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}