{"id":"https://openalex.org/W7167631248","doi":"https://doi.org/10.1145/3786181.3788730","title":"An Automated Methodology for Generating Labeled Datasets of Semantic Errors in Code","display_name":"An Automated Methodology for Generating Labeled Datasets of Semantic Errors in Code","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7167631248","doi":"https://doi.org/10.1145/3786181.3788730"},"language":null,"primary_location":{"id":"doi:10.1145/3786181.3788730","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788730","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 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3786181.3788730","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140203281","display_name":"Mahmoud Kassem","orcid":"https://orcid.org/0009-0003-9449-213X"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Mahmoud Kassem","raw_affiliation_strings":["New York University Abu Dhabi, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0009-0003-9449-213X","affiliations":[{"raw_affiliation_string":"New York University Abu Dhabi, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I120250893"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011563016","display_name":"Francisco Ribeiro","orcid":"https://orcid.org/0000-0003-0427-4503"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Francisco Ribeiro","raw_affiliation_strings":["New York University Abu Dhabi, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0003-0427-4503","affiliations":[{"raw_affiliation_string":"New York University Abu Dhabi, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I120250893"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054083284","display_name":"Sarah Nadi","orcid":"https://orcid.org/0000-0002-0091-6030"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Sarah Nadi","raw_affiliation_strings":["New York University Abu Dhabi, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0002-0091-6030","affiliations":[{"raw_affiliation_string":"New York University Abu Dhabi, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I120250893"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I120250893"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.9491255,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.2630000114440918,"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":0.2630000114440918,"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/T10028","display_name":"Topic Modeling","score":0.11540000140666962,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.08869999647140503,"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":0.6506999731063843},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5210999846458435},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.38839998841285706},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3736000061035156},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.365200012922287},{"id":"https://openalex.org/keywords/semantic-data-model","display_name":"Semantic data model","score":0.3603000044822693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8403000235557556},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6506999731063843},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.527400016784668},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5210999846458435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4945000112056732},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.46779999136924744},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.365200012922287},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3409999907016754},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28060001134872437},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3786181.3788730","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788730","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 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3786181.3788730","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788730","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 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4616492986679077}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W90447038","https://openalex.org/W841012168","https://openalex.org/W1985236007","https://openalex.org/W1986453394","https://openalex.org/W2101161997","https://openalex.org/W2139885493","https://openalex.org/W2156723666","https://openalex.org/W2163922914","https://openalex.org/W2165533158","https://openalex.org/W2343875716","https://openalex.org/W2963935794","https://openalex.org/W2993007949","https://openalex.org/W3089815674","https://openalex.org/W3098605233","https://openalex.org/W3102072454","https://openalex.org/W3105943882","https://openalex.org/W3106124812","https://openalex.org/W3160007051","https://openalex.org/W3161474773","https://openalex.org/W3164640227","https://openalex.org/W3177813494","https://openalex.org/W4213007905","https://openalex.org/W4221166942","https://openalex.org/W4249297534","https://openalex.org/W4287024925","https://openalex.org/W4288080276","https://openalex.org/W4312805641","https://openalex.org/W4362514336","https://openalex.org/W4365205411","https://openalex.org/W4384345652","https://openalex.org/W4388483179","https://openalex.org/W4388483352","https://openalex.org/W4389544160","https://openalex.org/W4392020025","https://openalex.org/W4392866983","https://openalex.org/W4393728160","https://openalex.org/W4400484970","https://openalex.org/W4400680602","https://openalex.org/W4400848635","https://openalex.org/W4402684113","https://openalex.org/W4405930819","https://openalex.org/W4407551092","https://openalex.org/W4409796230","https://openalex.org/W4411552824","https://openalex.org/W4412703963","https://openalex.org/W4416172932","https://openalex.org/W7133198585","https://openalex.org/W7133231870"],"related_works":[],"abstract_inverted_index":{"Code":[0],"generated":[1],"by":[2],"language":[3],"models":[4],"frequently":[5],"contains":[6],"subtle":[7],"semantic":[8,49,65,89],"errors":[9,25,50],"that":[10,29],"are":[11,30],"difficult":[12],"to":[13,32,60,92],"detect":[14],"with":[15,88],"conventional":[16],"static":[17],"analysis":[18],"and":[19,73],"machine":[20],"learning":[21],"classifiers.":[22],"Studying":[23],"these":[24],"requires":[26],"specialized":[27],"datasets":[28],"laborious":[31],"create":[33],"manually.":[34],"To":[35],"address":[36],"this,":[37],"we":[38],"present":[39,78],"an":[40,53],"automated":[41],"methodology":[42],"for":[43],"generating":[44],"a":[45,79,82],"labeled":[46,83],"dataset":[47,84],"of":[48,85],"based":[51],"on":[52],"established":[54],"taxonomy.":[55],"Our":[56],"approach":[57],"uses":[58],"GPT-4.1":[59],"systematically":[61],"introduce":[62],"single,":[63],"isolated":[64],"bugs":[66],"into":[67],"correct":[68],"code":[69,87],"from":[70],"the":[71],"HumanEval":[72],"BigCodeBench":[74],"benchmarks.":[75],"We":[76],"also":[77],"resulting":[80],"artifact:":[81],"Python":[86],"errors,":[90],"designed":[91],"facilitate":[93],"classification":[94],"research.":[95]},"counts_by_year":[],"updated_date":"2026-07-08T06:22:20.291053","created_date":"2026-07-08T00:00:00"}