{"id":"https://openalex.org/W4402442614","doi":"https://doi.org/10.1145/3650212.3680401","title":"Evaluating Deep Neural Networks in Deployment: A Comparative Study (Replicability Study)","display_name":"Evaluating Deep Neural Networks in Deployment: A Comparative Study (Replicability Study)","publication_year":2024,"publication_date":"2024-09-11","ids":{"openalex":"https://openalex.org/W4402442614","doi":"https://doi.org/10.1145/3650212.3680401"},"language":"en","primary_location":{"id":"doi:10.1145/3650212.3680401","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650212.3680401","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3650212.3680401","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018159625","display_name":"Eduard Pinconschi","orcid":"https://orcid.org/0000-0002-0729-4684"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eduard Pinconschi","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0002-0729-4684","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103969534","display_name":"Divya Gopinath","orcid":"https://orcid.org/0000-0002-1242-7701"},"institutions":[{"id":"https://openalex.org/I1280536761","display_name":"Ames Research Center","ror":"https://ror.org/02acart68","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280536761","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divya Gopinath","raw_affiliation_strings":["KBR Inc., Mountain View, USA / NASA Ames, Mountain View, USA"],"raw_orcid":"https://orcid.org/0000-0002-1242-7701","affiliations":[{"raw_affiliation_string":"KBR Inc., Mountain View, USA / NASA Ames, Mountain View, USA","institution_ids":["https://openalex.org/I1280536761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030785658","display_name":"Rui Abreu","orcid":"https://orcid.org/0000-0003-3734-3157"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Rui Abreu","raw_affiliation_strings":["INESC-ID, Porto, Portugal / University of Porto, Porto, Portugal"],"raw_orcid":"https://orcid.org/0000-0003-3734-3157","affiliations":[{"raw_affiliation_string":"INESC-ID, Porto, Portugal / University of Porto, Porto, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I182534213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053134485","display_name":"Corina S. P\u0103s\u0103reanu","orcid":"https://orcid.org/0000-0002-5579-6961"},"institutions":[{"id":"https://openalex.org/I1280536761","display_name":"Ames Research Center","ror":"https://ror.org/02acart68","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280536761","https://openalex.org/I4210124779"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Corina S. P\u0103s\u0103reanu","raw_affiliation_strings":["Carnegie Mellon University, Mountain View, USA / NASA Ames, Mountain View, USA"],"raw_orcid":"https://orcid.org/0000-0002-5579-6961","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Mountain View, USA / NASA Ames, Mountain View, USA","institution_ids":["https://openalex.org/I1280536761","https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"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":"1300","last_page":"1311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9984999895095825,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9984999895095825,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.994700014591217,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9560999870300293,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.6955693364143372},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6669551134109497},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6239404678344727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5175827741622925},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4760406017303467},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4222193956375122},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34607821702957153},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.15848392248153687}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955693364143372},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6669551134109497},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6239404678344727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5175827741622925},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4760406017303467},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4222193956375122},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34607821702957153},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.15848392248153687}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3650212.3680401","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650212.3680401","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3650212.3680401","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650212.3680401","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1487130678","https://openalex.org/W2912500072","https://openalex.org/W2937523352","https://openalex.org/W3034355291","https://openalex.org/W3040318838","https://openalex.org/W3089756992","https://openalex.org/W3091441586","https://openalex.org/W3186232356","https://openalex.org/W3198845996","https://openalex.org/W4213308532","https://openalex.org/W4296899580","https://openalex.org/W4389215048","https://openalex.org/W4391558359"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4380075502","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128"],"abstract_inverted_index":{"As":[0],"deep":[1],"neural":[2,140],"networks":[3,23,141],"(DNNs)":[4],"are":[5,24],"increasingly":[6],"used":[7],"in":[8,65,127,142],"safety-critical":[9,143],"applications,":[10],"there":[11],"is":[12,30,71,101,125],"a":[13,47],"growing":[14],"concern":[15],"for":[16,79,135],"their":[17,35,83,97],"reliability.":[18],"Even":[19],"highly":[20],"trained,":[21],"high-performant":[22],"not":[25],"100%":[26],"accurate.":[27],"However,":[28],"it":[29,70,100],"very":[31],"difficult":[32,89,102],"to":[33,59,73,90,103,111,131],"predict":[34],"behavior":[36],"during":[37],"deployment":[38],"without":[39],"ground":[40],"truth.":[41],"In":[42],"this":[43,146],"paper,":[44],"we":[45,148],"provide":[46],"comparative":[48],"and":[49,75,86,158],"replicability":[50],"study":[51],"on":[52,82,93,161],"recent":[53],"approaches":[54,81,157],"that":[55,69,122,153],"have":[56],"been":[57],"proposed":[58],"evaluate":[60],"the":[61,77,105,108,112,137,155],"reliability":[62,138],"of":[63,107,114,139],"DNNs":[64],"deployment.":[66],"We":[67],"find":[68],"hard":[72],"run":[74,91],"reproduce":[76],"results":[78,120],"these":[80],"replication":[84],"packages":[85],"even":[87],"more":[88,123],"them":[92],"artifacts":[94],"other":[95],"than":[96],"own.":[98],"Further,":[99],"compare":[104],"effectiveness":[106],"approaches,":[109],"due":[110],"lack":[113],"clearly":[115],"defined":[116],"evaluation":[117,151,160],"metrics.":[118,166],"Our":[119],"indicate":[121],"effort":[124],"needed":[126],"our":[128],"research":[129],"community":[130],"obtain":[132],"sound":[133],"techniques":[134],"evaluating":[136],"domains.":[144],"To":[145],"end,":[147],"contribute":[149],"an":[150],"framework":[152],"incorporates":[154],"considered":[156],"enables":[159],"common":[162,165],"benchmarks,":[163],"using":[164]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}