{"id":"https://openalex.org/W7162644904","doi":"https://doi.org/10.48550/arxiv.2605.27618","title":"Evaluating Local Explainability Metrics for Machine Learning Models on Tabular Data","display_name":"Evaluating Local Explainability Metrics for Machine Learning Models on Tabular Data","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162644904","doi":"https://doi.org/10.48550/arxiv.2605.27618"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.27618","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27618","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.27618","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137252728","display_name":"Tom\u00e1s Pereira","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pereira, Tom\u00e1s","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137218545","display_name":"Jo\u00e3o Vitorino","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vitorino, Jo\u00e3o","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093364042","display_name":"Eva Maia","orcid":"https://orcid.org/0000-0003-0775-8677"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maia, Eva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130968350","display_name":"Isabel Pra\u00e7a","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pra\u00e7a, Isabel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.991100013256073,"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":0.991100013256073,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0008999999845400453,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6499999761581421},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4973999857902527},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47049999237060547},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.42160001397132874},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4083000123500824},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.4081000089645386},{"id":"https://openalex.org/keywords/multiple-kernel-learning","display_name":"Multiple kernel learning","score":0.3474999964237213}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7204999923706055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6786999702453613},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6499999761581421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6237000226974487},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4973999857902527},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47049999237060547},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C2776879701","wikidata":"https://www.wikidata.org/wiki/Q25048660","display_name":"Multiple kernel learning","level":4,"score":0.3474999964237213},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30390000343322754},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.27410000562667847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.27618","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27618","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.27618","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27618","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,11,17,36,52,74,85,149,169],"wide":[2],"use":[3],"of":[4,13,39,54,84,113],"explainability":[5,56],"techniques":[6,57],"to":[7,9,30,34,60,73,78,122,167],"attempt":[8],"understand":[10],"behavior":[12],"Artificial":[14],"Intelligence":[15],"(AI),":[16],"generated":[18],"explanations":[19,150],"may":[20],"not":[21,152],"always":[22,153],"be":[23,168],"reliable.":[24],"An":[25],"explanation":[26,86,173],"can":[27],"appear":[28],"plausible":[29],"humans":[31],"but":[32],"fail":[33],"capture":[35],"internal":[37],"reasoning":[38],"a":[40,156],"model,":[41],"particularly":[42],"when":[43,58],"dealing":[44],"with":[45,155],"complex":[46,61],"tabular":[47,62],"data.":[48],"This":[49],"paper":[50],"studies":[51],"trustworthiness":[53],"local":[55],"applied":[59],"classification":[63],"tasks,":[64],"considering":[65],"evaluated":[66],"metrics":[67],"for":[68,92],"three":[69],"main":[70,170],"properties:":[71],"faithfulness":[72],"model's":[75,157],"predictions,":[76],"robustness":[77],"input":[79],"data":[80],"variations,":[81],"and":[82,103,110,135,163,175],"complexity":[83,162],"itself.":[87],"A":[88],"benchmark":[89],"was":[90],"performed":[91],"Local":[93],"Interpretable":[94],"Model-Agnostic":[95],"Explanations":[96],"(LIME),":[97],"Kernel":[98],"SHapley":[99],"Additive":[100],"exPlanations":[101],"(SHAP),":[102],"Feature":[104],"Ablation":[105],"techniques,":[106],"across":[107],"32":[108],"datasets":[109],"different":[111],"types":[112],"machine":[114],"learning":[115],"models.":[116],"Model":[117],"performance":[118],"ranges":[119],"were":[120],"analyzed":[121],"identify":[123],"two":[124],"groups:":[125],"consensus-correct,":[126],"which":[127],"are":[128,151],"samples":[129,137],"that":[130,138,147,148],"all":[131,139],"models":[132,140],"predicted":[133,141],"correctly,":[134],"consensus-wrong,":[136],"incorrectly.":[142],"The":[143],"obtained":[144],"results":[145],"demonstrate":[146],"correlated":[154],"predictive":[158],"performance.":[159],"Instead,":[160],"dataset":[161],"feature":[164],"distributions":[165],"seem":[166],"factors":[171],"affecting":[172],"quality":[174],"reliability.":[176]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-29T00:00:00"}