{"id":"https://openalex.org/W7125409982","doi":"https://doi.org/10.5281/zenodo.18335922","title":"Replication package of the paper \"Machine Learning in the Wild: Early Evidence of Non-Compliant ML-Automation in Open-Source Software\"","display_name":"Replication package of the paper \"Machine Learning in the Wild: Early Evidence of Non-Compliant ML-Automation in Open-Source Software\"","publication_year":2026,"publication_date":"2026-01-22","ids":{"openalex":"https://openalex.org/W7125409982","doi":"https://doi.org/10.5281/zenodo.18335922"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.18335922","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18335922","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.18335922","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Arshid, Zohaib","orcid":"https://orcid.org/0009-0007-4910-1864"},"institutions":[{"id":"https://openalex.org/I16337185","display_name":"University of Sannio","ror":"https://ror.org/04vc81p87","country_code":"IT","type":"education","lineage":["https://openalex.org/I16337185"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Arshid, Zohaib","raw_affiliation_strings":["University of Sannio"],"raw_orcid":"https://orcid.org/0009-0007-4910-1864","affiliations":[{"raw_affiliation_string":"University of Sannio","institution_ids":["https://openalex.org/I16337185"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bifolco, Daniele","orcid":"https://orcid.org/0009-0009-4151-3551"},"institutions":[{"id":"https://openalex.org/I16337185","display_name":"University of Sannio","ror":"https://ror.org/04vc81p87","country_code":"IT","type":"education","lineage":["https://openalex.org/I16337185"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Bifolco, Daniele","raw_affiliation_strings":["University of Sannio"],"raw_orcid":"https://orcid.org/0009-0009-4151-3551","affiliations":[{"raw_affiliation_string":"University of Sannio","institution_ids":["https://openalex.org/I16337185"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zampetti, Fiorella","orcid":"https://orcid.org/0000-0001-7098-8964"},"institutions":[{"id":"https://openalex.org/I16337185","display_name":"University of Sannio","ror":"https://ror.org/04vc81p87","country_code":"IT","type":"education","lineage":["https://openalex.org/I16337185"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Zampetti, Fiorella","raw_affiliation_strings":["University of Sannio"],"raw_orcid":"https://orcid.org/0000-0001-7098-8964","affiliations":[{"raw_affiliation_string":"University of Sannio","institution_ids":["https://openalex.org/I16337185"]}]},{"author_position":"last","author":{"id":null,"display_name":"Di Penta, Massimiliano","orcid":"https://orcid.org/0000-0002-0340-9747"},"institutions":[{"id":"https://openalex.org/I16337185","display_name":"University of Sannio","ror":"https://ror.org/04vc81p87","country_code":"IT","type":"education","lineage":["https://openalex.org/I16337185"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Di Penta, Massimiliano","raw_affiliation_strings":["University of Sannio"],"raw_orcid":"https://orcid.org/0000-0002-0340-9747","affiliations":[{"raw_affiliation_string":"University of Sannio","institution_ids":["https://openalex.org/I16337185"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16337185"],"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":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/commit","display_name":"Commit","score":0.6021000146865845},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.5612999796867371},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5281999707221985},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4122999906539917},{"id":"https://openalex.org/keywords/data-file","display_name":"Data file","score":0.4106999933719635},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.40610000491142273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.815500020980835},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.6021000146865845},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.5612999796867371},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5281999707221985},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4546999931335449},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42989999055862427},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.4106999933719635},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38499999046325684},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34459999203681946},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C95637964","wikidata":"https://www.wikidata.org/wiki/Q82753","display_name":"Computer file","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.18335922","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18335922","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.18335922","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18335922","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Replication":[0],"Package":[1],"This":[2,96,132,234,383,596,669],"replication":[3],"package":[4,282],"contains":[5,98,134,385],"the":[6,14,22,35,57,63,68,82,93,105,114,120,135,149,160,192,202,209,219,229,237,240,243,249,253,259,280,286,293,326,339,373,386,400,408,419,425,438,447,453,460,467,494,500,506,523,532,552,572,585,588,599,622,626,645,656,672,679,698,706,734,749,772,778,796],"necessary":[7],"data":[8,51,774,779],"and":[9,66,70,86,126,248,276,302,315,330,359,368,379,591,683,705,753,768],"Python":[10,274,281,309,320,715],"script":[11,310,321],"for":[12,263,285,615,728],"reproducing":[13],"results":[15],"of":[16,26,34,59,72,102,104,119,124,129,137,159,167,171,175,180,185,191,239,344,365,389,407,418,446,452,459,465,474,493,517,541,558,560,565,632,647,655,658],"our":[17,269,604],"paper:":[18],"\"Machine":[19],"Learning":[20],"in":[21,29,43,92,201,399,499,571,603,625,639,665,700,777],"Wild:":[23],"Early":[24],"Evidence":[25],"Non-Compliant":[27],"ML-Automation":[28],"Open-Source":[30],"Software\".":[31],"The":[32,77,196,205,214,224],"goal":[33],"study":[36,605,627],"is":[37,79,221,231,236,509,703],"to":[38,56,207,267,300,350,377,511,531,606,628,756,782],"analyze":[39],"automated":[40,616],"decision-making":[41,401],"processes":[42],"open-source,":[44],"high-risk":[45],"ML":[46,568],"projects.":[47,74],"It":[48,257],"involves":[49],"gathering":[50],"from":[52,338,348],"GitHub,":[53],"comparing":[54],"it":[55,702,755],"dependents":[58,103,328,798],"huggingface/transformers,":[60],"manually":[61],"reviewing":[62],"project's":[64],"workflow,":[65],"clustering":[67,363],"post-processing":[69,375],"outputs":[71,364],"various":[73],"Project":[75],"Structure":[76],"project":[78,94,113,154,397,409,426,454,461,533],"organized":[80],"into":[81],"following":[83],"main":[84,439,589],"directories":[85],"files:":[87],"data/:":[88],"Contains":[89,273,335,362,575,580],"datasets":[90],"used":[91,200,266,398,498,510,570,602,624,704],"dependents_transformers.csv:":[95],"file":[97,115,133,235,299,384,752],"a":[99,345,581,630,652,691,723],"pre-sorted":[100,797],"list":[101,388],"huggingface/transformer":[106,254],"library":[107,255],"on":[108,211,428,535,718],"GitHub.":[109,212],"For":[110,152,693],"each":[111,153,352,687,694],"client":[112,250],"reports:":[116],"(i)":[117],"name":[118,417,445,451,458],"project,":[121,501],"(ii)":[122],"number":[123,128],"stars,":[125],"(iii)":[127],"forks.":[130,172],"github_domain_repos.csv:":[131],"set":[136,769],"projects":[138,246,251,265,367,609,664],"we":[139,155,696],"have":[140,714],"retrieved":[141],"by":[142,144,313,663,737,747],"searching":[143],"topics":[145],"(application":[146],"areas)":[147],"using":[148],"GitHub":[150,294,306,312,346,366,391,420,608,681,724,759],"API.":[151],"report:":[156],"repoName:":[157,415],"Name":[158,492],"repository":[161,210,220,317,347,553],"(owner":[162],"name/project":[163],"name).":[164],"stars:":[165],"Number":[166,170,174],"stars.":[168],"forks:":[169],"total_commits:":[173],"total":[176],"commits.":[177],"lastcommitmonth:":[178],"Month":[179],"last":[181,186,193],"commit.":[182,187,194],"lastcommitauthor:":[183],"Author":[184],"lastcommitmessage:":[188],"Commit":[189],"message":[190],"language:":[195],"primary":[197],"programming":[198],"language":[199,496],"repository.":[203,421,448],"github_link:":[204],"URL":[206],"access":[208,726],"domain:":[213,403],"specific":[215,225],"domain/topic":[216,314],"under":[217,227],"which":[218,228,701],"categorized.":[222],"sub-field:":[223,434],"sub-domain":[226],"domain":[230,785,793],"sub-categorized.":[232],"overlap_github_transformers.csv:":[233],"result":[238],"intersection":[241],"between":[242,587],"high":[244],"risk":[245],"(github_domain_repos.csv)":[247],"importing":[252],"(sorted_dependents_repo_huggingface_transformers.csv).":[256],"lists":[258,671],"initial":[260],"sample":[261],"accounting":[262],"173":[264],"answer":[268],"research":[270],"questions.":[271],"python/:":[272],"scripts":[275],"dependencies.":[277],"requirements.txt:":[278],"Lists":[279],"dependencies":[283,736],"required":[284,735,773],"project.":[287,573],".env:":[288],"Holds":[289],"environment":[290,298,746,751],"variables,":[291],"including":[292],"token.":[295,307],"example.env:":[296],"Example":[297],"copy":[301,762],"populate":[303],"with":[304,325,795],"your":[305,719,745,758],"domain_wise_repository_github.py:":[308],"queries":[311],"saves":[316],"metadata.":[318],"overlapGithubWithTransformersDep.py:":[319],"compares":[322],"domain-fetched":[323],"repositories":[324,682,699],"HuggingFace":[327],"CSV":[329],"produces":[331],"matched":[332],"output.":[333,360,525],"results/:":[334],"output":[336,508,649],"files":[337,775],"analysis.":[340,402],"github_systems_domain_wise_workflow.pdf:":[341],"Extended":[342],"workflow":[343],"input":[349],"output:":[351],"step":[353],"includes":[354],"input,":[355],"pre-processing,":[356],"decision,":[357],"post-processing,":[358],"automated_decision_types.pdf:":[361],"their":[369,592],"explanations.":[370],"postprocessing_rulebase_cluster.pdf:":[371],"Describes":[372],"rule-based":[374,479],"applied":[376,521],"clusters":[378],"selection":[380],"logic.":[381,480],"final_decision_making_repos.csv:":[382],"final":[387,513],"selected":[390],"repositories.":[392],"Each":[393],"row":[394],"represents":[395],"one":[396],"Main":[404],"application":[405],"area":[406,436],"(such":[410],"as":[411,690],"healthcare":[412],"or":[413,432,443,478,486,519,545,556,567,617,641,660],"finance).":[414],"Short":[416],"dependent:":[422],"Shows":[423,482],"whether":[424,483,551],"depends":[427],"other":[429],"tools,":[430],"models,":[431],"systems.":[433],"Specific":[435],"within":[437],"domain.":[440,455],"repository_name:":[441],"Full":[442],"official":[444],"domain_name:":[449],"standardized":[450,457],"subdomainname:":[456],"sub-domain.":[462],"decision_type:":[463],"Type":[464,516],"decision":[466,633,659],"system":[468],"performs":[469],"TraditionalMLModel/":[470],"Logical:":[471],"Indicates":[472,550],"use":[473],"traditional":[475],"machine":[476,612,674],"learning":[477,485,613,675],"Transformer/DeepLearningModel:":[481],"deep":[484],"transformer":[487],"models":[488,562,569,614,676],"are":[489],"used.":[490],"LLM_Used:":[491],"large":[495],"model":[497,524,688],"if":[502],"any.":[503],"modeloutputusage:":[504],"How":[505,781],"model\u2019s":[507],"make":[512],"decisions.":[514],"post-processing_type:":[515],"rules":[518],"logic":[520],"after":[522],"cluster":[526],":":[527,539,549,563],"Cluster":[528],"group":[529],"assigned":[530],"based":[534],"its":[536],"functionality.":[537],"automation_level":[538],"Level":[540],"automation":[542],"(manual,":[543],"semi-automatic,":[544],"fully":[546],"automatic).":[547],"termofuse_restricted(yes/no)":[548],"has":[554],"usage":[555,708],"violation":[557],"term":[559],"use.":[561],"List":[564],"AI":[566],"appendix/:":[574],"additional":[576],"analysis":[577],"documents.":[578],"github_projects_domain_sub-domains_analysis.pdf:":[579],"table":[582,597,670],"that":[583,610,643],"illustrates":[584],"relationship":[586],"domains":[590],"corresponding":[593,707],"sub-domains.":[594],"output_categories.pdf:":[595],"summarizes":[598],"output-based":[600],"categorization":[601],"classify":[607],"employ":[611],"semi-automated":[618],"decision-making.":[619],"Category":[620],"Name:":[621],"label":[623],"identify":[629],"class":[631],"outputs;":[634],"Keywords:":[635],"representative":[636],"terms":[637],"observed":[638],"documentation":[640],"code":[642],"signal":[644],"presence":[646],"this":[648,666],"type;":[650],"Description:":[651],"concise":[653],"explanation":[654],"kind":[657],"artifact":[661],"generated":[662],"category.":[667],"unique_models_github_systems_analysis.pdf:":[668],"unique":[673],"identified":[677],"across":[678],"analyzed":[680],"reports":[684],"how":[685],"often":[686],"appears":[689],"dependency.":[692],"model,":[695],"show":[697],"count.":[709],"Setup":[710],"Instructions":[711],"Ensure":[712,771],"you":[713],"3.8+":[716],"installed":[717],"Windows":[720],"machine.":[721],"Obtain":[722],"personal":[725],"token":[727],"higher":[729],"API":[730],"rate":[731],"limits.":[732],"Install":[733],"running:":[738],"pip":[739],"install":[740],"-r":[741],"python/requirements.txt":[742],"Set":[743],"up":[744],"copying":[748],"example":[750],"editing":[754],"include":[757],"token:cd":[760],"python":[761,788,789],"example.env":[763],".env":[764,767],"#":[765],"Edit":[766],"GITHUB_TOKEN=ghp_...":[770],"exist":[776],"folder.":[780],"Run":[783],"Fetch":[784],"repositories:":[786],"cd":[787],"domain_wise_repository_github.py":[790],"Compare":[791],"fetched":[792],"repos":[794],"CSV:python":[799],"compare_sorted_dependents_repo_huggingface_with_git_domain_wise_data.py":[800]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-01-23T00:00:00"}