{"id":"https://openalex.org/W2940740603","doi":"https://doi.org/10.1007/s10664-020-09825-8","title":"PHANTOM: Curating GitHub for engineered software projects using time-series clustering","display_name":"PHANTOM: Curating GitHub for engineered software projects using time-series clustering","publication_year":2020,"publication_date":"2020-05-27","ids":{"openalex":"https://openalex.org/W2940740603","doi":"https://doi.org/10.1007/s10664-020-09825-8","mag":"2940740603"},"language":"en","primary_location":{"id":"doi:10.1007/s10664-020-09825-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-020-09825-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-020-09825-8.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10664-020-09825-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Peter Pickerill","orcid":null},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Peter Pickerill","raw_affiliation_strings":["Department of Computer Science and Engineering, Chalmers University of Technology, Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chalmers University of Technology, Gothenburg, Sweden","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Heiko Joshua Jungen","orcid":null},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Heiko Joshua Jungen","raw_affiliation_strings":["Department of Computer Science and Engineering, Chalmers University of Technology, Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chalmers University of Technology, Gothenburg, Sweden","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Miros\u0142aw Ochodek","orcid":null},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Miros\u0142aw Ochodek","raw_affiliation_strings":["Poznan University of Technology, Poznan, Poland"],"affiliations":[{"raw_affiliation_string":"Poznan University of Technology, Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Micha\u0142 Ma\u0107kowiak","orcid":null},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Micha\u0142 Ma\u0107kowiak","raw_affiliation_strings":["Poznan University of Technology, Poznan, Poland"],"affiliations":[{"raw_affiliation_string":"Poznan University of Technology, Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miroslaw Staron","orcid":null},"institutions":[{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]},{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Miroslaw Staron","raw_affiliation_strings":["Chalmers University of Technology, University of Gothenburg, Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology, University of Gothenburg, Gothenburg, Sweden","institution_ids":["https://openalex.org/I66862912","https://openalex.org/I881427289"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66862912"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":2.132,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.87511454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"25","issue":"4","first_page":"2897","last_page":"2929"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.3343999981880188,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.3343999981880188,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10260","display_name":"Software Engineering Research","score":0.18690000474452972,"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"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.12610000371932983,"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/metadata","display_name":"Metadata","score":0.8116000294685364},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7821000218391418},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6875},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6736000180244446},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5824999809265137},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5486000180244446},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4837000072002411},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4749999940395355}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8116000294685364},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7821000218391418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401000261306763},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6875},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6736000180244446},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5824999809265137},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5666000247001648},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5486000180244446},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C104293457","wikidata":"https://www.wikidata.org/wiki/Q28324852","display_name":"Imaging phantom","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33000001311302185},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C2988343187","wikidata":"https://www.wikidata.org/wiki/Q1130645","display_name":"Open source software","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C101317890","wikidata":"https://www.wikidata.org/wiki/Q940053","display_name":"Software maintenance","level":4,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10664-020-09825-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-020-09825-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-020-09825-8.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1904.11164","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.11164","pdf_url":"https://arxiv.org/pdf/1904.11164","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/s10664-020-09825-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-020-09825-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-020-09825-8.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2940740603.pdf","grobid_xml":"https://content.openalex.org/works/W2940740603.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1914969610","https://openalex.org/W1970271205","https://openalex.org/W1972386298","https://openalex.org/W1987196563","https://openalex.org/W1989280111","https://openalex.org/W1999987361","https://openalex.org/W2009082127","https://openalex.org/W2021840107","https://openalex.org/W2040915209","https://openalex.org/W2047988765","https://openalex.org/W2054288159","https://openalex.org/W2057128378","https://openalex.org/W2060669876","https://openalex.org/W2081028405","https://openalex.org/W2099223743","https://openalex.org/W2142958724","https://openalex.org/W2143960295","https://openalex.org/W2147846500","https://openalex.org/W2166547175","https://openalex.org/W2476494490","https://openalex.org/W2525290333","https://openalex.org/W2559885217","https://openalex.org/W2579754794","https://openalex.org/W2597809331","https://openalex.org/W2601908482","https://openalex.org/W2602793737","https://openalex.org/W2605284977","https://openalex.org/W2605856244","https://openalex.org/W2611190712","https://openalex.org/W2725411909","https://openalex.org/W2729099293","https://openalex.org/W2732148014","https://openalex.org/W2732522303","https://openalex.org/W2768067395","https://openalex.org/W2891332953","https://openalex.org/W2953212509","https://openalex.org/W3151685851","https://openalex.org/W4232691406","https://openalex.org/W4236390018","https://openalex.org/W4239439500","https://openalex.org/W4251460506"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Context":[1],"Within":[2],"the":[3,25,34,82,115,120,135,139,158,165,185,200,204,238,244],"field":[4],"of":[5,36,58,67,71,167,193,198,203,250],"Mining":[6],"Software":[7],"Repositories,":[8],"there":[9],"are":[10],"numerous":[11],"methods":[12,28],"employed":[13],"to":[14,19,52,62,130,133,145,151,221,226,233,237],"filter":[15],"datasets":[16],"in":[17,74,171],"order":[18],"avoid":[20],"analysing":[21],"low-quality":[22],"projects.":[23,229],"Unfortunately,":[24],"existing":[26,37,239],"filtering":[27,68],"have":[29],"not":[30],"kept":[31],"up":[32,150],"with":[33,149],"growth":[35],"data":[38],"sources,":[39],"such":[40],"as":[41,108],"GitHub,":[42],"and":[43,49,142,154,163],"researchers":[44],"often":[45],"rely":[46],"on":[47,138,157],"quick":[48],"dirty":[50],"techniques":[51],"curate":[53],"datasets.":[54],"Objective":[55],"The":[56,88,196],"objective":[57],"this":[59],"study":[60,80,187],"is":[61,100,106,180,219],"develop":[63],"a":[64,75,103,109,124,175,190],"method":[65,201],"capable":[66],"large":[69],"quantities":[70],"software":[72],"projects":[73,148],"resource-efficient":[76],"way.":[77],"Method":[78],"This":[79],"follows":[81],"Design":[83],"Science":[84],"Research":[85],"(DSR)":[86],"methodology.":[87],"proposed":[89],"method,":[90],"PHANTOM,":[91],"extracts":[92],"five":[93],"measures":[94],"from":[95,123],"Git":[96],"logs.":[97],"Each":[98],"measure":[99],"transformed":[101],"into":[102],"time-series,":[104],"which":[105,179,188],"represented":[107],"feature":[110],"vector":[111],"for":[112],"clustering":[113],"using":[114,174],"k-means":[116],"algorithm.":[117],"Results":[118],"Using":[119],"ground":[121,136],"truth":[122,137],"previous":[125,186],"study,":[126],"PHANTOM":[127,161,230],"was":[128,143,207,231],"shown":[129,232],"be":[131,234],"able":[132,144],"rediscover":[134],"training":[140],"dataset,":[141],"identify":[146,227],"\u201cengineered\u201d":[147],"0.87":[152],"Precision":[153],"0.94":[155],"Recall":[156],"validation":[159],"dataset.":[160],"downloaded":[162],"processed":[164],"metadata":[166],"1,786,601":[168],"GitHub":[169],"repositories":[170,212],"21.5":[172],"days":[173],"single":[176],"personal":[177],"computer,":[178],"over":[181],"33%":[182],"faster":[183],"than":[184],"used":[189],"computer":[191],"cluster":[192],"200":[194],"nodes.":[195],"possibility":[197],"applying":[199],"outside":[202],"open-source":[205],"community":[206],"investigated":[208],"by":[209,214,247],"curating":[210],"100":[211],"owned":[213],"two":[215,248],"companies.":[216],"Conclusions":[217],"It":[218],"possible":[220],"use":[222],"an":[223],"unsupervised":[224],"approach":[225],"engineered":[228],"competitive":[235],"compared":[236],"supervised":[240],"approaches":[241],"while":[242],"reducing":[243],"hardware":[245],"requirements":[246],"orders":[249],"magnitude.":[251]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2019-05-03T00:00:00"}