{"id":"https://openalex.org/W4415964956","doi":"https://doi.org/10.1016/j.inffus.2026.104406","title":"Mitigating Clever Hans strategies in image classifiers through generating counterexamples","display_name":"Mitigating Clever Hans strategies in image classifiers through generating counterexamples","publication_year":2026,"publication_date":"2026-04-25","ids":{"openalex":"https://openalex.org/W4415964956","doi":"https://doi.org/10.1016/j.inffus.2026.104406"},"language":"en","primary_location":{"id":"doi:10.1016/j.inffus.2026.104406","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.inffus.2026.104406","pdf_url":null,"source":{"id":"https://openalex.org/S7560371","display_name":"Information Fusion","issn_l":"1566-2535","issn":["1566-2535","1872-6305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Fusion","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.inffus.2026.104406","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022980918","display_name":"Sidney Bender","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139777","display_name":"Berlin Institute of Health at Charit\u00e9 - Universit\u00e4tsmedizin Berlin","ror":"https://ror.org/0493xsw21","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210139777","https://openalex.org/I7877124"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sidney Bender","raw_affiliation_strings":["BIFOLD \u2013 Berlin Institute for the Foundations of Learning and Data, Berlin, 10587, Germany","Machine Learning Group, Technische Universit\u00e4t Berlin, Berlin, 10587, Germany"],"raw_orcid":"https://orcid.org/0009-0007-1727-8577","affiliations":[{"raw_affiliation_string":"BIFOLD \u2013 Berlin Institute for the Foundations of Learning and Data, Berlin, 10587, Germany","institution_ids":["https://openalex.org/I4210139777"]},{"raw_affiliation_string":"Machine Learning Group, Technische Universit\u00e4t Berlin, Berlin, 10587, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120282352","display_name":"Ole Delzer","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ole Delzer","raw_affiliation_strings":["Machine Learning Group, Technische Universit\u00e4t Berlin, Berlin, 10587, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1973-1909","affiliations":[{"raw_affiliation_string":"Machine Learning Group, Technische Universit\u00e4t Berlin, Berlin, 10587, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111451669","display_name":"Jan Herrmann","orcid":"https://orcid.org/0009-0001-7209-0848"},"institutions":[{"id":"https://openalex.org/I4210107087","display_name":"BASF (Germany)","ror":"https://ror.org/01q8f6705","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210107087"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Herrmann","raw_affiliation_strings":["BASF SE, Ludwigshafen am Rhein, 67056, Germany"],"raw_orcid":"https://orcid.org/0009-0001-7209-0848","affiliations":[{"raw_affiliation_string":"BASF SE, Ludwigshafen am Rhein, 67056, Germany","institution_ids":["https://openalex.org/I4210107087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015713326","display_name":"Heike Marxfeld","orcid":"https://orcid.org/0000-0001-5390-0633"},"institutions":[{"id":"https://openalex.org/I4210107087","display_name":"BASF (Germany)","ror":"https://ror.org/01q8f6705","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210107087"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Heike Antje Marxfeld","raw_affiliation_strings":["BASF SE, Ludwigshafen am Rhein, 67056, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5390-0633","affiliations":[{"raw_affiliation_string":"BASF SE, Ludwigshafen am Rhein, 67056, Germany","institution_ids":["https://openalex.org/I4210107087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072994165","display_name":"Klaus-Robert M\u00fcller","orcid":"https://orcid.org/0000-0002-3861-7685"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]},{"id":"https://openalex.org/I4210139777","display_name":"Berlin Institute of Health at Charit\u00e9 - Universit\u00e4tsmedizin Berlin","ror":"https://ror.org/0493xsw21","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210139777","https://openalex.org/I7877124"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE","KR"],"is_corresponding":false,"raw_author_name":"Klaus-Robert M\u00fcller","raw_affiliation_strings":["BIFOLD \u2013 Berlin Institute for the Foundations of Learning and Data, Berlin, 10587, Germany","Department of Artificial Intelligence, Korea University, Seoul, 02841, Korea","Machine Learning Group, Technische Universit\u00e4t Berlin, Berlin, 10587, Germany","Max-Planck Institute for Informatics, Saarbr\u00fccken, 66123, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3861-7685","affiliations":[{"raw_affiliation_string":"BIFOLD \u2013 Berlin Institute for the Foundations of Learning and Data, Berlin, 10587, Germany","institution_ids":["https://openalex.org/I4210139777"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, 02841, Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Machine Learning Group, Technische Universit\u00e4t Berlin, Berlin, 10587, Germany","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Max-Planck Institute for Informatics, Saarbr\u00fccken, 66123, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026240645","display_name":"Gr\u00e9goire Montavon","orcid":"https://orcid.org/0000-0001-7243-6186"},"institutions":[{"id":"https://openalex.org/I4210139777","display_name":"Berlin Institute of Health at Charit\u00e9 - Universit\u00e4tsmedizin Berlin","ror":"https://ror.org/0493xsw21","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210139777","https://openalex.org/I7877124"]},{"id":"https://openalex.org/I7877124","display_name":"Charit\u00e9 - Universit\u00e4tsmedizin Berlin","ror":"https://ror.org/001w7jn25","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I7877124"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Gr\u00e9goire Montavon","raw_affiliation_strings":["BIFOLD \u2013 Berlin Institute for the Foundations of Learning and Data, Berlin, 10587, Germany","Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin, Berlin, 10115, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7243-6186","affiliations":[{"raw_affiliation_string":"BIFOLD \u2013 Berlin Institute for the Foundations of Learning and Data, Berlin, 10587, Germany","institution_ids":["https://openalex.org/I4210139777"]},{"raw_affiliation_string":"Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin, Berlin, 10115, Germany","institution_ids":["https://openalex.org/I7877124"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5026240645"],"corresponding_institution_ids":["https://openalex.org/I4210139777","https://openalex.org/I7877124"],"apc_list":{"value":4740,"currency":"USD","value_usd":4740},"apc_paid":{"value":4740,"currency":"USD","value_usd":4740},"fwci":13.5756,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.97433013,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"135","issue":null,"first_page":"104406","last_page":"104406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.43639999628067017,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.43639999628067017,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.22179999947547913,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.09269999712705612,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.9189000129699707},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.8849999904632568},{"id":"https://openalex.org/keywords/counterexample","display_name":"Counterexample","score":0.682200014591217},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6722999811172485},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.41350001096725464},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.35929998755455017},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.34540000557899475},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3334999978542328}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.9189000129699707},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8849999904632568},{"id":"https://openalex.org/C162838799","wikidata":"https://www.wikidata.org/wiki/Q596077","display_name":"Counterexample","level":2,"score":0.682200014591217},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6722999811172485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6513000130653381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6187999844551086},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6087999939918518},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3212999999523163},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C169345407","wikidata":"https://www.wikidata.org/wiki/Q8216221","display_name":"Uncorrelated","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.2533999979496002},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.inffus.2026.104406","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.inffus.2026.104406","pdf_url":null,"source":{"id":"https://openalex.org/S7560371","display_name":"Information Fusion","issn_l":"1566-2535","issn":["1566-2535","1872-6305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Fusion","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2510.17524","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.17524","pdf_url":"https://arxiv.org/pdf/2510.17524","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.17524","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.17524","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1016/j.inffus.2026.104406","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.inffus.2026.104406","pdf_url":null,"source":{"id":"https://openalex.org/S7560371","display_name":"Information Fusion","issn_l":"1566-2535","issn":["1566-2535","1872-6305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Fusion","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3411782263","display_name":null,"funder_award_id":"01IS18037 A","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4711502783","display_name":null,"funder_award_id":"2022-0-00984","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6435501467","display_name":null,"funder_award_id":"RS-2022-II220984","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320307790","display_name":"BASF","ror":"https://ror.org/01q8f6705"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320324094","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0,31],"learning":[1],"models":[2],"remain":[3],"vulnerable":[4],"to":[5,10,40,101,145,164],"spurious":[6,72,177],"correlations":[7,73],",":[8],"leading":[9],"so-called":[11],"Clever":[12],"Hans":[13],"predictors":[14],"that":[15,89],"undermine":[16],"robustness":[17,27],"even":[18,78],"in":[19,172],"large-scale":[20],"foundation":[21],"and":[22,65,104,148,193],"self-supervised":[23],"models.":[24],"Group":[25],"distributional":[26],"methods,":[28],"such":[29],"as":[30],"Feature":[32],"Reweighting":[33],"(DFR)":[34],"rely":[35],"on":[36,185,199],"explicit":[37],"group":[38,49],"labels":[39,50],"upweight":[41],"underrepresented":[42],"subgroups,":[43],"but":[44,125],"face":[45],"key":[46],"limitations:":[47],"(1)":[48],"are":[51],"often":[52],"unavailable,":[53],"(2)":[54],"low":[55],"within-group":[56],"sample":[57],"sizes":[58],"hinder":[59],"coverage":[60],"of":[61,188],"the":[62,75,106,122,186,189],"subgroup":[63],"distribution,":[64],"(3)":[66],"performance":[67],"degrades":[68],"sharply":[69],"when":[70],"multiple":[71,146],"fragment":[74],"data":[76,132],"into":[77],"smaller":[79],"groups.":[80,153],"We":[81,154],"propose":[82],"Counterfactual":[83],"Knowledge":[84],"Distillation":[85],"(CFKD),":[86],"a":[87,98,111],"framework":[88],"sidesteps":[90],"these":[91],"issues":[92],"by":[93],"generating":[94],"diverse":[95],"counterfactuals,":[96],"enabling":[97],"human":[99],"annotator":[100],"efficiently":[102],"explore":[103],"correct":[105],"model\u2019s":[107],"decision":[108],"boundaries":[109],"through":[110],"knowledge":[112],"distillation":[113],"step.":[114],"Unlike":[115],"DFR,":[116],"our":[117],"method":[118,135],"not":[119,137],"only":[120],"reweights":[121],"undersampled":[123],"groups,":[124],"it":[126],"also":[127],"enriches":[128],"them":[129],"with":[130,168,175],"new":[131],"points.":[133],"Our":[134],"does":[136],"require":[138],"any":[139],"confounder":[140],"labels,":[141],"achieves":[142],"effective":[143],"scaling":[144],"confounders,":[147],"yields":[149],"balanced":[150],"generalization":[151],"across":[152,158],"demonstrate":[155],"CFKD\u2019s":[156],"efficacy":[157],"five":[159],"datasets,":[160],"spanning":[161],"synthetic":[162],"tasks":[163],"an":[165,182],"industrial":[166],"application,":[167],"particularly":[169],"strong":[170],"gains":[171],"low-data":[173],"regimes":[174],"pronounced":[176],"correlations.":[178],"Additionally,":[179],"we":[180],"provide":[181],"ablation":[183],"study":[184],"effect":[187],"chosen":[190],"counterfactual":[191],"explainer":[192],"teacher":[194],"model,":[195],"highlighting":[196],"their":[197],"impact":[198],"robustness.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-22T00:00:00"}