{"id":"https://openalex.org/W2403186811","doi":"https://doi.org/10.1145/2901739.2901753","title":"Adressing problems with external validity of repository mining studies through a smart data platform","display_name":"Adressing problems with external validity of repository mining studies through a smart data platform","publication_year":2016,"publication_date":"2016-05-14","ids":{"openalex":"https://openalex.org/W2403186811","doi":"https://doi.org/10.1145/2901739.2901753","mag":"2403186811"},"language":"en","primary_location":{"id":"doi:10.1145/2901739.2901753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2901739.2901753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Mining Software Repositories","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068855431","display_name":"Fabian Trautsch","orcid":"https://orcid.org/0000-0002-8374-9142"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Fabian Trautsch","raw_affiliation_strings":["Georg-August-Universit\u00e4t G\u00f6ttingen, Germany"],"affiliations":[{"raw_affiliation_string":"Georg-August-Universit\u00e4t G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027032646","display_name":"Steffen Herbold","orcid":"https://orcid.org/0000-0001-9765-2803"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Herbold","raw_affiliation_strings":["Georg-August-Universit\u00e4t G\u00f6ttingen, Germany"],"affiliations":[{"raw_affiliation_string":"Georg-August-Universit\u00e4t G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040234160","display_name":"Philip Makedonski","orcid":"https://orcid.org/0000-0001-7752-0029"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philip Makedonski","raw_affiliation_strings":["Georg-August-Universit\u00e4t G\u00f6ttingen, Germany"],"affiliations":[{"raw_affiliation_string":"Georg-August-Universit\u00e4t G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078674128","display_name":"Jens Grabowski","orcid":"https://orcid.org/0000-0003-2994-3531"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Grabowski","raw_affiliation_strings":["Georg-August-Universit\u00e4t G\u00f6ttingen, Germany"],"affiliations":[{"raw_affiliation_string":"Georg-August-Universit\u00e4t G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068855431"],"corresponding_institution_ids":["https://openalex.org/I74656192"],"apc_list":null,"apc_paid":null,"fwci":20.5677,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.9926426,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9929999709129333,"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"}},{"id":"https://openalex.org/T11675","display_name":"Open Source Software Innovations","score":0.9799000024795532,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/comparability","display_name":"Comparability","score":0.8402602672576904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.757337749004364},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.7388676404953003},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6979689002037048},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6020722985267639},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5563162565231323},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5269601941108704},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5261706113815308},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5065969228744507},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4470592737197876},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32768237590789795},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3241347074508667}],"concepts":[{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.8402602672576904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757337749004364},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.7388676404953003},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6979689002037048},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6020722985267639},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5563162565231323},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5269601941108704},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5261706113815308},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5065969228744507},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4470592737197876},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32768237590789795},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3241347074508667},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2901739.2901753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2901739.2901753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Mining Software Repositories","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.550000011920929,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W168970045","https://openalex.org/W821933395","https://openalex.org/W1564257470","https://openalex.org/W1568352442","https://openalex.org/W1976200507","https://openalex.org/W1989479444","https://openalex.org/W1994493193","https://openalex.org/W2002476888","https://openalex.org/W2005519590","https://openalex.org/W2017439596","https://openalex.org/W2018871545","https://openalex.org/W2022897498","https://openalex.org/W2040977941","https://openalex.org/W2049828091","https://openalex.org/W2067148378","https://openalex.org/W2067623084","https://openalex.org/W2072632642","https://openalex.org/W2073429012","https://openalex.org/W2097883090","https://openalex.org/W2099395913","https://openalex.org/W2122414758","https://openalex.org/W2125889680","https://openalex.org/W2131975293","https://openalex.org/W2145021485","https://openalex.org/W2151511199","https://openalex.org/W2151666086","https://openalex.org/W2180620742","https://openalex.org/W2189465200","https://openalex.org/W2213051614","https://openalex.org/W2247907802","https://openalex.org/W2295279484","https://openalex.org/W2318063279","https://openalex.org/W2321915840","https://openalex.org/W2612101971","https://openalex.org/W4229585260","https://openalex.org/W4240298746","https://openalex.org/W4245682088","https://openalex.org/W4285719527","https://openalex.org/W4289783255","https://openalex.org/W6687322159","https://openalex.org/W6700160807","https://openalex.org/W6700469755"],"related_works":["https://openalex.org/W2365594754","https://openalex.org/W4287902769","https://openalex.org/W2575292835","https://openalex.org/W3001140700","https://openalex.org/W3021704418","https://openalex.org/W2995453361","https://openalex.org/W4390295458","https://openalex.org/W1990407237","https://openalex.org/W2092282998","https://openalex.org/W2053982300"],"abstract_inverted_index":{"Research":[0],"in":[1,45,52],"software":[2],"repository":[3],"mining":[4],"has":[5],"grown":[6],"considerably":[7],"the":[8,13,26,34,50,56,67,77,82,91,95,98,132,163,168],"last":[9],"decade.":[10],"Due":[11],"to":[12,33,117],"data-driven":[14],"nature":[15],"of":[16,19,37,42,76,97,165],"this":[17,110,153],"venue":[18],"investigation,":[20],"we":[21,112,141,155],"identified":[22],"several":[23,145],"problems":[24,54,119],"within":[25],"current":[27],"state-of-the-art":[28],"that":[29,124,135],"pose":[30],"a":[31,74,114,121],"threat":[32],"external":[35],"validity":[36],"results.":[38],"The":[39],"heavy":[40],"re-use":[41],"data":[43,57,65,126,143],"sets":[44],"many":[46,63],"studies":[47,64,92],"may":[48],"invalidate":[49],"results":[51,78],"case":[53],"with":[55],"itself":[58],"are":[59,69],"identified.":[60],"Moreover,":[61],"for":[62],"and/or":[66],"implementations":[68],"not":[70],"available,":[71,94],"which":[72],"hinders":[73],"replication":[75,104],"and,":[79],"thereby,":[80],"decreases":[81],"comparability":[83],"between":[84],"studies.":[85],"Even":[86],"if":[87],"all":[88],"information":[89],"about":[90],"is":[93],"diversity":[96],"used":[99],"tooling":[100],"can":[101],"make":[102],"their":[103],"even":[105],"then":[106],"very":[107],"hard.":[108],"Within":[109,152],"paper,":[111],"discuss":[113,159],"potential":[115],"solution":[116],"these":[118],"through":[120],"cloud-based":[122],"platform":[123],"integrates":[125],"collection":[127],"and":[128,147,158,167],"analytics.":[129],"We":[130],"created":[131,148],"prototype":[133],"SmartSHARK":[134,157,166],"implements":[136],"our":[137,160],"approach.":[138],"Using":[139],"SmartSHARK,":[140],"collected":[142],"from":[144],"projects":[146],"different":[149],"analytic":[150],"examples.":[151],"article,":[154],"present":[156],"experiences":[161],"regarding":[162],"use":[164],"mentioned":[169],"problems.":[170]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}