{"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/getting-a-clue-a-method-for-explaining","title":"Getting a CLUE: A Method for Explaining Uncertainty Estimates","arxiv_id":"2006.06848","date":"2020-06-11","proceeding":"ICLR 2021 1","authors":["Javier Antorán","Umang Bhatt","Tameem Adel","Adrian Weller","José Miguel Hernández-Lobato"],"abstract":"Both uncertainty estimation and interpretability are important factors for trustworthy machine learning systems. However, there is little work at the intersection of these two areas. We address this gap by proposing a novel method for interpreting uncertainty estimates from differentiable probabilistic models, like Bayesian Neural Networks (BNNs). Our method, Counterfactual Latent Uncertainty Explanations (CLUE), indicates how to change an input, while keeping it on the data manifold, such that a BNN becomes more confident about the input's prediction. We validate CLUE through 1) a novel framework for evaluating counterfactual explanations of uncertainty, 2) a series of ablation experiments, and 3) a user study. Our experiments show that CLUE outperforms baselines and enables practitioners to better understand which input patterns are responsible for predictive uncertainty.","url_abs":"https://arxiv.org/abs/2006.06848v2","url_pdf":"https://arxiv.org/pdf/2006.06848v2.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":"getting-a-clue-a-method-for-explaining","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"}}],"tasks":[{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2006.06848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06848"}},"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":"deterministic:regex_extraction","url":"https://github.com/cambridge-mlg/CLUE","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/propublica/compas-analysis","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/carla-recourse/CARLA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"found_in_text":{"samples":8,"ran":0,"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":"c0a6c860eb0a4920","entry":"X_dims_to_input_dim_vec","repo":"cambridge-mlg/CLUE","repo_kind":"found_in_text","path":"src/compas_loader.py","file_url":"https://github.com/cambridge-mlg/CLUE/blob/HEAD/src/compas_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c0a6c860eb0a4920"}},{"code_sha256_prefix":"d18f0dd4a69ae09c","entry":"check_data_file","repo":"cambridge-mlg/CLUE","repo_kind":"found_in_text","path":"src/LSAT_loader.py","file_url":"https://github.com/cambridge-mlg/CLUE/blob/HEAD/src/LSAT_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d18f0dd4a69ae09c"}},{"code_sha256_prefix":"8872f711e7965d33","entry":"get_my_COMPAS","repo":"cambridge-mlg/CLUE","repo_kind":"found_in_text","path":"src/compas_loader.py","file_url":"https://github.com/cambridge-mlg/CLUE/blob/HEAD/src/compas_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8872f711e7965d33"}},{"code_sha256_prefix":"967e06b170f2f53b","entry":"get_my_LSAT","repo":"cambridge-mlg/CLUE","repo_kind":"found_in_text","path":"src/LSAT_loader.py","file_url":"https://github.com/cambridge-mlg/CLUE/blob/HEAD/src/LSAT_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"967e06b170f2f53b"}},{"code_sha256_prefix":"50f57aef8a925df8","entry":"input_dim_vec_to_X_dims","repo":"cambridge-mlg/CLUE","repo_kind":"found_in_text","path":"src/LSAT_loader.py","file_url":"https://github.com/cambridge-mlg/CLUE/blob/HEAD/src/LSAT_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50f57aef8a925df8"}},{"code_sha256_prefix":"9f964290543f2ad8","entry":"join_compas_targets","repo":"cambridge-mlg/CLUE","repo_kind":"found_in_text","path":"src/compas_loader.py","file_url":"https://github.com/cambridge-mlg/CLUE/blob/HEAD/src/compas_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f964290543f2ad8"}},{"code_sha256_prefix":"325087ca64c93dc9","entry":"load_doodle_dset","repo":"cambridge-mlg/CLUE","repo_kind":"found_in_text","path":"src/doodle_loader.py","file_url":"https://github.com/cambridge-mlg/CLUE/blob/HEAD/src/doodle_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"325087ca64c93dc9"}},{"code_sha256_prefix":"252202c54d21c615","entry":"unnormalise_cat_vars","repo":"cambridge-mlg/CLUE","repo_kind":"found_in_text","path":"src/UCI_loader.py","file_url":"https://github.com/cambridge-mlg/CLUE/blob/HEAD/src/UCI_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"252202c54d21c615"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}