{"id":"https://openalex.org/W4392763822","doi":"https://doi.org/10.1007/s10994-023-06502-x","title":"Glacier: guided locally constrained counterfactual explanations for time series classification","display_name":"Glacier: guided locally constrained counterfactual explanations for time series classification","publication_year":2024,"publication_date":"2024-03-13","ids":{"openalex":"https://openalex.org/W4392763822","doi":"https://doi.org/10.1007/s10994-023-06502-x"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-023-06502-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06502-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06502-x.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06502-x.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073744353","display_name":"Zhendong Wang","orcid":"https://orcid.org/0000-0002-8575-421X"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Zhendong Wang","raw_affiliation_strings":["Stockholm University, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Stockholm University, Stockholm, Sweden","institution_ids":["https://openalex.org/I161593684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013519991","display_name":"Isak Samsten","orcid":"https://orcid.org/0000-0002-3056-6801"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Isak Samsten","raw_affiliation_strings":["Stockholm University, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Stockholm University, Stockholm, Sweden","institution_ids":["https://openalex.org/I161593684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060236527","display_name":"Ioanna Miliou","orcid":"https://orcid.org/0000-0002-1357-1967"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ioanna Miliou","raw_affiliation_strings":["Stockholm University, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Stockholm University, Stockholm, Sweden","institution_ids":["https://openalex.org/I161593684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017148994","display_name":"Rami Mochaourab","orcid":"https://orcid.org/0000-0003-0995-9835"},"institutions":[{"id":"https://openalex.org/I2800664555","display_name":"RISE Research Institutes of Sweden","ror":"https://ror.org/03nnxqz81","country_code":"SE","type":"other","lineage":["https://openalex.org/I2800664555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Rami Mochaourab","raw_affiliation_strings":["RISE Research Institutes of Sweden, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"RISE Research Institutes of Sweden, Stockholm, Sweden","institution_ids":["https://openalex.org/I2800664555"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044999523","display_name":"Panagiotis Papapetrou","orcid":"https://orcid.org/0000-0002-4632-4815"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Panagiotis Papapetrou","raw_affiliation_strings":["Stockholm University, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Stockholm University, Stockholm, Sweden","institution_ids":["https://openalex.org/I161593684"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073744353"],"corresponding_institution_ids":["https://openalex.org/I161593684"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":3.7647,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93911615,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"113","issue":"7","first_page":"4639","last_page":"4669"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.982699990272522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.8807574510574341},{"id":"https://openalex.org/keywords/counterfactual-conditional","display_name":"Counterfactual conditional","score":0.7487739324569702},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6348834037780762},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5802040696144104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5459722876548767},{"id":"https://openalex.org/keywords/univariate","display_name":"Univariate","score":0.46936896443367004},{"id":"https://openalex.org/keywords/competitor-analysis","display_name":"Competitor analysis","score":0.45229753851890564},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.4317411780357361},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4275458753108978},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.4188568592071533},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2740347981452942},{"id":"https://openalex.org/keywords/multivariate-statistics","display_name":"Multivariate statistics","score":0.1978868544101715},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14183557033538818},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.09373095631599426},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08116763830184937}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8807574510574341},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.7487739324569702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6348834037780762},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5802040696144104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5459722876548767},{"id":"https://openalex.org/C199163554","wikidata":"https://www.wikidata.org/wiki/Q1681619","display_name":"Univariate","level":3,"score":0.46936896443367004},{"id":"https://openalex.org/C127576917","wikidata":"https://www.wikidata.org/wiki/Q624630","display_name":"Competitor analysis","level":2,"score":0.45229753851890564},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.4317411780357361},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4275458753108978},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.4188568592071533},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2740347981452942},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.1978868544101715},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14183557033538818},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.09373095631599426},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08116763830184937},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10994-023-06502-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06502-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06502-x.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:DiVA.org:ri-72856","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:ri:diva-72856","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"pmh:oai:arpi.unipi.it:11568/1300468","is_oa":false,"landing_page_url":"https://hdl.handle.net/11568/1300468","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"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":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10994-023-06502-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06502-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06502-x.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6499999761581421,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F379871122","display_name":"Digital Futures","ror":null},{"id":"https://openalex.org/F4320325669","display_name":"Stockholms Universitet","ror":"https://ror.org/05f0yaq80"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392763822.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W2020571458","https://openalex.org/W2118657370","https://openalex.org/W2282821441","https://openalex.org/W2468738844","https://openalex.org/W2524083015","https://openalex.org/W2553915786","https://openalex.org/W2555077524","https://openalex.org/W2618995589","https://openalex.org/W2754051771","https://openalex.org/W2765204106","https://openalex.org/W2892035503","https://openalex.org/W2911964244","https://openalex.org/W2945295328","https://openalex.org/W2945315238","https://openalex.org/W2970801625","https://openalex.org/W2972810968","https://openalex.org/W2982438846","https://openalex.org/W3004999940","https://openalex.org/W3016419862","https://openalex.org/W3018234152","https://openalex.org/W3023497337","https://openalex.org/W3034697737","https://openalex.org/W3042807565","https://openalex.org/W3081435493","https://openalex.org/W3083891030","https://openalex.org/W3099844187","https://openalex.org/W3104149808","https://openalex.org/W3107975486","https://openalex.org/W3112088560","https://openalex.org/W3121603028","https://openalex.org/W3125923948","https://openalex.org/W3125997628","https://openalex.org/W3166235221","https://openalex.org/W3193042250","https://openalex.org/W3199714491","https://openalex.org/W3202810143","https://openalex.org/W3207741336","https://openalex.org/W4210974218","https://openalex.org/W4221016718","https://openalex.org/W6730267373","https://openalex.org/W6773686317"],"related_works":["https://openalex.org/W2056582926","https://openalex.org/W3137864021","https://openalex.org/W2162910442","https://openalex.org/W2079879923","https://openalex.org/W4200271736","https://openalex.org/W3017854570","https://openalex.org/W2104420793","https://openalex.org/W2028689793","https://openalex.org/W4313936361","https://openalex.org/W4242448314"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"machine":[2],"learning":[3],"applications,":[4],"there":[5],"is":[6,37,127,138,169],"a":[7,57,66,75,101,123,270],"need":[8,52],"to":[9,19,24,33,53,74,152,170,241,255],"obtain":[10,34],"predictive":[11],"models":[12],"of":[13,47,65,84,135,141,166,179,187,211,225,244,254,264],"high":[14],"performance":[15,272],"and,":[16],"most":[17],"importantly,":[18],"allow":[20],"end-users":[21],"and":[22,26,194,233,266],"practitioners":[23],"understand":[25],"act":[27],"on":[28,49,81,90,117,122,143,201],"their":[29],"predictions.":[30],"One":[31],"way":[32],"such":[35],"understanding":[36],"via":[38],"counterfactuals,":[39,174,230],"that":[40,61,126,148,218,261],"provide":[41],"sample-based":[42],"explanations":[43,93,108],"in":[44,223],"the":[45,62,82,118,139,144,177,180,205,220,242,245,251,256,262,275,278],"form":[46],"recommendations":[48],"which":[50],"features":[51],"be":[54],"modified":[55],"from":[56,70,204],"test":[58],"example":[59],"so":[60],"classification":[63,112],"outcome":[64,73],"given":[67],"classifier":[68],"changes":[69,151],"an":[71,130],"undesired":[72],"desired":[76],"one.":[77],"This":[78],"paper":[79],"focuses":[80],"domain":[83],"time":[85,96,110,154],"series":[86,111,155],"classification,":[87],"more":[88,172],"specifically,":[89],"defining":[91],"counterfactual":[92,107,145,181,238],"for":[94,104,109,229],"univariate":[95],"series.":[97],"We":[98,197],"propose":[99],",":[100],"model-agnostic":[102],"method":[103,137],"generating":[105],"locally-constrained":[106],"using":[113],"gradient":[114],"search":[115],"either":[116],"original":[119],"space":[120,125],"or":[121,157],"latent":[124],"learned":[128],"through":[129],"auto-encoder.":[131],"An":[132],"additional":[133],"flexibility":[134],"our":[136],"inclusion":[140,263],"constraints":[142,168,188,193,268],"generation":[146,182],"process":[147],"favour":[149],"applying":[150],"particular":[153,185],"points":[156],"segments":[158],"while":[159,175,273],"discouraging":[160],"changing":[161],"others.":[162],"The":[163],"main":[164],"purpose":[165],"these":[167],"ensure":[171],"reliable":[173],"increasing":[176],"efficiency":[178],"process.":[183],"Two":[184],"types":[186],"are":[189],"considered,":[190],"i.e.,":[191,231],"example-specific":[192,265],"global":[195,267],"constraints.":[196],"conduct":[198],"extensive":[199],"experiments":[200],"40":[202],"datasets":[203],"UCR":[206],"archive,":[207],"comparing":[208,250],"different":[209,279],"instantiations":[210],"against":[212],"three":[213,221,246],"competitors.":[214,247],"Our":[215],"findings":[216],"suggest":[217],"outperforms":[219],"competitors":[222],"terms":[224],"two":[226],"common":[227],"metrics":[228],"proximity":[232],"compactness.":[234],"Moreover,":[235],"obtains":[236],"comparable":[237],"validity":[239],"compared":[240],"best":[243],"Finally,":[248],"when":[249],"unconstrained":[252],"variant":[253],"constraint-based":[257],"variants,":[258],"we":[259],"conclude":[260],"yields":[269],"good":[271],"demonstrating":[274],"trade-off":[276],"between":[277],"metrics.":[280]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}