{"id":"https://openalex.org/W7160083841","doi":"https://doi.org/10.1007/s10515-026-00623-y","title":"Beyond syntax: enhancing automated documentation with data differences","display_name":"Beyond syntax: enhancing automated documentation with data differences","publication_year":2026,"publication_date":"2026-05-04","ids":{"openalex":"https://openalex.org/W7160083841","doi":"https://doi.org/10.1007/s10515-026-00623-y"},"language":"en","primary_location":{"id":"doi:10.1007/s10515-026-00623-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10515-026-00623-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10515-026-00623-y.pdf","source":{"id":"https://openalex.org/S4210177399","display_name":"Automated Software Engineering","issn_l":"0928-8910","issn":["0928-8910","1573-7535"],"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":"Automated Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10515-026-00623-y.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122278531","display_name":"Giacomo Fantino","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128445","display_name":"Torino e-district","ror":"https://ror.org/03cxxc369","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210128445"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Giacomo Fantino","raw_affiliation_strings":["Department of Control and Computer Engineering, Torino, Italy"],"raw_orcid":"https://orcid.org/0009-0009-5808-604X","affiliations":[{"raw_affiliation_string":"Department of Control and Computer Engineering, Torino, Italy","institution_ids":["https://openalex.org/I4210128445"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047965231","display_name":"Antonio Vetr\u00f2","orcid":"https://orcid.org/0000-0003-2027-3308"},"institutions":[{"id":"https://openalex.org/I4210128445","display_name":"Torino e-district","ror":"https://ror.org/03cxxc369","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210128445"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Antonio Vetro\u2019","raw_affiliation_strings":["Department of Control and Computer Engineering, Torino, Italy"],"raw_orcid":"https://orcid.org/0000-0003-2027-3308","affiliations":[{"raw_affiliation_string":"Department of Control and Computer Engineering, Torino, Italy","institution_ids":["https://openalex.org/I4210128445"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015536188","display_name":"Marco Torchiano","orcid":"https://orcid.org/0000-0001-5328-368X"},"institutions":[{"id":"https://openalex.org/I4210128445","display_name":"Torino e-district","ror":"https://ror.org/03cxxc369","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210128445"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Marco Torchiano","raw_affiliation_strings":["Department of Control and Computer Engineering, Torino, Italy"],"raw_orcid":"https://orcid.org/0000-0001-5328-368X","affiliations":[{"raw_affiliation_string":"Department of Control and Computer Engineering, Torino, Italy","institution_ids":["https://openalex.org/I4210128445"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135117412","display_name":"Federica Cappelluti","orcid":"https://orcid.org/0000-0003-4485-9055"},"institutions":[{"id":"https://openalex.org/I2799848540","display_name":"Center for Open Science","ror":"https://ror.org/05d5mza29","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2799848540"]},{"id":"https://openalex.org/I4210100607","display_name":"Institute of Electronics, Computer and Telecommunication Engineering","ror":"https://ror.org/00n4jbh84","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210100607","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210128445","display_name":"Torino e-district","ror":"https://ror.org/03cxxc369","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210128445"]}],"countries":["IT","US"],"is_corresponding":true,"raw_author_name":"Federica Cappelluti","raw_affiliation_strings":["Center for Open Science Studies, Torino, Italy","Department of Electronics and Telecommunications, Torino, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4485-9055","affiliations":[{"raw_affiliation_string":"Center for Open Science Studies, Torino, Italy","institution_ids":["https://openalex.org/I4210128445","https://openalex.org/I2799848540"]},{"raw_affiliation_string":"Department of Electronics and Telecommunications, Torino, Italy","institution_ids":["https://openalex.org/I4210100607"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015536188","https://openalex.org/A5047965231","https://openalex.org/A5122278531","https://openalex.org/A5135117412"],"corresponding_institution_ids":["https://openalex.org/I2799848540","https://openalex.org/I4210100607","https://openalex.org/I4210128445"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66538663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"3","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":0.9817000031471252,"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":0.9817000031471252,"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":0.003700000001117587,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.003599999938160181,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.5927000045776367},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5758000016212463},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.48260000348091125},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4602000117301941},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.45170000195503235},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.3991999924182892},{"id":"https://openalex.org/keywords/code-review","display_name":"Code review","score":0.38989999890327454},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3643999993801117},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3547999858856201}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8288000226020813},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.5927000045776367},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5758000016212463},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.503000020980835},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.48260000348091125},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.45419999957084656},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.3991999924182892},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.38989999890327454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3741999864578247},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3643999993801117},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3547999858856201},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.35339999198913574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34619998931884766},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33469998836517334},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3165999948978424},{"id":"https://openalex.org/C81587897","wikidata":"https://www.wikidata.org/wiki/Q181702","display_name":"Software documentation","level":5,"score":0.3156000077724457},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.31299999356269836},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C120894424","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory data analysis","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28769999742507935},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C116253237","wikidata":"https://www.wikidata.org/wiki/Q1437424","display_name":"Formal specification","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.27300000190734863},{"id":"https://openalex.org/C121957198","wikidata":"https://www.wikidata.org/wiki/Q14365593","display_name":"KPI-driven code analysis","level":5,"score":0.2703000009059906},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2694999873638153},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C2779791154","wikidata":"https://www.wikidata.org/wiki/Q258040","display_name":"Model transformation","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C10272871","wikidata":"https://www.wikidata.org/wiki/Q929972","display_name":"Software inspection","level":5,"score":0.2624000012874603},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10515-026-00623-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10515-026-00623-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10515-026-00623-y.pdf","source":{"id":"https://openalex.org/S4210177399","display_name":"Automated Software Engineering","issn_l":"0928-8910","issn":["0928-8910","1573-7535"],"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":"Automated Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10515-026-00623-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10515-026-00623-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10515-026-00623-y.pdf","source":{"id":"https://openalex.org/S4210177399","display_name":"Automated Software Engineering","issn_l":"0928-8910","issn":["0928-8910","1573-7535"],"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":"Automated Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313985","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160083841.pdf","grobid_xml":"https://content.openalex.org/works/W7160083841.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2061504941","https://openalex.org/W2302501749","https://openalex.org/W2809161078","https://openalex.org/W3016234956","https://openalex.org/W3098605233","https://openalex.org/W3128627341","https://openalex.org/W3166880922","https://openalex.org/W3195727321","https://openalex.org/W4210294742","https://openalex.org/W4249853476","https://openalex.org/W4284704125","https://openalex.org/W4287262177","https://openalex.org/W4288374490","https://openalex.org/W4312661333","https://openalex.org/W4318159335","https://openalex.org/W4367059011","https://openalex.org/W4388483373","https://openalex.org/W4391558490","https://openalex.org/W4400484905","https://openalex.org/W4400770977","https://openalex.org/W4402302241","https://openalex.org/W4403536355","https://openalex.org/W4404570261","https://openalex.org/W4405570253","https://openalex.org/W4409495048","https://openalex.org/W4409884391","https://openalex.org/W4410357414","https://openalex.org/W4411469899","https://openalex.org/W4411491073","https://openalex.org/W4413006388"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Modern":[1],"software":[2,21,60,361],"development":[3,22,362],"automation":[4],"is":[5,35,70,328],"mostly":[6],"based":[7],"on":[8,44,68,101,179,293],"AI,":[9],"covering":[10],"every":[11],"aspect":[12],"of":[13,50,66,127,142,175,206,246,254,312],"code":[14,27,39,67,112,348],"production":[15],"and":[16,26,31,47,103,132,155,217,226,310,333,346,363],"maintenance,":[17],"throughout":[18],"the":[19,64,98,173,204,262,308,325],"entire":[20],"lifecycle,":[23],"from":[24,130],"requirements":[25],"writing":[28],"to":[29,77,114,138,171,214,302],"testing":[30],"maintenance.":[32],"Code":[33],"commenting":[34],"no":[36,199],"exception.":[37],"Automated":[38],"comment":[40,180,219,237,322],"generation":[41],"methods":[42],"rely":[43],"static":[45],"syntactic":[46],"lexical":[48],"features":[49],"source":[51],"code.":[52,121],"However,":[53,230],"these":[54,153],"approaches":[55],"frequently":[56],"underperform":[57],"in":[58,196,236,239,273,320,358],"data-centric":[59,360],"applications,":[61],"where":[62,198],"understanding":[63],"effect":[65,100],"data":[69,90,94,119,144,201,285],"essential.":[71],"We":[72,122,146],"explore":[73],"an":[74],"execution-aware":[75],"extension":[76],"automatic":[78,225],"documentation":[79],"generation.":[80,181,323],"In":[81],"this":[82,176,188,258],"exploratory":[83],"work,":[84],"we":[85,231],"aim":[86],"at":[87],"capturing":[88,152],"post-execution":[89,339],"transformations":[91,286],"(i.e.,":[92],"semantic":[93],"differences)":[95],"that":[96,185,261,338],"reveal":[97],"code\u2019s":[99],"data,":[102],"use":[104],"it":[105,336],"as":[106,221,316],"a":[107,124,134,148,159,294,317,352],"complementary":[108,318],"signal":[109,319],"alongside":[110],"existing":[111],"representations":[113],"automate":[115],"explanatory":[116],"comments":[117,256,266],"for":[118,151,248,355],"wrangling":[120],"build":[123],"curated":[125],"dataset":[126,331],"Python":[128],"notebooks":[129],"Kaggle":[131],"apply":[133],"lightweight":[135],"execution":[136],"tracer":[137],"extract":[139],"structured":[140],"descriptions":[141],"runtime":[143],"transformations.":[145],"define":[147],"formal":[149],"grammar":[150],"effects":[154],"integrate":[156],"them":[157],"into":[158],"multimodal":[160],"encoder-decoder":[161],"model":[162],"using":[163,313],"co-attention":[164],"mechanisms.":[165],"Multiple":[166],"training":[167],"strategies":[168],"are":[169,290],"explored":[170],"assess":[172],"impact":[174],"new":[177],"modality":[178,189,263,334],"Our":[182,305],"evaluation":[183,228],"reveals":[184],"models":[186,357],"incorporating":[187],"performed":[190],"competitively":[191],"with":[192],"code-only":[193],"baselines.":[194],"Notably,":[195],"cases":[197],"observable":[200],"transformation":[202],"occurred,":[203],"presence":[205],"symbolic":[207],"$$\\langle":[208],"\\mathsf":[209],"{no\\_diff}":[210],"\\rangle$$":[211],"signals":[212],"led":[213],"improved":[215],"robustness":[216],"higher":[218],"quality,":[220],"measured":[222],"by":[223,267,330],"both":[224],"human":[227],"metrics.":[229],"did":[232],"not":[233,278],"observe":[234],"improvements":[235],"quality":[238],"semantically":[240],"rich":[241],"scenarios,":[242],"suggesting":[243,300],"possible":[244],"paths":[245],"improvement":[247],"future":[249],"research":[250],"direction.":[251],"Qualitative":[252],"analysis":[253],"generated":[255],"supports":[257],"pattern,":[259],"indicating":[260],"helps":[264],"stabilize":[265],"reducing":[268],"unnecessary":[269],"or":[270],"speculative":[271],"details":[272],"neutral":[274],"cases,":[275],"but":[276],"does":[277],"provide":[279],"yet":[280],"consistent":[281],"guidance":[282],"when":[283],"meaningful":[284],"occur.":[287],"These":[288],"trends":[289],"less":[291],"pronounced":[292],"larger,":[295],"noisier":[296],"extended":[297],"test":[298],"set,":[299],"sensitivity":[301],"comment\u2013code":[303],"alignment.":[304],"study":[306],"demonstrates":[307,337],"feasibility":[309],"potential":[311],"execution-derived":[314],"feedback":[315],"automated":[321],"While":[324],"current":[326],"approach":[327],"limited":[329],"size":[332],"noise,":[335],"state":[340],"changes":[341],"can":[342],"guide":[343],"more":[344],"context-aware":[345],"stable":[347],"summarization.":[349],"This":[350],"suggests":[351],"promising":[353],"direction":[354],"execution-sensitive":[356],"assisting":[359],"its":[364],"documentation.":[365]},"counts_by_year":[],"updated_date":"2026-06-20T20:08:15.867695","created_date":"2026-05-05T00:00:00"}
