{"id":"https://openalex.org/W7224847207","doi":"https://doi.org/10.48550/arxiv.2610.39872","title":"STORY2DIFF: A Dataset Linking Real-World User Stories to Code Changes","display_name":"STORY2DIFF: A Dataset Linking Real-World User Stories to Code Changes","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224847207","doi":"https://doi.org/10.48550/arxiv.2610.39872"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39872","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39872","pdf_url":"https://arxiv.org/pdf/2610.39872","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39872","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118497321","display_name":"Benedetta Donato","orcid":"https://orcid.org/0009-0001-1548-4429","observed_orcids":["https://orcid.org/0009-0001-1548-4429"]},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Donato, Benedetta","raw_affiliation_strings":["University of Milano-Bicocca , Milan , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca , Milan , Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009137359","display_name":"Daniele Franchini","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Franchini, Daniele","raw_affiliation_strings":["University of Milano-Bicocca , Milan , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca , Milan , Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160232629","display_name":"Alessandro Greco","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Greco, Alessandro","raw_affiliation_strings":["University of Milano-Bicocca , Milan , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca , Milan , Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015376844","display_name":"Oliviero Riganelli","orcid":"https://orcid.org/0000-0003-2120-2894","observed_orcids":["https://orcid.org/0000-0003-2120-2894"]},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Riganelli, Oliviero","raw_affiliation_strings":["University of Milano-Bicocca , Milan , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca , Milan , Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015645148","display_name":"Daniela Micucci","orcid":"https://orcid.org/0000-0003-1261-2234","observed_orcids":["https://orcid.org/0000-0003-1261-2234"]},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Micucci, Daniela","raw_affiliation_strings":["University of Milano-Bicocca , Milan , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca , Milan , Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036120394","display_name":"Leonardo Mariani","orcid":"https://orcid.org/0000-0001-9527-7042","observed_orcids":["https://orcid.org/0000-0001-9527-7042"]},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mariani, Leonardo","raw_affiliation_strings":["University of Milano-Bicocca , Milan , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca , Milan , Italy","institution_ids":["https://openalex.org/I66752286"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66752286"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10260","display_name":"Software Engineering Research","score":0.9848999977111816,"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":0.9848999977111816,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.014800000004470348,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/user-stories","display_name":"user stories","score":0.925000011920929},{"id":"https://openalex.org/keywords/requirements-traceability","display_name":"requirements traceability","score":0.5699999928474426},{"id":"https://openalex.org/keywords/requirements-engineering","display_name":"requirements engineering","score":0.4129999876022339},{"id":"https://openalex.org/keywords/pull-requests","display_name":"pull requests","score":0.6489999890327454},{"id":"https://openalex.org/keywords/code-changes","display_name":"code amendments","score":0.7289999723434448},{"id":"https://openalex.org/keywords/requirements-discovery","display_name":"requirements discovery","score":0.460999995470047},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.5730000138282776},{"id":"https://openalex.org/keywords/python","display_name":"Python","score":0.9549999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8111000061035156},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6952999830245972},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.6894999742507935},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.5720000267028809},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5177000164985657},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.49889999628067017},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4733999967575073},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42890000343322754},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4106999933719635},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40950000286102295},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.37599998712539673},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33899998664855957},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.325300008058548},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C133237599","wikidata":"https://www.wikidata.org/wiki/Q2295111","display_name":"Code smell","level":5,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39872","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39872","pdf_url":"https://arxiv.org/pdf/2610.39872","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2610.39872","doi":"https://doi.org/10.48550/arxiv.2610.39872","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39872","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.39872","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39872","pdf_url":"https://arxiv.org/pdf/2610.39872","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224847207.pdf","grobid_xml":"https://content.openalex.org/works/W7224847207.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7168162147","https://openalex.org/W3189840617","https://openalex.org/W2086106475","https://openalex.org/W7030074541","https://openalex.org/W4408670289","https://openalex.org/W1969308933","https://openalex.org/W4411271580","https://openalex.org/W7220663716","https://openalex.org/W7171969584","https://openalex.org/W4393557306"],"abstract_inverted_index":{"Research":[0],"on":[1],"requirements-to-code":[2],"tasks":[3],"needs":[4],"examples":[5],"in":[6,70],"which":[7],"a":[8,36,59,87,131,138],"genuine":[9],"requirement":[10,143],"is":[11,56],"paired":[12],"with":[13],"the":[14,71,74,80,91,96,101,107,121,125],"change":[15],"that":[16],"implemented":[17],"it.":[18],"Existing":[19],"user-story":[20],"collections,":[21],"however,":[22],"largely":[23],"contain":[24],"isolated":[25],"or":[26],"synthetic":[27],"text.":[28],"To":[29],"address":[30],"this":[31],"limitation,":[32],"we":[33,111],"present":[34],"STORY2DIFF,":[35],"dataset":[37,55,72,135],"of":[38,61,124,140],"7,785":[39],"English":[40],"user":[41],"stories":[42],"linked":[43],"to":[44,51,113,119],"merged":[45],"pull":[46,82,98],"requests":[47],"from":[48,58],"January":[49],"2017":[50],"July":[52],"2026.":[53],"The":[54,109,134],"mined":[57],"set":[60],"982":[62],"public":[63],"Java":[64],"and":[65,84,100,105,149],"Python":[66],"repositories.":[67],"Each":[68],"record":[69],"combines":[73],"original":[75],"issue,":[76],"extracted":[77],"Connextra":[78],"elements,":[79],"associated":[81,97],"request":[83],"commit":[85],"metadata,":[86],"file-level":[88],"diff":[89],"capturing":[90],"code":[92,151],"changes":[93],"introduced":[94],"by":[95],"request,":[99],"affected":[102],"files":[103],"before":[104],"after":[106],"change.":[108],"tool":[110],"built":[112],"mine":[114],"STORY2DIFF":[115],"can":[116,136],"be":[117],"used":[118],"repeat":[120],"automatic":[122],"extraction":[123],"records,":[126],"using":[127],"different":[128,132],"parameters":[129],"(e.g.,":[130],"timeframe).":[133],"support":[137],"variety":[139],"tasks,":[141],"including":[142],"discovery,":[144],"traceability,":[145],"change-":[146],"impact":[147],"estimation,":[148],"requirements-aware":[150],"generation.":[152],"Dataset:":[153],"https://github.com/riganelli/user-story-mining-pipeline/":[154],"releases/tag/V4.0.1.":[155],"Video:":[156],"https://youtu.be/qOhXUeyeiTQ.":[157]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-10-31T00:00:00"}
