{"id":"https://openalex.org/W2238673293","doi":"https://doi.org/10.1145/2837614.2837671","title":"Learning programs from noisy data","display_name":"Learning programs from noisy data","publication_year":2016,"publication_date":"2016-01-07","ids":{"openalex":"https://openalex.org/W2238673293","doi":"https://doi.org/10.1145/2837614.2837671","mag":"2238673293"},"language":"en","primary_location":{"id":"doi:10.1145/2837614.2837671","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2837614.2837671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd Annual ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages","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/A5051227985","display_name":"Veselin Raychev","orcid":null},"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":true,"raw_author_name":"Veselin Raychev","raw_affiliation_strings":["ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090644266","display_name":"Pavol Bielik","orcid":null},"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":"Pavol Bielik","raw_affiliation_strings":["ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069901599","display_name":"Martin Vechev","orcid":"https://orcid.org/0000-0002-0054-9568"},"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":"Martin Vechev","raw_affiliation_strings":["ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003040843","display_name":"Andreas Krause","orcid":"https://orcid.org/0000-0001-7260-9673"},"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":"Andreas Krause","raw_affiliation_strings":["ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051227985"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":30.4795,"has_fulltext":false,"cited_by_count":127,"citation_normalized_percentile":{"value":0.99615844,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"761","last_page":"774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9988999962806702,"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":0.9927999973297119,"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":0.8541228771209717},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8072695732116699},{"id":"https://openalex.org/keywords/digital-subscriber-line","display_name":"Digital subscriber line","score":0.6077759265899658},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5667846202850342},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5322083830833435},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.532105565071106},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5094266533851624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4699456989765167},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4428115487098694},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.435604453086853},{"id":"https://openalex.org/keywords/toolchain","display_name":"Toolchain","score":0.4324432611465454},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.41112980246543884},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38591086864471436},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.20485079288482666},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19266363978385925},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11030611395835876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8541228771209717},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8072695732116699},{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.6077759265899658},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5667846202850342},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5322083830833435},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.532105565071106},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5094266533851624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4699456989765167},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4428115487098694},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.435604453086853},{"id":"https://openalex.org/C2777062904","wikidata":"https://www.wikidata.org/wiki/Q545406","display_name":"Toolchain","level":3,"score":0.4324432611465454},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.41112980246543884},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38591086864471436},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.20485079288482666},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19266363978385925},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11030611395835876},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2837614.2837671","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2837614.2837671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd Annual ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.708.3847","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.708.3847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.srl.inf.ethz.ch/papers/popl16.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W104884240","https://openalex.org/W1480909796","https://openalex.org/W1482827835","https://openalex.org/W1530458829","https://openalex.org/W1531552153","https://openalex.org/W1542723682","https://openalex.org/W1561572740","https://openalex.org/W1607768087","https://openalex.org/W1973831620","https://openalex.org/W1994573369","https://openalex.org/W2026775511","https://openalex.org/W2045964207","https://openalex.org/W2048027175","https://openalex.org/W2061091230","https://openalex.org/W2083878868","https://openalex.org/W2100604298","https://openalex.org/W2113641473","https://openalex.org/W2116272605","https://openalex.org/W2122646361","https://openalex.org/W2122735631","https://openalex.org/W2132525863","https://openalex.org/W2134734244","https://openalex.org/W2141692389","https://openalex.org/W2142403498","https://openalex.org/W2143861926","https://openalex.org/W2144951274","https://openalex.org/W2146574666","https://openalex.org/W2148190602","https://openalex.org/W2149236697","https://openalex.org/W2156981320","https://openalex.org/W2157976942","https://openalex.org/W2158615804","https://openalex.org/W2162960800","https://openalex.org/W2171561334","https://openalex.org/W2251236187","https://openalex.org/W2728991836","https://openalex.org/W2912532449","https://openalex.org/W2913273467","https://openalex.org/W2914795292","https://openalex.org/W2950680102","https://openalex.org/W3014235357","https://openalex.org/W4237412827","https://openalex.org/W4242364663","https://openalex.org/W4299828299"],"related_works":["https://openalex.org/W2013037783","https://openalex.org/W2909413202","https://openalex.org/W1999008563","https://openalex.org/W4385243142","https://openalex.org/W2561644314","https://openalex.org/W2794118724","https://openalex.org/W2912135124","https://openalex.org/W3047895653","https://openalex.org/W4288087796","https://openalex.org/W3122369893"],"abstract_inverted_index":{"We":[0,68,117,151,173],"present":[1,119,200],"a":[2,19,25,30,41,64,83,91,99,113,135,166,183,196,201,232,263,280,297,305],"new":[3,17,100,121,191],"approach":[4,12,74,178],"for":[5,204,300],"learning":[6],"programs":[7,143],"from":[8,247],"noisy":[9],"datasets.":[10],"Our":[11],"is":[13,229,262,291],"based":[14,28],"on":[15,29,55,85,108,214,282],"two":[16,59,76,120,129],"concepts:":[18],"regularized":[20,137],"program":[21,27,124],"generator":[22],"which":[23,44,126,268],"produces":[24],"candidate":[26,52],"small":[31],"sample":[32],"of":[33,102,123,148,217,315],"the":[34,47,51,80,86,128,146,154,160,177,186,248,255,259,284,293,302,312],"entire":[35],"dataset":[36,42,48,81,187],"while":[37,162],"avoiding":[38],"overfitting,":[39],"and":[40,88,239,265],"sampler":[43],"carefully":[45],"samples":[46],"by":[49,112,195,258],"leveraging":[50],"program's":[53],"score":[54],"that":[56,140,153,244,292],"dataset.":[57,249],"The":[58,94,226],"components":[60],"are":[61,211,296],"connected":[62],"in":[63,145,159,169,182,243],"continuous":[65],"feedback-directed":[66],"loop.":[67],"show":[69,152,175],"how":[70,176],"to":[71,75,98,230,240,278],"apply":[72],"this":[73],"settings:":[77],"one":[78],"where":[79,185],"has":[82],"bound":[84],"noise,":[87],"another":[89],"without":[90],"noise":[92,130],"bound.":[93],"second":[95],"setting":[96,184],"leads":[97],"way":[101],"performing":[103],"approximate":[104],"empirical":[105],"risk":[106],"minimization":[107],"hypotheses":[109],"classes":[110],"formed":[111],"discrete":[114],"search":[115],"space.":[116],"then":[118,253],"kinds":[122],"synthesizers":[125],"target":[127],"settings.":[131],"First,":[132],"we":[133,199,274],"introduce":[134,231],"novel":[136,202],"bitstream":[138],"synthesizer":[139,155],"successfully":[141],"generates":[142],"even":[144],"presence":[147],"incorrect":[149],"examples.":[150],"can":[156,179],"detect":[157],"errors":[158],"examples":[161,192],"combating":[163],"overfitting":[164],"--":[165],"major":[167],"problem":[168],"existing":[170,271],"synthesis":[171],"techniques.":[172],"also":[174,221],"be":[180,287],"used":[181],"grows":[188],"dynamically":[189],"via":[190],"(e.g.,":[193],"provided":[194],"human).":[197],"Second,":[198],"technique":[203,267],"constructing":[205],"statistical":[206],"code":[207,308],"completion":[208,309],"systems.":[209,318],"These":[210,250],"systems":[212],"trained":[213],"massive":[215],"datasets":[216],"open":[218],"source":[219],"programs,":[220],"known":[222],"as":[223,273],"``Big":[224],"Code''.":[225],"key":[227],"idea":[228],"domain":[233],"specific":[234],"language":[235],"(DSL)":[236],"over":[237],"trees":[238],"learn":[241],"functions":[242,252,295],"DSL":[245],"directly":[246],"learned":[251,294],"condition":[254],"predictions":[256],"made":[257],"system.":[260],"This":[261],"flexible":[264],"powerful":[266],"generalizes":[269],"several":[270],"works":[272],"no":[275],"longer":[276],"need":[277],"decide":[279],"priori":[281],"what":[283],"prediction":[285,313],"should":[286],"conditioned":[288],"(another":[289],"benefit":[290],"natural":[298],"mechanism":[299],"explaining":[301],"prediction).":[303],"As":[304],"result,":[306],"our":[307],"system":[310],"surpasses":[311],"capabilities":[314],"existing,":[316],"hard-wired":[317]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":16}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}