{"id":"https://openalex.org/W7123342804","doi":"https://doi.org/10.1109/access.2026.3652670","title":"A Large-Scale Investigation Into the Loss of Pull Request Data on GitHub","display_name":"A Large-Scale Investigation Into the Loss of Pull Request Data on GitHub","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123342804","doi":"https://doi.org/10.1109/access.2026.3652670"},"language":null,"primary_location":{"id":"doi:10.1109/access.2026.3652670","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3652670","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3652670","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122873381","display_name":"Bowen Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Bowen Tang","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Ritsumeikan University, Ibaraki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Ritsumeikan University, Ibaraki, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102721255","display_name":"Katsuhisa Maruyama","orcid":"https://orcid.org/0000-0002-8437-7360"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuhisa Maruyama","raw_affiliation_strings":["Department of Information Science and Engineering, Ritsumeikan University, Ibaraki, Japan"],"raw_orcid":"https://orcid.org/0000-0002-8437-7360","affiliations":[{"raw_affiliation_string":"Department of Information Science and Engineering, Ritsumeikan University, Ibaraki, Japan","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0405697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"6927","last_page":"6943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.2547999918460846,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.2547999918460846,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.24060000479221344,"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/T10260","display_name":"Software Engineering Research","score":0.20569999516010284,"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/commit","display_name":"Commit","score":0.8147000074386597},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.762499988079071},{"id":"https://openalex.org/keywords/data-source","display_name":"Data source","score":0.694100022315979},{"id":"https://openalex.org/keywords/data-loss","display_name":"Data loss","score":0.5496000051498413},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.4645000100135803},{"id":"https://openalex.org/keywords/information-loss","display_name":"Information loss","score":0.45509999990463257},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44850000739097595},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4341000020503998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8245999813079834},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.8147000074386597},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.762499988079071},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.694100022315979},{"id":"https://openalex.org/C193519340","wikidata":"https://www.wikidata.org/wiki/Q891179","display_name":"Data loss","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.4645000100135803},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44850000739097595},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.43369999527931213},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.41429999470710754},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C2988343187","wikidata":"https://www.wikidata.org/wiki/Q1130645","display_name":"Open source software","level":3,"score":0.3580000102519989},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3458000123500824},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.31119999289512634},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.2736000120639801},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2026.3652670","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3652670","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3652670","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3652670","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1819759706","https://openalex.org/W1914969610","https://openalex.org/W1984080818","https://openalex.org/W1995969252","https://openalex.org/W2110498832","https://openalex.org/W2110499955","https://openalex.org/W2116228345","https://openalex.org/W2124100711","https://openalex.org/W2125854594","https://openalex.org/W2136421959","https://openalex.org/W2139092060","https://openalex.org/W2152010691","https://openalex.org/W2164519300","https://openalex.org/W2809214960","https://openalex.org/W2953630964","https://openalex.org/W2960130540","https://openalex.org/W2963173301","https://openalex.org/W2999118008","https://openalex.org/W3040728396","https://openalex.org/W3124560715","https://openalex.org/W3133564273","https://openalex.org/W3140103367","https://openalex.org/W4244051999","https://openalex.org/W4251460506","https://openalex.org/W4312864407","https://openalex.org/W4313229660","https://openalex.org/W4384026759","https://openalex.org/W4387814042","https://openalex.org/W4409796619","https://openalex.org/W4413754726"],"related_works":[],"abstract_inverted_index":{"Analyzing":[0],"pull":[1],"requests":[2],"(PRs)":[3],"on":[4,32],"GitHub":[5,37,90],"provides":[6],"valuable":[7],"insights":[8],"that":[9,60,123,159,191],"can":[10,63],"improve":[11],"software":[12],"development":[13],"and":[14,27,70,92,109,143,215],"maintenance.":[15],"Therefore,":[16],"researchers":[17,208],"must":[18],"collect":[19],"PRs":[20,43,87,108,116,127,158,163,182,190,214],"for":[21,42],"empirical":[22],"studies":[23,57],"when":[24],"testing":[25],"hypotheses":[26],"creating":[28],"practical":[29],"tools":[30],"based":[31],"these":[33,73],"insights.":[34],"Unfortunately,":[35],"using":[36],"as":[38],"a":[39,196],"data":[40,48,61,105,130,211],"source":[41,169,173],"carries":[44],"the":[45,68,97,113,126,138,188],"risk":[46],"of":[47,72,104,115,125,140],"loss,":[49],"owing":[50],"to":[51,157,167,187,202,219],"its":[52],"flexible":[53],"resource":[54],"management.":[55],"Existing":[56],"have":[58,168],"indicated":[59],"losses":[62,74],"occur":[64],"in":[65,112,180,184,195,213],"PRs;":[66],"however,":[67],"types":[69,103],"impacts":[71],"remain":[75],"unclear.":[76],"This":[77],"study":[78],"shares":[79],"findings":[80,206],"from":[81,88,153],"our":[82],"investigation,":[83],"which":[84],"analyzed":[85],"84,828":[86],"30":[89],"repositories":[91],"2,345,724":[93],"actions":[94],"recorded":[95],"within":[96],"PRs.":[98],"It":[99],"clarifies":[100],"how":[101],"different":[102],"loss":[106,134,139,151,175,212],"affect":[107],"highlights":[110],"variations":[111],"percentage":[114],"affected":[117],"by":[118],"loss.":[119,131,204],"The":[120,172],"results":[121],"showed":[122],"54.79%":[124],"experienced":[128],"some":[129],"Source":[132],"code":[133,170,174],"was":[135,145,177],"common,":[136],"whereas":[137],"user":[141,149],"information":[142,150],"commits":[144],"less":[146],"frequent.":[147],"Most":[148],"resulted":[152],"missing":[154],"committers.":[155],"Compared":[156],"were":[160,164,199],"rejected,":[161],"merged":[162],"more":[165,200],"likely":[166],"losses.":[171],"rate":[176],"much":[178],"lower":[179],"testing-related":[181],"than":[183],"those":[185],"unrelated":[186],"testing.":[189],"lacked":[192],"files":[193],"written":[194],"programming":[197],"language":[198],"prone":[201],"commit":[203],"These":[205],"help":[207],"better":[209],"understand":[210],"develop":[216],"effective":[217],"strategies":[218],"prevent":[220],"it.":[221]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-14T00:00:00"}
