{"id":"https://openalex.org/W4313563421","doi":"https://doi.org/10.1145/3551349.3556903","title":"CrystalBLEU: Precisely and Efficiently Measuring the Similarity of Code","display_name":"CrystalBLEU: Precisely and Efficiently Measuring the Similarity of Code","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4313563421","doi":"https://doi.org/10.1145/3551349.3556903"},"language":"en","primary_location":{"id":"doi:10.1145/3551349.3556903","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3551349.3556903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","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/A5002459483","display_name":"Aryaz Eghbali","orcid":"https://orcid.org/0000-0001-9763-8147"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Aryaz Eghbali","raw_affiliation_strings":["University of Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9763-8147","affiliations":[{"raw_affiliation_string":"University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013438083","display_name":"Michael Pradel","orcid":"https://orcid.org/0000-0003-1623-498X"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Pradel","raw_affiliation_strings":["University of Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1623-498X","affiliations":[{"raw_affiliation_string":"University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9934999942779541,"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/T10028","display_name":"Topic Modeling","score":0.9921000003814697,"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":0.8188515901565552},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.5948797464370728},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5630882382392883},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5569394826889038},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5347157120704651},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5326288342475891},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4974227249622345},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.47821876406669617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4715927839279175},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4690314531326294},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46863627433776855},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4501693546772003},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32205918431282043},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09146773815155029},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07782435417175293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8188515901565552},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5948797464370728},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5630882382392883},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5569394826889038},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5347157120704651},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5326288342475891},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4974227249622345},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.47821876406669617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4715927839279175},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4690314531326294},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46863627433776855},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4501693546772003},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32205918431282043},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09146773815155029},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07782435417175293},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3551349.3556903","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3551349.3556903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G8390793956","display_name":null,"funder_award_id":"851895","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"}],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2065053490","https://openalex.org/W2124763802","https://openalex.org/W2143177362","https://openalex.org/W2150824314","https://openalex.org/W2242083635","https://openalex.org/W2247864914","https://openalex.org/W2251023345","https://openalex.org/W2402619042","https://openalex.org/W2600463316","https://openalex.org/W2605202003","https://openalex.org/W2747329762","https://openalex.org/W2794908093","https://openalex.org/W2795150841","https://openalex.org/W2796460440","https://openalex.org/W2806532810","https://openalex.org/W2884276923","https://openalex.org/W2887364112","https://openalex.org/W2888557792","https://openalex.org/W2907705732","https://openalex.org/W2945332763","https://openalex.org/W2950599942","https://openalex.org/W2954823997","https://openalex.org/W2962706825","https://openalex.org/W2962936887","https://openalex.org/W2963532001","https://openalex.org/W2963868406","https://openalex.org/W2963935794","https://openalex.org/W2967096374","https://openalex.org/W2998011150","https://openalex.org/W3005628256","https://openalex.org/W3011013751","https://openalex.org/W3011564318","https://openalex.org/W3091730360","https://openalex.org/W3104907093","https://openalex.org/W3105867435","https://openalex.org/W3105903381","https://openalex.org/W3108032709","https://openalex.org/W3125781052","https://openalex.org/W3146720657","https://openalex.org/W3162689995","https://openalex.org/W3195156628","https://openalex.org/W4206312123","https://openalex.org/W4281611258","https://openalex.org/W4308643013","https://openalex.org/W6602670149"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W3110702597","https://openalex.org/W2078761926","https://openalex.org/W2110441383","https://openalex.org/W2125620709","https://openalex.org/W1498872724","https://openalex.org/W4233149903","https://openalex.org/W4293864700","https://openalex.org/W2524540579","https://openalex.org/W2326878701"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2,111],"brought":[3],"a":[4,39,49,92,221,253],"surge":[5],"of":[6,11,34,38,48,108,117,124,137,177,185,225,257],"work":[7,30,218],"on":[8,81,166,213,220],"predicting":[9],"pieces":[10,107],"source":[12],"code,":[13,198],"e.g.,":[14],"for":[15,65,170,259],"code":[16,18,109,145,148,239],"completion,":[17],"migration,":[19],"program":[20],"repair,":[21],"or":[22,195],"translating":[23],"natural":[24,67,96],"language":[25,68,84],"into":[26],"code.":[27,178,260],"All":[28],"this":[29],"faces":[31],"the":[32,36,46,57,103,118,135,138,155,175,182,203,248],"challenge":[33],"evaluating":[35,66],"quality":[37],"prediction":[40],"w.r.t.":[41],"some":[42],"oracle,":[43],"typically":[44],"in":[45,72,102,154],"form":[47],"reference":[50],"solution.":[51],"A":[52],"common":[53,113],"evaluation":[54,88,163],"metric":[55,62,139,164,180],"is":[56,100],"BLEU":[58,250,258],"score,":[59],"an":[60,162],"n-gram-based":[61],"originally":[63],"proposed":[64,255],"translation,":[69],"but":[70],"adopted":[71],"software":[73],"engineering":[74],"because":[75,116],"it":[76],"can":[77,234],"be":[78],"easily":[79],"computed":[80],"any":[82],"programming":[83,98,125],"and":[85,97,121,147,172,199,219,252],"enables":[86],"automated":[87],"at":[89],"scale.":[90],"However,":[91],"key":[93],"difference":[94],"between":[95,142],"languages":[99],"that":[101,129,150,168,232],"latter,":[104],"completely":[105],"unrelated":[106],"may":[110],"many":[112],"n-grams":[114,133],"simply":[115],"syntactic":[119],"verbosity":[120],"coding":[122],"conventions":[123],"languages.":[126],"We":[127,210],"observe":[128],"these":[130],"trivially":[131,207],"shared":[132,208],"hamper":[134],"ability":[136],"to":[140,192,247],"distinguish":[141,235],"truly":[143],"similar":[144,236],"examples":[146,149,240],"are":[151],"merely":[152],"written":[153],"same":[156],"language.":[157],"This":[158],"paper":[159],"presents":[160],"CrystalBLEU,":[161],"based":[165],"BLEU,":[167,186],"allows":[169],"precisely":[171],"efficiently":[173],"measuring":[174],"similarity":[176],"Our":[179,229],"preserves":[181],"desirable":[183],"properties":[184],"such":[187],"as":[188],"being":[189],"language-agnostic,":[190],"able":[191],"handle":[193],"incomplete":[194],"partially":[196],"incorrect":[197],"efficient,":[200],"while":[201],"reducing":[202],"noise":[204],"caused":[205],"by":[206],"n-grams.":[209],"evaluate":[211],"CrystalBLEU":[212,233],"two":[214],"datasets":[215],"from":[216,237],"prior":[217],"new,":[222],"labeled":[223],"dataset":[224],"semantically":[226],"equivalent":[227],"programs.":[228],"results":[230],"show":[231],"dissimilar":[238],"1.9\u20134.5":[241],"times":[242],"more":[243],"effectively,":[244],"when":[245],"compared":[246],"original":[249],"score":[251],"previously":[254],"variant":[256]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}