{"id":"https://openalex.org/W4403750442","doi":"https://doi.org/10.48550/arxiv.2407.12504","title":"Case2Code: Scalable Synthetic Data for Code Generation","display_name":"Case2Code: Scalable Synthetic Data for Code Generation","publication_year":2024,"publication_date":"2024-07-17","ids":{"openalex":"https://openalex.org/W4403750442","doi":"https://doi.org/10.48550/arxiv.2407.12504"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2407.12504","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.12504","pdf_url":"https://arxiv.org/pdf/2407.12504","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.12504","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061237050","display_name":"Yunfan Shao","orcid":"https://orcid.org/0000-0002-2770-7036","observed_orcids":["https://orcid.org/0000-0002-2770-7036"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shao, Yunfan","raw_affiliation_strings":["School of Computer Science , Fudan University","Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070182061","display_name":"Linyang Li","orcid":"https://orcid.org/0009-0005-4892-6253","observed_orcids":["https://orcid.org/0009-0005-4892-6253"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Linyang","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100965510","display_name":"Yichuan Ma","orcid":"https://orcid.org/0000-0003-4661-0034","observed_orcids":["https://orcid.org/0000-0003-4661-0034"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma, Yichuan","raw_affiliation_strings":["School of Computer Science , Fudan University","Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034347070","display_name":"Peiji Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Peiji","raw_affiliation_strings":["School of Computer Science , Fudan University","Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010089116","display_name":"Demin Song","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song, Demin","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004651932","display_name":"Qinyuan Cheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng, Qinyuan","raw_affiliation_strings":["School of Computer Science , Fudan University","Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Shimin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Shimin","raw_affiliation_strings":["School of Computer Science , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100711201","display_name":"Xiaonan Li","orcid":"https://orcid.org/0000-0003-3661-2394","observed_orcids":["https://orcid.org/0000-0003-3661-2394"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Xiaonan","raw_affiliation_strings":["School of Computer Science , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100317566","display_name":"Pengyu Wang","orcid":"https://orcid.org/0000-0002-4792-5997","observed_orcids":["https://orcid.org/0000-0002-4792-5997"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Pengyu","raw_affiliation_strings":["School of Computer Science , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101481141","display_name":"Qipeng Guo","orcid":"https://orcid.org/0000-0002-8805-8789","observed_orcids":["https://orcid.org/0000-0002-8805-8789"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Qipeng","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100567689","display_name":"Hang Yan","orcid":"https://orcid.org/0009-0004-5675-0406","observed_orcids":["https://orcid.org/0009-0004-5675-0406"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yan, Hang","raw_affiliation_strings":["Shanghai AI Laboratory","The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044665993","display_name":"Xipeng Qiu","orcid":"https://orcid.org/0000-0001-7163-5247","observed_orcids":["https://orcid.org/0000-0001-7163-5247"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiu, Xipeng","raw_affiliation_strings":["School of Computer Science , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088834359","display_name":"Xuanjing Huang","orcid":"https://orcid.org/0000-0001-9197-9426","observed_orcids":["https://orcid.org/0000-0001-9197-9426"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Xuanjing","raw_affiliation_strings":["School of Computer Science , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010087030","display_name":"Dahua Lin","orcid":"https://orcid.org/0000-0002-8865-7896","observed_orcids":["https://orcid.org/0000-0002-8865-7896"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Lin, Dahua","raw_affiliation_strings":["Shanghai AI Laboratory","The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9833999872207642,"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":0.9833999872207642,"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/T10533","display_name":"Teaching and Learning Programming","score":0.0052999998442828655,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.005200000014156103,"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/synthetic-data-generation","display_name":"synthetic data generation","score":0.7020000219345093},{"id":"https://openalex.org/keywords/code-generation","display_name":"code generation","score":0.9629999995231628},{"id":"https://openalex.org/keywords/inductive-reasoning","display_name":"inductive reasoning","score":0.6320000290870667},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8500000238418579},{"id":"https://openalex.org/keywords/program-synthesis","display_name":"program synthesis","score":0.5669999718666077},{"id":"https://openalex.org/keywords/program-execution","display_name":"program execution","score":0.4749999940395355},{"id":"https://openalex.org/keywords/input-output-examples","display_name":"input-output examples","score":0.6439999938011169},{"id":"https://openalex.org/keywords/program-behavior","display_name":"program behavior","score":0.48899999260902405}],"concepts":[{"id":"https://openalex.org/C21563000","wikidata":"https://www.wikidata.org/wiki/Q484511","display_name":"Inductive reasoning","level":2,"score":0.6630208492279053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48709702491760254},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.4840233027935028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4479137659072876},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32944101095199585},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.19885608553886414}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2407.12504","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.12504","pdf_url":"https://arxiv.org/pdf/2407.12504","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2407.12504","doi":"https://doi.org/10.48550/arxiv.2407.12504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.12504","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.12504","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.12504","pdf_url":"https://arxiv.org/pdf/2407.12504","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2565984771","display_name":null,"funder_award_id":"62236004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403750442.pdf","grobid_xml":"https://content.openalex.org/works/W4403750442.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7101595755","https://openalex.org/W4407711498","https://openalex.org/W4412444947","https://openalex.org/W4416610232","https://openalex.org/W4402733311","https://openalex.org/W4416068551","https://openalex.org/W4416034414","https://openalex.org/W4416037025","https://openalex.org/W4404344225","https://openalex.org/W7164194164"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2,139],"(LLMs)":[3],"have":[4],"shown":[5],"outstanding":[6],"breakthroughs":[7],"in":[8],"code":[9,14,51,79,121],"generation.":[10],"Recent":[11],"work":[12],"improves":[13],"LLMs":[15,90,134],"by":[16,22,60,81],"training":[17,118],"on":[18,36,49,147,153],"synthetic":[19,163],"data":[20,52,114,164],"generated":[21],"some":[23],"powerful":[24],"LLMs,":[25],"which":[26],"can":[27,108],"be":[28],"challenging":[29,130],"to":[30,33,76,91,102],"scale":[31,54,116],"due":[32],"the":[34,62,97,104,158],"dependence":[35],"a":[37,57],"teacher":[38],"model":[39],"and":[40,55,64,95,111,119,165],"high":[41],"generation":[42],"costs.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,107],"focus":[48],"synthesizing":[50],"at":[53,115],"propose":[56],"\\textbf{Case2Code}":[58,68,113,142],"task":[59,73],"exploiting":[61],"expressiveness":[63],"correctness":[65],"of":[66,161],"programs.":[67],"is":[69,129],"an":[70],"inductive":[71,166],"inference":[72],"that":[74,126],"aims":[75],"infer":[77],"underlying":[78],"implementations":[80],"observing":[82],"input-output":[83],"examples":[84],"or":[85],"program":[86,93,98,105],"behaviors,":[87],"By":[88],"incorporating":[89],"generate":[92],"inputs,":[94],"executing":[96],"with":[99,141],"these":[100],"inputs":[101],"obtain":[103],"outputs,":[106],"synthesize":[109],"diverse":[110],"high-quality":[112],"for":[117,131],"evaluating":[120],"LLMs.":[122],"Experimental":[123],"results":[124],"show":[125],"case-to-code":[127,149],"induction":[128,150],"current":[132],"representative":[133],"if":[135],"they":[136],"are":[137],"untrained.":[138],"trained":[140],"improve":[143],"performance":[144],"not":[145],"only":[146],"distribution":[148],"but":[151],"also":[152],"various":[154],"coding-generation":[155],"tasks,":[156],"demonstrating":[157],"great":[159],"potential":[160],"large-scale":[162],"learning.":[167]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2024-10-25T00:00:00"}