{"id":"https://openalex.org/W4414359231","doi":"https://doi.org/10.24963/ijcai.2025/826","title":"Lazy Testing of Machine-Learning Models","display_name":"Lazy Testing of Machine-Learning Models","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359231","doi":"https://doi.org/10.24963/ijcai.2025/826"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/826","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/826","pdf_url":"https://www.ijcai.org/proceedings/2025/0826.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2025/0826.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092526829","display_name":"Anastasia Isychev","orcid":"https://orcid.org/0000-0001-6375-0421"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Anastasia Isychev","raw_affiliation_strings":["TU Wien, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087604407","display_name":"Valentin W\u00fcstholz","orcid":"https://orcid.org/0000-0003-1496-1104"},"institutions":[{"id":"https://openalex.org/I4210102518","display_name":"ConsenSys (United States)","ror":"https://ror.org/01a2p6r88","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102518"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Valentin W\u00fcstholz","raw_affiliation_strings":["Consensys, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Consensys, Austria","institution_ids":["https://openalex.org/I4210102518"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064181052","display_name":"Maria Christakis","orcid":"https://orcid.org/0000-0002-2649-1958"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Maria Christakis","raw_affiliation_strings":["TU Wien, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien, Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2069625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7428","last_page":"7436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.37049999833106995,"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":0.37049999833106995,"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/T10320","display_name":"Neural Networks and Applications","score":0.35499998927116394,"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/T14470","display_name":"Advanced Data Processing Techniques","score":0.3481000065803528,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5877000093460083},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5455999970436096},{"id":"https://openalex.org/keywords/model-based-testing","display_name":"Model-based testing","score":0.5232999920845032},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5166000127792358},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4627000093460083},{"id":"https://openalex.org/keywords/stress-testing","display_name":"Stress testing (software)","score":0.40779998898506165},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.3529999852180481},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.3440999984741211},{"id":"https://openalex.org/keywords/manual-testing","display_name":"Manual testing","score":0.33550000190734863},{"id":"https://openalex.org/keywords/non-regression-testing","display_name":"Non-regression testing","score":0.33500000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440999746322632},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5877000093460083},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5455999970436096},{"id":"https://openalex.org/C165825675","wikidata":"https://www.wikidata.org/wiki/Q1399743","display_name":"Model-based testing","level":4,"score":0.5232999920845032},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.46369999647140503},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C7515471","wikidata":"https://www.wikidata.org/wiki/Q1936882","display_name":"Stress testing (software)","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3529999852180481},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C182122060","wikidata":"https://www.wikidata.org/wiki/Q6752328","display_name":"Manual testing","level":5,"score":0.33550000190734863},{"id":"https://openalex.org/C86469151","wikidata":"https://www.wikidata.org/wiki/Q917415","display_name":"Non-regression testing","level":5,"score":0.33500000834465027},{"id":"https://openalex.org/C106159264","wikidata":"https://www.wikidata.org/wiki/Q17146789","display_name":"Random testing","level":4,"score":0.3327000141143799},{"id":"https://openalex.org/C161821725","wikidata":"https://www.wikidata.org/wiki/Q917415","display_name":"Regression testing","level":5,"score":0.3188999891281128},{"id":"https://openalex.org/C107683887","wikidata":"https://www.wikidata.org/wiki/Q782466","display_name":"Integration testing","level":3,"score":0.3133000135421753},{"id":"https://openalex.org/C80823478","wikidata":"https://www.wikidata.org/wiki/Q4493432","display_name":"Functional testing","level":3,"score":0.3102000057697296},{"id":"https://openalex.org/C151552104","wikidata":"https://www.wikidata.org/wiki/Q7705809","display_name":"Test suite","level":4,"score":0.3052000105381012},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C169168650","wikidata":"https://www.wikidata.org/wiki/Q1675637","display_name":"Keyword-driven testing","level":5,"score":0.28110000491142273},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C80478641","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential analysis","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C178059732","wikidata":"https://www.wikidata.org/wiki/Q1982529","display_name":"Software performance testing","level":5,"score":0.2619999945163727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26080000400543213},{"id":"https://openalex.org/C2984328558","wikidata":"https://www.wikidata.org/wiki/Q188522","display_name":"Software testing","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C108913964","wikidata":"https://www.wikidata.org/wiki/Q2376856","display_name":"System under test","level":4,"score":0.25060001015663147},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/826","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/826","pdf_url":"https://www.ijcai.org/proceedings/2025/0826.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2025/826","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/826","pdf_url":"https://www.ijcai.org/proceedings/2025/0826.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3032849772","display_name":null,"funder_award_id":"TRR 248","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G548609350","display_name":"Automated Reasoning","funder_award_id":"DOC 1345324","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G8590477180","display_name":null,"funder_award_id":"10.55776","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G890954746","display_name":"TRR 248: Grundlagen verst\u00e4ndlicher SoftwareSysteme  f\u00fcr eine nachvollziehbare cyberphysische Welt","funder_award_id":"389792660","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414359231.pdf","grobid_xml":"https://content.openalex.org/works/W4414359231.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Checking":[0],"the":[1,84,91,109,115,142,151],"reliability":[2],"of":[3,24,52,62,79,86,154],"machine-learning":[4],"models":[5],"is":[6,13,57],"a":[7,132,147],"crucial,":[8],"but":[9,158],"challenging":[10],"task.":[11],"Nomos":[12,36,80],"an":[14,77],"existing,":[15],"automated":[16],"framework":[17],"for":[18],"testing":[19,56],"general,":[20],"user-provided":[21],"functional":[22],"properties":[23],"models,":[25],"including":[26],"so-called":[27],"hyperproperties":[28],"expressed":[29],"over":[30],"more":[31,98,143],"than":[32],"one":[33,134],"model":[34,40,53,87,110,138],"execution.":[35],"aims":[37],"to":[38,89,140,165],"find":[39,96],"inputs":[41],"that":[42,45,81,135],"expose":[43],"``bugs'',":[44],"is,":[46],"property":[47],"violations.":[48],"However,":[49],"performing":[50],"thousands":[51],"invocations":[54,88,139],"during":[55],"costly":[58],"both":[59],"in":[60,125],"terms":[61],"time":[63],"and":[64,94,163],"money":[65],"(for":[66],"metered":[67],"APIs,":[68],"such":[69],"as":[70,156],"OpenAI's).":[71],"We":[72],"present":[73],"LaZ":[74,103,149],"(pronounced":[75],"``lazy''),":[76],"extension":[78],"automatically":[82,104],"minimizes":[83],"number":[85,153],"boost":[90],"test":[92,101,117],"throughput":[93],"thereby":[95],"bugs":[97,155],"efficiently.":[99],"During":[100],"execution,":[102],"identifies":[105],"redundant":[106],"invocations---invocations":[107],"where":[108],"output":[111],"does":[112,159],"not":[113],"affect":[114],"final":[116],"outcome---and":[118],"skips":[119],"them,":[120],"much":[121],"like":[122],"lazy":[123],"evaluation":[124],"certain":[126],"programming":[127],"languages.":[128],"This":[129],"optimization":[130],"enables":[131],"second":[133],"dynamically":[136],"reorders":[137],"skip":[141],"expensive":[144],"ones.":[145],"As":[146],"result,":[148],"finds":[150],"same":[152],"Nomos,":[157],"so":[160],"median":[161],"33%":[162],"up":[164],"60%":[166],"faster.":[167]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}