{"id":"https://openalex.org/W7167672319","doi":"https://doi.org/10.1145/3786582.3786826","title":"From Execution to Embedding: Enriching Code Representations with Data Difference Signals for Comment Generation","display_name":"From Execution to Embedding: Enriching Code Representations with Data Difference Signals for Comment Generation","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7167672319","doi":"https://doi.org/10.1145/3786582.3786826"},"language":null,"primary_location":{"id":"doi:10.1145/3786582.3786826","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786582.3786826","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 48th International Conference on Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3786582.3786826","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122278531","display_name":"Giacomo Fantino","orcid":null},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giacomo Fantino","raw_affiliation_strings":["Politecnico di Torino, Torino, Italy"],"raw_orcid":"https://orcid.org/0009-0009-5808-604X","affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"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/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Antonio Vetr\u00f2","raw_affiliation_strings":["Politecnico di Torino, Torino, Italy"],"raw_orcid":"https://orcid.org/0000-0003-2027-3308","affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"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/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Torchiano","raw_affiliation_strings":["Politecnico di Torino, Torino, Italy"],"raw_orcid":"https://orcid.org/0000-0001-5328-368X","affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071785633","display_name":"Federica Cappelluti","orcid":"https://orcid.org/0000-0003-4485-9055"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Federica Cappelluti","raw_affiliation_strings":["Politecnico di Torino, Torino, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4485-9055","affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177477856"],"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":"136","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7468000054359436,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7468000054359436,"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"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.06239999830722809,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.05139999836683273,"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/python","display_name":"Python (programming language)","score":0.631600022315979},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5338000059127808},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.48249998688697815},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.47200000286102295},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4212999939918518},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41749998927116394},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4156999886035919},{"id":"https://openalex.org/keywords/abstract-syntax","display_name":"Abstract syntax","score":0.4097000062465668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8176000118255615},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.631600022315979},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5763999819755554},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5338000059127808},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.47200000286102295},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4212999939918518},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41749998927116394},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4104999899864197},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.4097000062465668},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3700000047683716},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3386000096797943},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3179999887943268},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.2802000045776367},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3786582.3786826","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786582.3786826","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 48th International Conference on Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3786582.3786826","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786582.3786826","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 48th International Conference on Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2809161078","https://openalex.org/W3098605233","https://openalex.org/W4210294742","https://openalex.org/W4284704125","https://openalex.org/W4318159335","https://openalex.org/W4367059011","https://openalex.org/W4388483373","https://openalex.org/W4394745253","https://openalex.org/W4400770977","https://openalex.org/W4402302241","https://openalex.org/W4403194077","https://openalex.org/W4409495048","https://openalex.org/W4409884391"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"automatic":[1,73],"comment":[2,116],"generation":[3],"tools":[4],"often":[5],"fail":[6],"to":[7,102,132],"capture":[8,25],"data-centric":[9],"workflow":[10],"intents,":[11],"because":[12],"syntax":[13],"alone":[14],"provides":[15],"weak":[16],"signals":[17],"of":[18,30,49,135],"how":[19],"code":[20,37],"transforms":[21],"data.":[22],"We":[23,42,95],"instead":[24],"semantic":[26],"data":[27,32,101],"differences\u2014symbolic":[28],"descriptions":[29],"post-execution":[31],"transformations\u2014and":[33],"integrate":[34],"them":[35],"with":[36],"through":[38],"a":[39,47,133],"dual-encoder":[40],"architecture.":[41],"evaluate":[43],"this":[44,109],"approach":[45],"on":[46,92,115],"dataset":[48],"executed":[50],"Python":[51],"notebooks":[52],"pairing":[53],"code,":[54],"effect":[55],"sequences,":[56],"and":[57,75,100,105,127],"human":[58,76],"comments.":[59],"When":[60,78],"no":[61],"transformation":[62],"is":[63,121],"detected,":[64],"the":[65,69,82],"full":[66],"pipeline":[67],"outperforms":[68],"baseline":[70,83],"across":[71],"both":[72],"metrics":[74],"evaluation.":[77],"transformations":[79],"are":[80],"present,":[81],"remains":[84],"competitive,":[85],"though":[86],"some":[87],"simplified":[88],"variants":[89],"surpass":[90],"it":[91],"specific":[93],"metrics.":[94],"make":[96],"available":[97],"all":[98],"software":[99],"encourage":[103],"replication":[104],"further":[106],"studies":[107],"in":[108],"area.":[110],"While":[111],"our":[112,118],"experiments":[113],"focus":[114],"generation,":[117],"core":[119],"contribution":[120],"broader:":[122],"we":[123],"introduce":[124],"execution-aware":[125],"embeddings":[126],"argue":[128],"for":[129],"their":[130],"applicability":[131],"variety":[134],"downstream":[136],"tasks.":[137]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-09T00:00:00"}