{"id":"https://openalex.org/W4400435247","doi":"https://doi.org/10.48550/arxiv.2407.04690","title":"Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks","display_name":"Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks","publication_year":2024,"publication_date":"2024-07-05","ids":{"openalex":"https://openalex.org/W4400435247","doi":"https://doi.org/10.48550/arxiv.2407.04690"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2407.04690","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.04690","pdf_url":"https://arxiv.org/pdf/2407.04690","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.04690","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020998070","display_name":"Aaron Mueller","orcid":"https://orcid.org/0009-0005-1148-5001","observed_orcids":["https://orcid.org/0009-0005-1148-5001"]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Mueller, Aaron","raw_affiliation_strings":["Northeastern University Technion -Israel Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University Technion -Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5020998070"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10778","display_name":"Philosophy of Biology and Scientific Explanation","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/counterfactuals","display_name":"counterfactuals","score":0.7609999775886536},{"id":"https://openalex.org/keywords/neural-network-interpretability","display_name":"neural network interpretability","score":0.746999979019165},{"id":"https://openalex.org/keywords/causal-inference","display_name":"causal inference","score":0.5730000138282776},{"id":"https://openalex.org/keywords/counterfactual-intervention","display_name":"counterfactual intervention","score":0.8730000257492065},{"id":"https://openalex.org/keywords/causal-diagrams","display_name":"causal graphs","score":0.6959999799728394},{"id":"https://openalex.org/keywords/model-explainability","display_name":"model explainability","score":0.4099999964237213}],"concepts":[{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.9211252927780151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49768832325935364},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4803844094276428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4716044068336487},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4672990143299103},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.4132688045501709},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.31823909282684326},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.21720242500305176},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08526179194450378}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2407.04690","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.04690","pdf_url":"https://arxiv.org/pdf/2407.04690","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.04690","doi":"https://doi.org/10.48550/arxiv.2407.04690","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.04690","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.04690","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.04690","pdf_url":"https://arxiv.org/pdf/2407.04690","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337253","display_name":"Instituto de Ciencias del Mar y Limnolog\u00eda, Universidad Nacional Aut\u00f3noma de M\u00e9xico","ror":"https://ror.org/040wdye98"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400435247.pdf","grobid_xml":"https://content.openalex.org/works/W4400435247.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2888169584","https://openalex.org/W2978017171","https://openalex.org/W2980827866","https://openalex.org/W3016682301","https://openalex.org/W3092292868","https://openalex.org/W3117576675","https://openalex.org/W3159900299","https://openalex.org/W3172136722","https://openalex.org/W4287854901","https://openalex.org/W4323557327","https://openalex.org/W4365597196","https://openalex.org/W4384918485","https://openalex.org/W4385473442","https://openalex.org/W4385572928","https://openalex.org/W4386721684","https://openalex.org/W4389518250","https://openalex.org/W4389520348","https://openalex.org/W4392428679","https://openalex.org/W4393336283","https://openalex.org/W4395443869","https://openalex.org/W4404782809"],"related_works":["https://openalex.org/W3217151167","https://openalex.org/W4416027175","https://openalex.org/W7118126954","https://openalex.org/W7101622256","https://openalex.org/W7036788306","https://openalex.org/W7160293633","https://openalex.org/W4417485189","https://openalex.org/W3161175241","https://openalex.org/W4394597817","https://openalex.org/W4312495737"],"abstract_inverted_index":{"Interpretability":[0],"research":[1],"takes":[2],"counterfactual":[3,14,62,86],"theories":[4,63],"of":[5,21,28,72,111],"causality":[6],"for":[7,98,114,121],"granted.":[8],"Most":[9],"causal":[10,102],"methods":[11,97],"rely":[12],"on":[13],"interventions":[15],"to":[16,79],"inputs":[17],"or":[18,35],"the":[19,29,73,109],"activations":[20],"particular":[22],"model":[23],"components,":[24],"followed":[25],"by":[26],"observations":[27],"change":[30],"in":[31,55,88],"models'":[32],"output":[33],"logits":[34],"behaviors.":[36],"While":[37],"this":[38],"yields":[39],"more":[40],"faithful":[41],"evidence":[42],"than":[43],"correlational":[44],"methods,":[45],"counterfactuals":[46],"nonetheless":[47],"have":[48],"key":[49],"problems":[50],"that":[51],"bias":[52],"our":[53],"findings":[54],"specific":[56],"and":[57,84,100,117],"predictable":[58],"ways.":[59],"Specifically,":[60],"(i)":[61],"do":[64],"not":[65,93],"effectively":[66],"capture":[67],"multiple":[68],"independently":[69],"sufficient":[70],"causes":[71,82],"same":[74],"effect,":[75],"which":[76,95],"leads":[77],"us":[78],"miss":[80],"certain":[81],"entirely;":[83],"(ii)":[85],"dependencies":[87],"neural":[89,105],"networks":[90],"are":[91],"generally":[92],"transitive,":[94],"complicates":[96],"extracting":[99],"interpreting":[101],"graphs":[103],"from":[104],"networks.":[106],"We":[107],"discuss":[108],"implications":[110],"these":[112],"challenges":[113],"interpretability":[115],"researchers":[116],"propose":[118],"concrete":[119],"suggestions":[120],"future":[122],"work.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-07-09T00:00:00"}