{"id":"https://openalex.org/W6930569758","doi":"https://doi.org/10.5281/zenodo.15275192","title":"CppSATD: A Reusable Self-Admitted Technical Debt Dataset in C++","display_name":"CppSATD: A Reusable Self-Admitted Technical Debt Dataset in C++","publication_year":2025,"publication_date":"2025-05-31","ids":{"openalex":"https://openalex.org/W6930569758","doi":"https://doi.org/10.5281/zenodo.15275192"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.15275192","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15275192","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.15275192","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Pham, Phuoc","orcid":"https://orcid.org/0009-0001-9770-6995"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Pham, Phuoc","raw_affiliation_strings":["University of Oulu"],"raw_orcid":"https://orcid.org/0009-0001-9770-6995","affiliations":[{"raw_affiliation_string":"University of Oulu","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sridharan, Murali","orcid":"https://orcid.org/0000-0002-5212-588X"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sridharan, Murali","raw_affiliation_strings":["University of Oulu"],"raw_orcid":"https://orcid.org/0000-0002-5212-588X","affiliations":[{"raw_affiliation_string":"University of Oulu","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Esposito, Matteo","orcid":"https://orcid.org/0000-0002-8451-3668"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Esposito, Matteo","raw_affiliation_strings":["University of Oulu"],"raw_orcid":"https://orcid.org/0000-0002-8451-3668","affiliations":[{"raw_affiliation_string":"University of Oulu","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lenarduzzi, Valentina","orcid":"https://orcid.org/0000-0003-0511-5133"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Lenarduzzi, Valentina","raw_affiliation_strings":["University of Oulu"],"raw_orcid":"https://orcid.org/0000-0003-0511-5133","affiliations":[{"raw_affiliation_string":"University of Oulu","institution_ids":["https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98381234"],"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":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/technical-debt","display_name":"Technical debt","score":0.7408999800682068},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.6173999905586243},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.5123999714851379},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.48510000109672546},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.4724000096321106},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4634000062942505},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.454800009727478},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4348999857902527}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523999810218811},{"id":"https://openalex.org/C159198006","wikidata":"https://www.wikidata.org/wiki/Q1532172","display_name":"Technical debt","level":4,"score":0.7408999800682068},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.6173999905586243},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.5123999714851379},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42669999599456787},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.3962000012397766},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3873000144958496},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3675999939441681},{"id":"https://openalex.org/C120527767","wikidata":"https://www.wikidata.org/wiki/Q3196867","display_name":"Debt","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.15275192","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15275192","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.15275192","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15275192","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":[{"id":"https://metadata.un.org/sdg/17","score":0.4387362003326416,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"CppSATD":[0,50,83],"is":[1,51,142,221],"the":[2,18,29,53,81,86,92,104,147,193,209,225,237,256],"first":[3],"dataset":[4,30,57,84,257],"of":[5,17,63,103,122,146,227],"Self-Admitted":[6],"Technical":[7],"Debt":[8,131,133,135,137,139],"(SATD)":[9],"comments":[10,111],"that":[11],"focuses":[12],"on":[13,173],"C++":[14,106,211],"projects,":[15],"one":[16,145],"most":[19],"widely-used":[20],"programming":[21],"languages.":[22],"In":[23],"addition":[24],"to":[25,118,156,162,187,189,207,223],"multi-class":[26],"SATD":[27,46,56,74,110,123,127,149],"annotations,":[28],"also":[31],"captures":[32],"source":[33,60],"code":[34,102],"context":[35],"around":[36],"each":[37],"comment,":[38],"offering":[39],"valuable":[40],"insight":[41],"into":[42],"where":[43],"and":[44,91,167,196,213],"how":[45],"occurs":[47],"in":[48,180,230],"practice.":[49],"currently":[52],"largest":[54],"multi-type":[55],"with":[58,96],"contextual":[59],"code,":[61],"consisting":[62],"over":[64],"531,000":[65],"annotated":[66,88],"comments,":[67],"including":[68],"more":[69],"than":[70],"13,000":[71],"manually":[72,87],"classified":[73],"instances.":[75],"Contents":[76],"File":[77],"Description":[78],"data_and_scripts.zip":[79,238],"Contains":[80],"full":[82],"(cppsatd.csv),":[85],"subset":[89],"(manual_annotations.csv),":[90],"Python":[93],"extraction":[94],"scripts":[95],"pattern":[97,197],"files":[98,229],"(cppsatd.data.extraction.zip).":[99],"repos.zip":[100,203],"Source":[101],"5":[105],"repositories":[107],"from":[108],"which":[109],"were":[112],"extracted.":[113],"Annotation_Reference_Document.pdf":[114],"Guideline":[115],"document":[116],"used":[117],"ensure":[119,224],"consistent":[120],"annotation":[121],"types":[124,150],"among":[125],"annotators.":[126],"Types":[128],"Covered":[129],"Design/Code":[130],"Requirement":[132],"Defect":[134],"Test":[136],"Documentation":[138],"Each":[140],"comment":[141,164],"labeled":[143],"as":[144,153],"above":[148],"or":[151,182,191,244,251],"marked":[152],"NON-SATD.":[154],"How":[155],"Use":[157,160,169,202],"Explore":[158],"Annotations:":[159],"cppsatd.csv":[161],"analyze":[163],"distributions,":[165],"frequencies,":[166],"types.":[168],"Manual":[170],"Labels:":[171],"Rely":[172],"manual_annotations.csv":[174],"for":[175],"high-quality":[176],"ground":[177],"truth":[178],"data":[179,194],"training":[181],"evaluation.":[183],"Reproduce":[184],"Extraction:":[185],"Refer":[186],"cppsatd.data.extraction.zip":[188],"understand":[190],"replicate":[192],"collection":[195],"matching":[198],"process.":[199],"Inspect":[200],"Repos:":[201],"if":[204],"you":[205],"want":[206],"see":[208],"actual":[210],"projects":[212],"their":[214],"corresponding":[215,241],"comments.":[216],"Checksums":[217],"A":[218],"SIGNATURES.MD":[219],"file":[220],"included":[222],"integrity":[226],"all":[228],"this":[231],"replication":[232],"package.":[233],"You":[234],"can":[235],"verify":[236],"using":[239],"its":[240],"MD5,":[242],"SHA1,":[243],"SHA256":[245],"digest.":[246],"Contact":[247],"For":[248],"questions,":[249],"suggestions,":[250],"collaboration":[252],"inquiries,":[253],"please":[254],"contact":[255],"authors.":[258]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
