{"id":"https://openalex.org/W4405812309","doi":"https://doi.org/10.1109/ojcs.2024.3523183","title":"Statistical Validity of Neural-Net Benchmarks","display_name":"Statistical Validity of Neural-Net Benchmarks","publication_year":2024,"publication_date":"2024-12-26","ids":{"openalex":"https://openalex.org/W4405812309","doi":"https://doi.org/10.1109/ojcs.2024.3523183"},"language":"en","primary_location":{"id":"doi:10.1109/ojcs.2024.3523183","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3523183","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/ojcs.2024.3523183","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115661854","display_name":"Alain Hadges","orcid":null},"institutions":[{"id":"https://openalex.org/I153151563","display_name":"Harrisburg University of Science and Technology","ror":"https://ror.org/02g0s4z48","country_code":"US","type":"education","lineage":["https://openalex.org/I153151563"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alain Hadges","raw_affiliation_strings":["Harrisburg University of Science & Technology, Harrisburg, PA, USA","Doctoral Candidate, Harrisburg University of Science & Technology, Harrisburg, PA, USA"],"raw_orcid":"https://orcid.org/0009-0003-7996-6528","affiliations":[{"raw_affiliation_string":"Harrisburg University of Science & Technology, Harrisburg, PA, USA","institution_ids":["https://openalex.org/I153151563"]},{"raw_affiliation_string":"Doctoral Candidate, Harrisburg University of Science & Technology, Harrisburg, PA, USA","institution_ids":["https://openalex.org/I153151563"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111102931","display_name":"Srikar Bellur","orcid":null},"institutions":[{"id":"https://openalex.org/I153151563","display_name":"Harrisburg University of Science and Technology","ror":"https://ror.org/02g0s4z48","country_code":"US","type":"education","lineage":["https://openalex.org/I153151563"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srikar Bellur","raw_affiliation_strings":["Department of Data Analytics, Harrisburg University of Science & Technology, Harrisburg, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Analytics, Harrisburg University of Science & Technology, Harrisburg, PA, USA","institution_ids":["https://openalex.org/I153151563"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5115661854"],"corresponding_institution_ids":["https://openalex.org/I153151563"],"apc_list":{"value":1750,"currency":"USD","value_usd":1750},"apc_paid":{"value":1750,"currency":"USD","value_usd":1750},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21398393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"211","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7807999849319458,"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/T10320","display_name":"Neural Networks and Applications","score":0.7807999849319458,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.5332275032997131},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49333062767982483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3585754632949829},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34250712394714355}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5332275032997131},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49333062767982483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3585754632949829},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34250712394714355}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ojcs.2024.3523183","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3523183","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ea33a80f195c40cfa155b8e148d6ba9d","is_oa":true,"landing_page_url":"https://doaj.org/article/ea33a80f195c40cfa155b8e148d6ba9d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Open Journal of the Computer Society, Vol 6, Pp 211-222 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/ojcs.2024.3523183","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3523183","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2154185090","https://openalex.org/W2161498332","https://openalex.org/W2534788641","https://openalex.org/W2547503455","https://openalex.org/W2557007068","https://openalex.org/W2582743722","https://openalex.org/W2587914027","https://openalex.org/W2963240192","https://openalex.org/W2964137095","https://openalex.org/W3096609285","https://openalex.org/W3217628675","https://openalex.org/W6633851434","https://openalex.org/W6639809013","https://openalex.org/W6640665466","https://openalex.org/W6687483927","https://openalex.org/W6755199091","https://openalex.org/W6802383100","https://openalex.org/W6804881294"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Claims":[0],"of":[1,38,46,50,65,73,76,93,119,126,132,139,145],"better,":[2],"faster":[3],"or":[4,21],"more":[5],"efficient":[6],"neural-net":[7,83,112,141],"designs":[8],"often":[9],"hinge":[10],"on":[11,35,135],"low":[12],"single":[13],"digit":[14],"percentage":[15],"improvements":[16],"(or":[17],"less)":[18],"in":[19],"accuracy":[20],"speed":[22],"compared":[23],"to":[24],"others.":[25],"Current":[26],"benchmark":[27,78,84,137],"differences":[28],"used":[29],"for":[30,106],"comparison":[31,98],"have":[32],"been":[33],"based":[34],"a":[36,140,143],"number":[37],"different":[39],"metrics":[40,60,114,138],"such":[41],"as":[42,142],"recall,":[43],"the":[44,48,127,130,136],"best":[45],"five-runs,":[47],"median":[49],"five":[51],"runs,":[52],"Top-1,":[53],"Top-5,":[54],"BLEU,":[55],"ROC,":[56],"RMS,":[57],"etc.":[58],"These":[59],"implicitly":[61],"assert":[62],"comparable":[63],"distributions":[64,86],"metrics.":[66],"Conspicuous":[67],"by":[68],"their":[69],"absence":[70],"are":[71,90],"measures":[72],"statistical":[74],"validity":[75],"these":[77],"comparisons.":[79],"This":[80],"study":[81],"examined":[82],"metric":[85],"and":[87,104,108,129],"determined":[88],"there":[89],"researcher":[91,117],"degrees":[92,118],"freedom":[94],"that":[95,115],"may":[96],"affect":[97],"validity.":[99],"An":[100],"essay":[101,122],"is":[102],"developed":[103],"proposed":[105],"benchmarking":[107],"comparing":[109],"reasonably":[110],"expected":[111],"performance":[113],"minimizes":[116],"freedom.":[120],"The":[121],"includes":[123],"an":[124],"estimate":[125],"effects":[128],"interactions":[131],"hyper-parameter":[133],"settings":[134],"measure":[144],"its":[146],"optimization":[147],"complexity.":[148]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}