{"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/on-the-robustness-of-interpretability-methods","title":"On the Robustness of Interpretability Methods","arxiv_id":"1806.08049","date":"2018-06-21","proceeding":null,"authors":["David Alvarez-Melis","Tommi S. Jaakkola"],"abstract":"We argue that robustness of explanations---i.e., that similar inputs should\ngive rise to similar explanations---is a key desideratum for interpretability.\nWe introduce metrics to quantify robustness and demonstrate that current\nmethods do not perform well according to these metrics. Finally, we propose\nways that robustness can be enforced on existing interpretability approaches.","url_abs":"http://arxiv.org/abs/1806.08049v1","url_pdf":"http://arxiv.org/pdf/1806.08049v1.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":"on-the-robustness-of-interpretability-methods","repo_url":"https://github.com/viggotw/robustness-of-interpretability-methods","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"on-the-robustness-of-interpretability-methods","repo_url":"https://github.com/pytorch/captum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"on-the-robustness-of-interpretability-methods","repo_url":"https://github.com/viggotw/Robustness-of-Interpretability-Methods/blob/main/README.md","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.08049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.08049"}},"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/pytorch/captum","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/viggotw/robustness-of-interpretability-methods","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/viggotw/Robustness-of-Interpretability-Methods/blob/main/README.md","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran_fixture":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":"7ff3fa2ba3fff337","entry":"explainer_func_wrapper","repo":"viggotw/robustness-of-interpretability-methods","repo_kind":"listed","path":"lipschitz_metric.py","file_url":"https://github.com/viggotw/robustness-of-interpretability-methods/blob/HEAD/lipschitz_metric.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7ff3fa2ba3fff337"}},{"code_sha256_prefix":"d56459ad1ce86e13","entry":"get_perturbations","repo":"viggotw/robustness-of-interpretability-methods","repo_kind":"listed","path":"lipschitz_metric.py","file_url":"https://github.com/viggotw/robustness-of-interpretability-methods/blob/HEAD/lipschitz_metric.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d56459ad1ce86e13"}},{"code_sha256_prefix":"d8c6a9cd6d06c3c4","entry":"lipschitz_metric","repo":"viggotw/robustness-of-interpretability-methods","repo_kind":"listed","path":"lipschitz_metric.py","file_url":"https://github.com/viggotw/robustness-of-interpretability-methods/blob/HEAD/lipschitz_metric.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d8c6a9cd6d06c3c4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}