{"id":"https://openalex.org/W4200504264","doi":"https://doi.org/10.1109/hpec49654.2021.9622815","title":"Efficiently Building a Large Scale Dataset for Program Induction","display_name":"Efficiently Building a Large Scale Dataset for Program Induction","publication_year":2021,"publication_date":"2021-09-20","ids":{"openalex":"https://openalex.org/W4200504264","doi":"https://doi.org/10.1109/hpec49654.2021.9622815"},"language":"en","primary_location":{"id":"doi:10.1109/hpec49654.2021.9622815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5055866024","display_name":"Lauren Milechin","orcid":"https://orcid.org/0000-0002-0554-3624"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lauren Milechin","raw_affiliation_strings":["EAPS, MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"EAPS, MIT, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071956957","display_name":"Javier Lopez-Contreras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Lopez-Contreras","raw_affiliation_strings":["EECS \u2013 CSAIL, MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"EECS \u2013 CSAIL, MIT, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044201500","display_name":"Ferran Alet","orcid":"https://orcid.org/0009-0000-3059-0062"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ferran Alet","raw_affiliation_strings":["EECS \u2013 CSAIL, MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"EECS \u2013 CSAIL, MIT, Cambridge, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055866024"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.20810981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.9916999936103821,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9894999861717224,"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/computer-science","display_name":"Computer science","score":0.8220338821411133},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6475185751914978},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5964267253875732},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5910191535949707},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5671573877334595},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.5269773006439209},{"id":"https://openalex.org/keywords/program-synthesis","display_name":"Program synthesis","score":0.49976634979248047},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.43431276082992554},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4240192472934723},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3521859049797058},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3429889976978302},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3281950056552887},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3165733218193054},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1737675666809082},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08114388585090637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8220338821411133},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6475185751914978},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5964267253875732},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5910191535949707},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5671573877334595},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.5269773006439209},{"id":"https://openalex.org/C2776937632","wikidata":"https://www.wikidata.org/wiki/Q4117718","display_name":"Program synthesis","level":2,"score":0.49976634979248047},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.43431276082992554},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4240192472934723},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3521859049797058},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3429889976978302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3281950056552887},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3165733218193054},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1737675666809082},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08114388585090637},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec49654.2021.9622815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W25727798","https://openalex.org/W1596936080","https://openalex.org/W2108598243","https://openalex.org/W2483051661","https://openalex.org/W2766447205","https://openalex.org/W2883672905","https://openalex.org/W2970575144","https://openalex.org/W3027453785","https://openalex.org/W3099253635","https://openalex.org/W3106525532","https://openalex.org/W3167634474","https://openalex.org/W3196144600","https://openalex.org/W4292779060","https://openalex.org/W6601062244","https://openalex.org/W6764109406","https://openalex.org/W6777469961","https://openalex.org/W6778883912","https://openalex.org/W6795892832"],"related_works":["https://openalex.org/W618248309","https://openalex.org/W2377336366","https://openalex.org/W1601203902","https://openalex.org/W2102464536","https://openalex.org/W2361332776","https://openalex.org/W4225671779","https://openalex.org/W1568097102","https://openalex.org/W2384289458","https://openalex.org/W2384797267","https://openalex.org/W293579695"],"abstract_inverted_index":{"One":[0],"of":[1,4,61,71,123,125],"the":[2,8,41,89,102],"applications":[3],"machine":[5],"learning":[6,18],"with":[7],"most":[9],"potential":[10],"is":[11,47,97,109],"speeding":[12],"up":[13],"expensive":[14],"computational":[15],"processes,":[16,53],"i.e.":[17],"to":[19,39,63,73,134],"think.":[20],"To":[21],"do":[22],"so,":[23],"one":[24,55],"first":[25],"generates":[26],"a":[27,31,37,48,65,68,76,84,93,106,110,136],"large-scale":[28,137],"dataset":[29,66],"by":[30],"compute-intensive":[32],"process":[33],"and":[34,129],"then":[35,74],"trains":[36],"model":[38],"approximate":[40],"distribution.":[42],"High":[43],"performance":[44],"computing":[45],"(HPC)":[46],"perfect":[49],"fit":[50],"for":[51,105],"these":[52],"as":[54],"may":[56],"efficiently":[57,120],"deploy":[58],"large":[59],"amounts":[60],"computation":[62],"generate":[64,135],"in":[67],"reasonable":[69],"amount":[70],"time,":[72],"learn":[75],"computationally-efficient":[77],"solution.":[78],"Here,":[79],"we":[80,116,119],"focus":[81],"on":[82],"generating":[83,101],"program":[85,90,108,138],"synthesis":[86,139],"dataset.":[87,140],"Finding":[88],"that":[91],"fits":[92],"given":[94,107],"input-output":[95,103],"specification":[96],"very":[98],"expensive,":[99],"but":[100],"pairs":[104],"well-defined":[111],"process.":[112],"In":[113],"this":[114],"work,":[115],"show":[117],"how":[118],"ran":[121],"hundreds":[122],"thousands":[124],"C++":[126],"codes":[127],"line-by-line":[128],"used":[130],"intermediate":[131],"variable":[132],"states":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}