{"id":"https://openalex.org/W4386977432","doi":"https://doi.org/10.1145/3622856","title":"Turaco: Complexity-Guided Data Sampling for Training Neural Surrogates of Programs","display_name":"Turaco: Complexity-Guided Data Sampling for Training Neural Surrogates of Programs","publication_year":2023,"publication_date":"2023-10-16","ids":{"openalex":"https://openalex.org/W4386977432","doi":"https://doi.org/10.1145/3622856"},"language":"en","primary_location":{"id":"doi:10.1145/3622856","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3622856","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3622856","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3622856","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043695340","display_name":"Alex Renda","orcid":"https://orcid.org/0000-0002-8318-0363"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alex Renda","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101401266","display_name":"Yi Ding","orcid":"https://orcid.org/0000-0003-2757-9182"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Ding","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091194125","display_name":"Michael Carbin","orcid":"https://orcid.org/0000-0002-6928-0456"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Carbin","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043695340"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12168612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"OOPSLA2","first_page":"1648","last_page":"1676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9997000098228455,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9997000098228455,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9983000159263611,"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":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8323839902877808},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5822272896766663},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5772433280944824},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5570976138114929},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.528171718120575},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5103916525840759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47559890151023865},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4734456241130829},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4711662232875824},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4650147557258606},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.45090052485466003},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14024990797042847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8323839902877808},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5822272896766663},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5772433280944824},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5570976138114929},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.528171718120575},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5103916525840759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47559890151023865},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4734456241130829},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4711662232875824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4650147557258606},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.45090052485466003},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14024990797042847},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3622856","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3622856","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3622856","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:arXiv.org:2309.11726","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.11726","pdf_url":"https://arxiv.org/pdf/2309.11726","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/153003","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/153003","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/153003/1/3622856.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Association for Computing Machinery","raw_type":"http://purl.org/eprint/type/JournalArticle"}],"best_oa_location":{"id":"doi:10.1145/3622856","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3622856","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3622856","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":[{"id":"https://openalex.org/G2082912093","display_name":null,"funder_award_id":"1918839","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3420604346","display_name":null,"funder_award_id":"CCF-2217064","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G40301894","display_name":null,"funder_award_id":"217064","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6625619449","display_name":null,"funder_award_id":"CCF-22170","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7353493908","display_name":null,"funder_award_id":"HR00112190046","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7588888253","display_name":"PPoSS: LARGE: Intel: Combining Learning and Formal Verification for Scalable Machine Programming (ScaMP)","funder_award_id":"2217064","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7676851319","display_name":null,"funder_award_id":"CCF-1918839,CCF-2217064,2030859","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7698193007","display_name":null,"funder_award_id":"2030859","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386977432.pdf","grobid_xml":"https://content.openalex.org/works/W4386977432.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1230660382","https://openalex.org/W1553894716","https://openalex.org/W2029538739","https://openalex.org/W2043100293","https://openalex.org/W2049451779","https://openalex.org/W2058760524","https://openalex.org/W2064068519","https://openalex.org/W2101512909","https://openalex.org/W2103953062","https://openalex.org/W2105035536","https://openalex.org/W2142096775","https://openalex.org/W2150324076","https://openalex.org/W2157070686","https://openalex.org/W2160401437","https://openalex.org/W2227234579","https://openalex.org/W2295915207","https://openalex.org/W2377019924","https://openalex.org/W2478429860","https://openalex.org/W2554131156","https://openalex.org/W2809933567","https://openalex.org/W2887178829","https://openalex.org/W2903158431","https://openalex.org/W2962360676","https://openalex.org/W2963674831","https://openalex.org/W2987395105","https://openalex.org/W3081873517","https://openalex.org/W3097352266","https://openalex.org/W3100537219","https://openalex.org/W3107652887","https://openalex.org/W3139485201","https://openalex.org/W3207455984","https://openalex.org/W4233896666","https://openalex.org/W4234542549","https://openalex.org/W4234924236","https://openalex.org/W4236934668","https://openalex.org/W4238893454","https://openalex.org/W4240237526","https://openalex.org/W4244730588","https://openalex.org/W4249753629"],"related_works":["https://openalex.org/W2140798747","https://openalex.org/W2948169060","https://openalex.org/W2730112582","https://openalex.org/W2110696645","https://openalex.org/W2358580169","https://openalex.org/W2111347279","https://openalex.org/W2487211728","https://openalex.org/W2378096925","https://openalex.org/W2485376993","https://openalex.org/W2042102171"],"abstract_inverted_index":{"Programmers":[0,29],"and":[1],"researchers":[2],"are":[3],"increasingly":[4],"developing":[5],"surrogates":[6,31,77],"of":[7,10,13,17,25,34,37,43,49,63,78,85,92,102,109,113,128,141],"programs,":[8,143],"models":[9],"a":[11,18,23,38,41,61,64,69,93,111,121,132,139],"subset":[12],"the":[14,35,83,103,107,114,126],"observable":[15],"behavior":[16,36],"given":[19,65],"program,":[20],"to":[21,57,59,74,87,98,124],"solve":[22],"variety":[24],"software":[26],"development":[27],"challenges.":[28],"train":[30,60,75],"from":[32,89],"measurements":[33],"program":[39,122],"on":[40,106,138],"dataset":[42],"input":[44,95],"examples.":[45],"A":[46],"key":[47],"challenge":[48],"surrogate":[50,62,112],"construction":[51],"is":[52],"determining":[53],"what":[54],"training":[55],"data":[56,86],"use":[58],"program.":[66,133],"We":[67,80,118,134],"present":[68],"methodology":[70],"for":[71],"sampling":[72,147],"datasets":[73],"neural-network-based":[76],"programs.":[79],"first":[81],"characterize":[82],"proportion":[84],"sample":[88],"each":[90],"region":[91],"program's":[94],"space":[96],"(corresponding":[97],"different":[99,129],"execution":[100,116],"paths":[101,130],"program)":[104],"based":[105],"complexity":[108,127],"learning":[110],"corresponding":[115],"path.":[117],"next":[119],"provide":[120],"analysis":[123],"determine":[125],"in":[131,149,152],"evaluate":[135],"these":[136],"results":[137,148],"range":[140],"real-world":[142],"demonstrating":[144],"that":[145],"complexity-guided":[146],"empirical":[150],"improvements":[151],"accuracy.":[153]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}