{"id":"https://openalex.org/W7125950054","doi":"https://doi.org/10.1109/ase63991.2025.00379","title":"Evaluating Program Coverage for Code-Model Training","display_name":"Evaluating Program Coverage for Code-Model Training","publication_year":2025,"publication_date":"2025-11-16","ids":{"openalex":"https://openalex.org/W7125950054","doi":"https://doi.org/10.1109/ase63991.2025.00379"},"language":null,"primary_location":{"id":"doi:10.1109/ase63991.2025.00379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase63991.2025.00379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051873291","display_name":"Narayanan Menon","orcid":"https://orcid.org/0000-0003-0901-8488"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Nandakishore Menon","raw_affiliation_strings":["IBM Research,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"IBM Research,Bangalore,India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010368277","display_name":"Diptikalyan Saha","orcid":"https://orcid.org/0000-0002-1583-5479"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Diptikalyan Saha","raw_affiliation_strings":["IBM Research,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"IBM Research,Bangalore,India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051873291"],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85784718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4078","last_page":"4081"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.5828999876976013,"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":0.5828999876976013,"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":0.21410000324249268,"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"}},{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.04270000010728836,"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/cobol","display_name":"COBOL","score":0.9819999933242798},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5809000134468079},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46790000796318054},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.4650000035762787},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.4602999985218048},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4410000145435333},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.40959998965263367}],"concepts":[{"id":"https://openalex.org/C128595289","wikidata":"https://www.wikidata.org/wiki/Q131140","display_name":"COBOL","level":2,"score":0.9819999933242798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8443999886512756},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6141999959945679},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5809000134468079},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4410000145435333},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.41620001196861267},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40959998965263367},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3889000117778778},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35589998960494995},{"id":"https://openalex.org/C2780589192","wikidata":"https://www.wikidata.org/wiki/Q7285140","display_name":"Raising (metalworking)","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.3116999864578247},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C2986991398","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntactic structure","level":3,"score":0.2619999945163727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ase63991.2025.00379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase63991.2025.00379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2291630781","https://openalex.org/W2295993424","https://openalex.org/W2904932877","https://openalex.org/W2949932035","https://openalex.org/W3189722042","https://openalex.org/W4411271944","https://openalex.org/W4412888189","https://openalex.org/W4414913062","https://openalex.org/W7125135101"],"related_works":[],"abstract_inverted_index":{"In":[0,75],"recent":[1],"years,":[2],"CodeLLMs":[3,38],"have":[4,69],"revolutionized":[5],"the":[6,49,84,91,100,108,118,135,138],"way":[7],"developers":[8],"interact":[9],"with":[10,131],"code.":[11],"One":[12],"notable":[13],"application":[14],"has":[15],"been":[16],"program":[17],"translation,":[18],"such":[19],"as":[20],"converting":[21],"COBOL":[22,61,88,132],"to":[23,27,124],"Java":[24],"or":[25],"C":[26],"Rust.":[28],"A":[29],"critical":[30],"challenge":[31],"in":[32],"this":[33,76],"domain":[34],"is":[35,54,96],"ensuring":[36],"that":[37,43],"are":[39,65],"trained":[40],"on":[41],"programs":[42],"cover":[44],"all":[45],"syntactic":[46,85,109,127],"features":[47],"of":[48,72,87,93,115,137],"target":[50],"language.":[51],"This":[52],"issue":[53],"especially":[55],"pronounced":[56],"for":[57,82],"legacy":[58],"languages":[59],"like":[60],"and":[62,68,105],"ABAP,":[63],"which":[64,103],"syntactically":[66],"rich":[67],"limited":[70],"availability":[71],"open-source":[73],"programs.":[74,89,116],"paper,":[77],"we":[78],"present":[79],"a":[80,97,113],"tool":[81,119],"evaluating":[83],"coverage":[86],"At":[90],"core":[92],"our":[94],"approach":[95],"representation":[98],"called":[99],"Coverage":[101],"Tree,":[102],"compactly":[104],"intuitively":[106],"captures":[107],"constructs":[110],"covered":[111],"by":[112],"set":[114],"Additionally,":[117],"can":[120],"generate":[121],"code":[122],"statements":[123],"address":[125],"uncovered":[126],"gaps.":[128],"Experimental":[129],"results":[130],"benchmarks":[133],"demonstrate":[134],"effectiveness":[136],"tool.":[139],"Screencast":[140],"URL:":[141],"https://youtu.be/lM0KHzcvllY.":[142]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-29T00:00:00"}
