{"id":"https://openalex.org/W7107877078","doi":"https://doi.org/10.5281/zenodo.17733825","title":"Replication Package for \"Cataloguing Hugging Face Models to Software Engineering Activities: Automation and Findings\"","display_name":"Replication Package for \"Cataloguing Hugging Face Models to Software Engineering Activities: Automation and Findings\"","publication_year":2025,"publication_date":"2025-11-27","ids":{"openalex":"https://openalex.org/W7107877078","doi":"https://doi.org/10.5281/zenodo.17733825"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17733825","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17733825","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.17733825","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gonz\u00e1lez \u00c1lvarez, Alexandra","orcid":"https://orcid.org/0009-0003-7634-0343"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Gonz\u00e1lez \u00c1lvarez, Alexandra","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya"],"raw_orcid":"https://orcid.org/0009-0003-7634-0343","affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Franch, Xavier","orcid":"https://orcid.org/0000-0001-9733-8830"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Franch, Xavier","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9733-8830","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lo, David","orcid":"https://orcid.org/0000-0002-4367-7201"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lo, David","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4367-7201","affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Mart\u00ednez-Fern\u00e1ndez, Silverio","orcid":"https://orcid.org/0000-0001-9928-133X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mart\u00ednez-Fern\u00e1ndez, Silverio","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9928-133X","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6771000027656555},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.6657999753952026},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.6251000165939331},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6168000102043152},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5943999886512756},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4943999946117401},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.49079999327659607},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.44600000977516174},{"id":"https://openalex.org/keywords/file-format","display_name":"File format","score":0.3725999891757965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623999714851379},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6771000027656555},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.6657999753952026},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.6251000165939331},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6168000102043152},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5943999886512756},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5453000068664551},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3617999851703644},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3562000095844269},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35589998960494995},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C13926793","wikidata":"https://www.wikidata.org/wiki/Q3507155","display_name":"Group method of data handling","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C3020440742","wikidata":"https://www.wikidata.org/wiki/Q1176855","display_name":"Software package","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C2778864079","wikidata":"https://www.wikidata.org/wiki/Q173285","display_name":"Digital data","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C52913732","wikidata":"https://www.wikidata.org/wiki/Q857102","display_name":"Software design","level":4,"score":0.2705000042915344},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2563999891281128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17733825","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17733825","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.17733825","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17733825","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Overview":[0],"This":[1,138,660],"replication":[2],"package":[3,166],"supports":[4],"the":[5,21,34,53,61,79,87,97,100,163,173,180,192,196,210,276,279,300,304,311,321,352,378,403,441,566,651],"paper":[6],"\"Cataloguing":[7],"Hugging":[8,26,238,322,379,571],"Face":[9,27,323,380,572],"Models":[10,31],"to":[11,24,42,45,107,320,382,648],"Software":[12,46,518,521,524,529],"Engineering":[13,47,516],"Activities:":[14],"Automation":[15],"and":[16,50,94,96,119,130,135,156,179,202,208,266,309,340,355,387,452,461,528,545,589,613,656],"Findings\".":[17],"The":[18,165,329,361,554],"goal":[19],"of":[20,36,55,57,63,83,99,114,144,278,405],"study":[22,69],"is":[23,364,646,661],"analyze":[25],"(HF)":[28],"Pre":[29],"Trained":[30],"(PTMs)":[32],"for":[33,161,188,205,274,287,482,542,617],"purpose":[35],"their":[37,43,611],"automatic":[38],"classification":[39],"with":[40,127,158,455,477,549,570],"respect":[41],"application":[44],"(SE)":[48],"activities":[49,354,509],"tasks":[51,77,356],"from":[52,78,86,237,264,402],"point":[54],"view":[56],"software":[58],"engineers":[59],"in":[60,195,358,394,411,431,440,446,467,489,552,561,663],"context":[62],"model":[64,91,480],"selection.":[65],"Our":[66],"repository":[67,151,308],"mining":[68],"followed":[70,222],"a":[71,111,131,141,153,483,535,631],"five-phase":[72],"pipeline:":[73],"(i)":[74],"identification":[75],"SE":[76,115,146,353,422,459,508,568,596],"literature;":[80],"(ii)":[81],"collection":[82],"PTM":[84,462],"data":[85,136,235,245,427,454,550],"HF":[88,587,615],"API,":[89],"including":[90,172,191],"card":[92],"descriptions":[93],"metadata,":[95,588],"abstracts":[98,404],"associated":[101,406],"arXiv":[102,407],"papers;":[103],"(iii)":[104],"text":[105],"processing":[106],"ensure":[108],"consistency;":[109],"(iv)":[110],"two-phase":[112],"validation":[113,177],"relevance,":[116],"involving":[117],"humans":[118],"LLM":[120,585,637,652],"assistance,":[121],"supported":[122],"by":[123,223,293],"five":[124],"pilot":[125,288,543],"studies":[126],"human":[128,176],"annotators":[129,557],"generalization":[132],"test;":[133],"(v)":[134],"analysis.":[137],"process":[139],"yielded":[140],"validated":[142],"catalogue":[143],"2,205":[145],"PTMs.":[147],"Repository":[148],"Structure":[149],"It":[150],"contains":[152,168],"README":[154],"file":[155],"scripts":[157,201],"detailed":[159],"instructions":[160],"replicating":[162],"study.":[164,360],"also":[167],"all":[169,384,626],"relevant":[170],"data,":[171],"raw":[174],"dataset,":[175],"annotations,":[178],"final":[181,546,632],"curated":[182],"dataset.":[183],"/analysis":[184],"\u251c\u2500\u2500":[185,212,230,240,250,259,268],"[Jupyter":[186],"notebooks":[187,204,541],"analyzing":[189],"PTMs,":[190],"figures":[193],"presented":[194],"paper]":[197],"/code":[198],"\u2514\u2500\u2500":[199,215,233,243,253,262,271,282,284],"[Pythons":[200],"Jupyter":[203],"collecting,":[206],"preparing":[207],"filtering":[209,485],"data]":[211],"llm/":[213],"\u2502":[214,232,242,252,261],"[Pilot":[216],"tests":[217,544],"using":[218,510],"Gemini":[219,332,511],"2.0":[220,333,512],"FLash":[221],"full-scale":[224],"evaluation":[225],"on":[226,247,425],"entire":[227],"dataset]":[228],"/data":[229],"data_collection/":[231],"[Raw":[234],"collected":[236],"Face]":[239],"data_filtering/":[241],"[Filtered":[244],"based":[246,424],"selection":[248],"criteria]":[249],"data_search/":[251],"[Data":[254,263,272,285],"obtained":[255],"through":[256],"search":[257],"processes]":[258],"related_work":[260],"HFCommunity":[265],"PeaTMOSS]":[267],"subset_LLM_generalization/":[269],"|":[270],"subsets":[273,286],"testing":[275],"generalizability":[277],"LLM's":[280],"prompt]":[281],"subset_pilot/":[283],"experiments,":[289],"which":[290,335],"were":[291],"annotated":[292,644],"3":[294],"independent":[295],"researchers]":[296],"Setup":[297],"To":[298],"replicate":[299],"analysis":[301],"or":[302],"run":[303],"pipeline,":[305],"clone":[306],"this":[307,359],"install":[310,315],"required":[312],"dependencies:":[313],"pip":[314],"-r":[316],"requirements.txt":[317],"Note:":[318],"Access":[319],"API":[324,327,338,381],"requires":[325,336],"an":[326,337],"key.":[328],"pipeline":[330],"uses":[331],"Flash,":[334],"key":[339],"may":[341],"incur":[342],"costs.":[343],"Pipeline":[344],"Description":[345],"1)":[346],"Task":[347,414],"Identification":[348],"-":[349,375,396,416,436,448,473,491,563,582,602,623,640],"code/define_SE_tasks.ipynb":[350],"Defines":[351],"used":[357,647],"resulting":[362],"list":[363],"saved":[365,393,410,430,445,466,488,551,579,599,620],"as":[366,458,600,621],"code/se_tasks_lemmatized.csv":[367],"2)":[368],"Data":[369,373,578],"Collection":[370],"&":[371],"3)":[372],"Processing":[374],"code/get_mdls_tasks.py":[376],"Uses":[377],"retrieve":[383],"available":[385],"PTMs":[386,419,503,569,605],"extract":[388],"any":[389,421],"declared":[390],"tasks.":[391],"Results":[392,409,429,444,465,487,598,619],"data/data_collection/mdls_se_tasks.csv":[395],"code/get_mdls_tasks_abstract.py":[397],"Similarly":[398],"extracts":[399],"task":[400,423],"information":[401],"papers.":[408],"data/data_collection/mdls_se_tasks_abstract.csv":[412],"3.2)":[413],"Search":[415],"analysis/data_search.ipynb":[417],"Selects":[418],"mentioning":[420],"both":[426],"sources.":[428],"data/data_search/mdls_with_tasks.csv":[432],"3.3)":[433],"Outlier":[434],"Detection":[435,472],"code/filtering_LOG-DEB-COD.py":[437],"Detects":[438,475,604],"outliers":[439,451],"previous":[442],"step.":[443,486],"data/data_filtering/mdls_with_tasks-LOG-DEB-COD-filtered.csv":[447],"analysis/data_filtering.ipynb":[449],"Filters":[450],"enriches":[453],"metadata":[456,573],"such":[457],"activity":[460,533,590],"creation":[463],"date.":[464],"data/data_filtering/mdls_with_tasks-LOG-DEB-COD-filtered_activities.csv":[468],"3.4)":[469],"Unique":[470],"Card":[471],"code/filtering_duplicate_cards.py":[474],"entries":[476],"highly":[478],"similar":[479],"cards":[481],"second":[484],"data/data_filtering/mdls_with_tasks-LOG-DEB-COD-filtered_activities_no-duplicate-cards-99-trace.csv":[490],"analysis/data_filtering_duplicates.ipynb":[492],"Analyzes":[493],"filtered":[494],"data.":[495],"4)":[496],"LLM-Based":[497],"Validation":[498],"4.1)":[499],"Prompts":[500],"Refinement":[501],"Selected":[502],"are":[504],"classified":[505],"into":[506,592,630],"specific":[507],"Flash":[513],"LLM:":[514],"Requirements":[515],"(RE),":[517],"Design":[519],"(SD),":[520],"Implementation":[522],"(SI),":[523],"Quality":[525],"Assurance":[526],"(SQA),":[527],"Maintenance":[530],"(SM).":[531],"Each":[532],"has":[534],"dedicated":[536],"folder":[537],"inside":[538],"code/llm":[539],"containing":[540],"runs:":[547],"code/llm/{se_activity}/{se_activity}_gemini_pilot_all.ipynb,":[548],"{se_activity}_gemini_all.csv":[553],"agreement":[555],"between":[556],"can":[558],"be":[559],"found":[560],"code/llm/manual_agreement.ipynb":[562],"code/get_mdls_HF_attributes.ipynb":[564],"Enriches":[565],"LLM-confirmed":[567],"(tags,":[574],"downloads,":[575],"likes,":[576],"etc.).":[577],"under":[580],"code/llm/{se_activity}/{se_activity}_gemini_all_HFinsights.csv":[581],"code/merge_mapping_HF_attributes.ipynb":[583],"Combines":[584],"classifications,":[586],"mappings":[591],"CSV":[593,628],"files":[594,629],"per":[595],"activity.":[597],"code/llm/{se_activity}/{se_activity}_gemini_all_HFinsights_merged.csv":[601,622],"code/get_HF_attributes_renamed_mdls.ipynb":[603],"that":[606,650],"have":[607],"been":[608],"renamed,":[609],"updates":[610],"name":[612],"gets":[614],"attributes":[616],"them.":[618],"code/llm/combine_llm_results.ipynb":[624],"Merges":[625],"per-activity":[627],"consolidated":[633],"dataset:":[634],"data/data_filtering/mdls_with_tasks-LOG-DEB-COD-filtered_activities_no-duplicate-cards-99-trace_LLM.csv":[635],"4.2)":[636],"Generalization":[638],"Test":[639],"data/subset_LLM_generalization/generalization_subset%20-%20subset.csv":[641],"A":[642],"manually":[643],"subset":[645],"verify":[649],"prompt":[653],"generalizes":[654],"well":[655],"does":[657],"not":[658],"overfit.":[659],"analyzed":[662],"code/llm/manual_agreement_generalization.ipynb":[664]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-11-28T00:00:00"}