{"id":"https://openalex.org/W4393505017","doi":"https://doi.org/10.5281/zenodo.2538876","title":"Dataset of A Large-scale Study about Quality and Reproducibility of Jupyter Notebooks / Understanding and Improving the Quality and Reproducibility of Jupyter Notebooks","display_name":"Dataset of A Large-scale Study about Quality and Reproducibility of Jupyter Notebooks / Understanding and Improving the Quality and Reproducibility of Jupyter Notebooks","publication_year":2019,"publication_date":"2019-03-13","ids":{"openalex":"https://openalex.org/W4393505017","doi":"https://doi.org/10.5281/zenodo.2538876"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.2538876","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.2538876","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.2538876","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108878533","display_name":"Jo\u00e3o Felipe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felipe, Jo\u00e3o","raw_affiliation_strings":["Pimentel"],"raw_orcid":"https://orcid.org/0000-0001-6680-7470","affiliations":[{"raw_affiliation_string":"Pimentel","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110803144","display_name":"L\u00e9onardo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":", Leonardo","raw_affiliation_strings":["Murta"],"raw_orcid":"https://orcid.org/0000-0002-5173-1247","affiliations":[{"raw_affiliation_string":"Murta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109186564","display_name":"Vanessa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":", Vanessa","raw_affiliation_strings":["Braganholo"],"raw_orcid":"https://orcid.org/0000-0002-1184-8192","affiliations":[{"raw_affiliation_string":"Braganholo","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113467926","display_name":"Juliana Juliana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":", Juliana","raw_affiliation_strings":["Freire"],"raw_orcid":"https://orcid.org/0000-0003-3915-7075","affiliations":[{"raw_affiliation_string":"Freire","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":{"id":"https://openalex.org/T13565","display_name":"Education and Learning Interventions","score":0.8325999975204468,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13565","display_name":"Education and Learning Interventions","score":0.8325999975204468,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/reproducibility","display_name":"Reproducibility","score":0.9324260354042053},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.567611038684845},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5391919612884521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.510246992111206},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.4100845456123352},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2308889627456665},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20818662643432617},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.144002765417099},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.11731460690498352},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09822255373001099},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05834582448005676}],"concepts":[{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.9324260354042053},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.567611038684845},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5391919612884521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.510246992111206},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.4100845456123352},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2308889627456665},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20818662643432617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.144002765417099},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.11731460690498352},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09822255373001099},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05834582448005676},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.2538876","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.2538876","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.2538876","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.2538876","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":["https://openalex.org/W2748952813","https://openalex.org/W2413717610","https://openalex.org/W1973270181","https://openalex.org/W2417696084","https://openalex.org/W2368782778","https://openalex.org/W2087830269","https://openalex.org/W3106281778","https://openalex.org/W2003643616","https://openalex.org/W638612878","https://openalex.org/W2361979572"],"abstract_inverted_index":{"The":[0,154,195,217,260,275,318],"self-documenting":[1],"aspects":[2],"and":[3,42,54,77,101,127,131,237,287,373,376,400],"the":[4,19,28,59,73,129,151,162,166,189,192,208,214,232,246,251,254,264,268,272,280,284,288,292,297,304,311,324,344,395],"ability":[5],"to":[6,35,49,242,342,363,365,370,389,407,412],"reproduce":[7,245],"results":[8,45],"have":[9],"been":[10,24],"touted":[11],"as":[12,221],"significant":[13],"benefits":[14],"of":[15,61,103,133,161,229,346],"Jupyter":[16,84,134,255],"Notebooks.":[17,85,135],"At":[18],"same":[20],"time,":[21],"there":[22],"has":[23],"growing":[25],"criticism":[26],"that":[27,43,184],"way":[29],"notebooks":[30,68,312,369,402],"are":[31,198,219,227],"being":[32],"used":[33,57,212],"leads":[34],"unexpected":[36],"behavior,":[37],"encourages":[38],"poor":[39],"coding":[40],"practices":[41,56],"their":[44],"can":[46],"be":[47],"hard":[48],"reproduce.":[50],"To":[51],"understand":[52],"good":[53],"bad":[55],"in":[58,200,213,231,283,313,323],"development":[60],"real":[62],"notebooks,":[63,236],"we":[64,75,168,211],"analyzed":[65],"1.4":[66],"million":[67],"from":[69,170,403],"GitHub.":[70],"Based":[71],"on":[72,109,240,253],"results,":[74],"proposed":[76],"evaluated":[78],"Julynter,":[79],"a":[80,158,201,410],"linting":[81],"tool":[82],"for":[83,348,358,394],"Papers:":[86],"PIMENTEL,":[87,117],"J.":[88,118],"F.;":[89,119],"MURTA,":[90,120],"L.;":[91,121],"BRAGANHOLO,":[92,122],"V.;":[93,123],"FREIRE,":[94,124],"J.;":[95,125],"A":[96],"large-scale":[97],"study":[98],"about":[99],"quality":[100],"reproducibility":[102,215],"jupyter":[104],"notebooks.":[105,171,290],"In:":[106],"International":[107],"Conference":[108],"Mining":[110],"Software":[111,137],"Repositories":[112],"(MSR),":[113],"2019,":[114],"Montreal,":[115],"Canada.":[116],"Understanding":[126],"Improving":[128],"Quality":[130],"Reproducibility":[132],"Empirical":[136],"Engineering,":[138],"2021":[139],"(in":[140],"press)":[141],"This":[142],"repository":[143,257,417],"contains":[144,157,187,207,263,278],"three":[145],"files:":[146],"db2020-09-22.dump.gz":[147,155,179],"sample.tar.gz":[148,261],"julynter_reproducility.tar.gz":[149,276],"<strong>Reproducing":[150,271],"Notebook":[152],"Study</strong>":[153],"file":[156,186,262,277],"PostgreSQL":[159],"dump":[160,388],"database,":[163],"with":[164,191,415],"all":[165,279],"data":[167,247,281,320,392],"extracted":[169,193],"For":[172,234],"loading":[173],"it,":[174],"run:":[175],"<pre><code":[176],"class=\"language-bash\">gunzip":[177],"-c":[178],"|":[180],"psql":[181],"jupyter</code></pre>":[182],"Note":[183],"this":[185,404],"only":[188],"database":[190,387],"data.":[194],"actual":[196],"repositories":[197,218,265],"available":[199],"google":[202],"drive":[203],"folder,":[204],"which":[205],"also":[206],"docker":[209],"images":[210],"study.":[216],"stored":[220,322],"<em>content/{hash_dir1}/{hash_dir2}.tar.bz2</em>,":[222],"where":[223],"<em>hash_dir1":[224],"</em>and":[225],"<em>hash_dir2</em>":[226],"columns":[228,362],"<em>repositories</em>":[230],"database.":[233],"scripts,":[235],"detailed":[238],"instructions":[239,252],"how":[241],"analyze":[243],"or":[244],"collection,":[248],"please":[249],"check":[250],"Archaeology":[256],"(tag":[258],"1.0.0)":[259],"obtained":[266],"during":[267],"manual":[269],"sampling.":[270],"Julynter":[273,285,384],"Experiment</strong>":[274],"collected":[282,319,393,416],"experiment":[286],"analysis":[289,293,401],"Reproducing":[291],"is":[294,321],"straightforward:":[295],"Uncompress":[296],"file:":[298],"$":[299,306],"tar":[300],"zxvf":[301],"julynter_reproducibility.tar.gz":[302],"Install":[303],"dependencies:":[305],"pip":[307],"install":[308],"julynter/requirements.txt":[309],"Run":[310],"order:":[314],"J1.Data.Collection.ipynb;":[315],"J2.Recommendations.ipynb;":[316],"J3.Usability.ipynb.":[317],"julynter/data":[325],"folder.":[326],"<strong>Changelog</strong>":[327],"2019/01/14":[328],"-":[329,332,336,339,352,355,379,382],"Version":[330,337,353,380],"1":[331],"Initial":[333],"version<br>":[334],"2019/01/22":[335],"2":[338],"Update":[340,356,386],"N8.Execution.ipynb":[341],"calculate":[343],"rate":[345],"failure":[347],"each":[349],"reason<br>":[350],"2019/03/13":[351],"3":[354],"package":[357,405],"camera":[359],"ready.":[360],"Add":[361,383],"db":[364],"detect":[366],"duplicates,":[367],"change":[368],"consider":[371],"them,":[372],"add":[374,409],"N1.Skip.Notebook.ipynb":[375],"N11.Repository.With.Notebook.Restriction.ipynb.<br>":[377],"2021/03/15":[378],"4":[381],"experiment;":[385],"include":[390],"new":[391],"second":[396],"paper;":[397],"remove":[398],"scripts":[399],"(moved":[406],"GitHub),":[408],"link":[411],"Google":[413],"Drive":[414],"files":[418]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
