{"id":"https://openalex.org/W4409311460","doi":"https://doi.org/10.1145/3720449","title":"API-Guided Dataset Synthesis to Finetune Large Code Models","display_name":"API-Guided Dataset Synthesis to Finetune Large Code Models","publication_year":2025,"publication_date":"2025-04-09","ids":{"openalex":"https://openalex.org/W4409311460","doi":"https://doi.org/10.1145/3720449"},"language":"en","primary_location":{"id":"doi:10.1145/3720449","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3720449","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3720449","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Programming Languages","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3720449","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101884078","display_name":"Zongjie Li","orcid":"https://orcid.org/0000-0002-9897-4086"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zongjie Li","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-9897-4086","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063510532","display_name":"Daoyuan Wu","orcid":"https://orcid.org/0000-0002-3752-0718"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Daoyuan Wu","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-3752-0718","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328264","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-0866-0308"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-0866-0308","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077610917","display_name":"Zhendong Su","orcid":"https://orcid.org/0000-0002-2970-1391"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Zhendong Su","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-2970-1391","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1214,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.9483781,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"9","issue":"OOPSLA1","first_page":"786","last_page":"815"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9998999834060669,"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/T10260","display_name":"Software Engineering Research","score":0.9940999746322632,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.6557443141937256},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5661668181419373},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4529005289077759},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34294235706329346},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.08306583762168884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6557443141937256},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5661668181419373},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4529005289077759},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34294235706329346},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.08306583762168884}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3720449","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3720449","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3720449","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Programming Languages","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-161160","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-161160","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":{"id":"doi:10.1145/3720449","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3720449","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3720449","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Programming Languages","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307117","display_name":"HSBC Bank USA","ror":"https://ror.org/00t2kp174"},{"id":"https://openalex.org/F4320323537","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409311460.pdf","grobid_xml":"https://content.openalex.org/works/W4409311460.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1964962870","https://openalex.org/W1971650562","https://openalex.org/W1977556410","https://openalex.org/W1987971958","https://openalex.org/W2029500775","https://openalex.org/W2085487226","https://openalex.org/W2097335450","https://openalex.org/W2148437670","https://openalex.org/W2149236697","https://openalex.org/W2157976942","https://openalex.org/W2187089797","https://openalex.org/W2240451833","https://openalex.org/W2535690855","https://openalex.org/W2560674852","https://openalex.org/W2561055248","https://openalex.org/W2768510408","https://openalex.org/W2769533150","https://openalex.org/W2949895386","https://openalex.org/W2995341674","https://openalex.org/W3091119136","https://openalex.org/W4226087539","https://openalex.org/W4238530241","https://openalex.org/W4251434917","https://openalex.org/W4292341621","https://openalex.org/W4292928781","https://openalex.org/W4307079201","https://openalex.org/W4353004773","https://openalex.org/W4385152093","https://openalex.org/W4390604635","https://openalex.org/W4391558518","https://openalex.org/W4400910426"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"code":[1,7,70,162],"models":[2,30,174],"(LCMs),":[3],"pre-trained":[4],"on":[5,176,183,194],"vast":[6],"corpora,":[8],"have":[9],"demonstrated":[10],"remarkable":[11],"performance":[12,37],"across":[13],"a":[14,24,47,77,121,152,190],"wide":[15],"array":[16],"of":[17,55,60,69,134,154,192,208,217,226],"code-related":[18],"tasks.":[19],"Supervised":[20],"fine-tuning":[21],"(SFT)":[22],"plays":[23],"vital":[25],"role":[26],"in":[27,38,76,97,128,220,239],"aligning":[28],"these":[29],"with":[31,138,173],"specific":[32],"requirements":[33],"and":[34,57,100,109,159,199,222,245,251],"enhancing":[35],"their":[36],"particular":[39],"domains.":[40],"However,":[41],"synthesizing":[42],"high-quality":[43,236],"SFT":[44,93,221],"datasets":[45,56,137,179,185],"poses":[46],"significant":[48],"challenge":[49],"due":[50],"to":[51,90,164,242],"the":[52,58,92,113,143,206,215,224],"uneven":[53],"quality":[54,219],"scarcity":[59],"domain-specific":[61,101,252],"datasets.":[62],"Inspired":[63],"by":[64,131,228],"APIs":[65],"as":[66,120,151],"high-level":[67,157],"abstractions":[68],"that":[71],"encapsulate":[72],"rich":[73],"semantic":[74],"information":[75],"concise":[78],"structure,":[79],"we":[80],"propose":[81],"DataScope":[82,103],",":[83],"an":[84,230],"API-guided":[85],"dataset":[86,126,149,218],"synthesis":[87,127,150],"framework":[88,233],"designed":[89],"enhance":[91],"process":[94,153],"for":[95,205,234,248],"LCMs":[96,227,247],"both":[98,249],"general":[99,129,250],"scenarios.":[102,253],"comprises":[104],"two":[105],"main":[106],"components:":[107],"Dslt":[108,116],"Dgen":[110,146],".":[111],"On":[112,142],"one":[114],"hand,":[115,145],"employs":[117],"API":[118,140],"coverage":[119],"core":[122],"metric,":[123],"enabling":[124],"efficient":[125],"scenarios":[130],"selecting":[132],"subsets":[133],"existing":[135],"(uneven-quality)":[136],"higher":[139],"coverage.":[141],"other":[144],"recasts":[147],"domain":[148],"using":[155],"API-specified":[156],"functionality":[158],"deliberately":[160],"constituted":[161],"skeletons":[163],"synthesize":[165],"concrete":[166],"code.":[167],"Extensive":[168],"experiments":[169],"demonstrate":[170],"DataScope\u2019s":[171],"effectiveness,":[172],"fine-tuned":[175],"its":[177],"synthesized":[178],"outperforming":[180],"those":[181],"tuned":[182],"unoptimized":[184],"five":[186],"times":[187],"larger.":[188],"Furthermore,":[189],"series":[191],"analyses":[193],"model":[195],"internals,":[196],"relevant":[197],"hyperparameters,":[198],"case":[200],"studies":[201],"provide":[202],"additional":[203],"evidence":[204],"efficacy":[207],"our":[209],"proposed":[210],"methods.":[211],"These":[212],"findings":[213],"underscore":[214],"significance":[216],"advance":[223],"field":[225],"providing":[229],"efficient,":[231],"cost-effective":[232],"constructing":[235],"datasets,":[237],"which":[238],"turn":[240],"lead":[241],"more":[243],"powerful":[244],"tailored":[246]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-10-10T00:00:00"}