{"id":"https://openalex.org/W2954131085","doi":"https://doi.org/10.1145/3314221.3314629","title":"SemCluster: clustering of imperative programming assignments based on quantitative semantic features","display_name":"SemCluster: clustering of imperative programming assignments based on quantitative semantic features","publication_year":2019,"publication_date":"2019-06-07","ids":{"openalex":"https://openalex.org/W2954131085","doi":"https://doi.org/10.1145/3314221.3314629","mag":"2954131085"},"language":"en","primary_location":{"id":"doi:10.1145/3314221.3314629","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3314221.3314629","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3314221.3314629","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3314221.3314629","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112223484","display_name":"David Mitchel Perry","orcid":null},"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":true,"raw_author_name":"David M. Perry","raw_affiliation_strings":["Purdue University, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078776535","display_name":"Dohyeong Kim","orcid":null},"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":"Dohyeong Kim","raw_affiliation_strings":["Purdue University, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050507709","display_name":"Roopsha Samanta","orcid":"https://orcid.org/0009-0000-2456-217X"},"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":"Roopsha Samanta","raw_affiliation_strings":["Purdue University, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107249133","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0000-0002-9544-2500"},"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":"Xiangyu Zhang","raw_affiliation_strings":["Purdue University, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112223484"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":5.6366,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.9611969,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"860","last_page":"873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9991999864578247,"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":0.9991999864578247,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/cluster-analysis","display_name":"Cluster analysis","score":0.8154175281524658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7877445220947266},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5048430562019348},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.48997417092323303},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.4548417329788208},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4467669427394867},{"id":"https://openalex.org/keywords/program-synthesis","display_name":"Program synthesis","score":0.4416372776031494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3737327456474304},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36875414848327637},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2248995304107666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11057129502296448}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8154175281524658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7877445220947266},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5048430562019348},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.48997417092323303},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.4548417329788208},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4467669427394867},{"id":"https://openalex.org/C2776937632","wikidata":"https://www.wikidata.org/wiki/Q4117718","display_name":"Program synthesis","level":2,"score":0.4416372776031494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3737327456474304},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36875414848327637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2248995304107666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11057129502296448},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3314221.3314629","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3314221.3314629","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3314221.3314629","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3314221.3314629","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3314221.3314629","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3314221.3314629","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1448401626","display_name":null,"funder_award_id":"N000141712947","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G1561463050","display_name":null,"funder_award_id":"1701331","funder_id":"https://openalex.org/F4320338291","funder_display_name":"Sandia National Laboratories"},{"id":"https://openalex.org/G2186541180","display_name":null,"funder_award_id":"CCF-1846327,1748764,1409668","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2304153372","display_name":null,"funder_award_id":"N000141410468","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G3477768063","display_name":"EAGER: A Python Program Analysis Infrastructure to Facilitate Better Data Processing","funder_award_id":"1748764","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5051192394","display_name":null,"funder_award_id":"FA8650-15-C","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5643251411","display_name":null,"funder_award_id":"and N00","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7496453604","display_name":null,"funder_award_id":"N000141410468,N000141712947","funder_id":"https://openalex.org/F4320338298","funder_display_name":"Office of Naval Research Global"},{"id":"https://openalex.org/G7991439394","display_name":null,"funder_award_id":"1409668","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8127390166","display_name":"For support to the NSTC Committee on Tecynology Innovation Workshop and subsequent policy analysis and implementation.","funder_award_id":"0001414","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8456866689","display_name":null,"funder_award_id":"FA8650-15-C-7562","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8535495650","display_name":"Multiscale Generalized Correlation: A Unified Distance-Based Correlation Measure for Dependency Discovery","funder_award_id":"1712947","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8639419808","display_name":null,"funder_award_id":"1846327","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"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/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"},{"id":"https://openalex.org/F4320338298","display_name":"Office of Naval Research Global","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2954131085.pdf","grobid_xml":"https://content.openalex.org/works/W2954131085.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W50000015","https://openalex.org/W150085617","https://openalex.org/W1480909796","https://openalex.org/W1485912969","https://openalex.org/W1513363711","https://openalex.org/W1528455415","https://openalex.org/W1537730723","https://openalex.org/W1910771831","https://openalex.org/W1972087783","https://openalex.org/W2012312630","https://openalex.org/W2031052551","https://openalex.org/W2049389441","https://openalex.org/W2049461910","https://openalex.org/W2053492725","https://openalex.org/W2076771354","https://openalex.org/W2084201645","https://openalex.org/W2087042523","https://openalex.org/W2101234009","https://openalex.org/W2107697055","https://openalex.org/W2111295912","https://openalex.org/W2117583561","https://openalex.org/W2125260159","https://openalex.org/W2129740354","https://openalex.org/W2130066447","https://openalex.org/W2137390126","https://openalex.org/W2146659255","https://openalex.org/W2153185479","https://openalex.org/W2181630915","https://openalex.org/W2246775628","https://openalex.org/W2295100577","https://openalex.org/W2299643279","https://openalex.org/W2396992199","https://openalex.org/W2397897814","https://openalex.org/W2405971678","https://openalex.org/W2474318526","https://openalex.org/W2486590439","https://openalex.org/W2498821183","https://openalex.org/W2535220184","https://openalex.org/W2605403059","https://openalex.org/W2607296636","https://openalex.org/W2729177083","https://openalex.org/W2798812031","https://openalex.org/W2963780546","https://openalex.org/W2997591727","https://openalex.org/W3003163926","https://openalex.org/W4285719527","https://openalex.org/W4292014584","https://openalex.org/W6681648988"],"related_works":["https://openalex.org/W2046435967","https://openalex.org/W2804364458","https://openalex.org/W4231775656","https://openalex.org/W4298130764","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W2083665254","https://openalex.org/W2393816671","https://openalex.org/W2158836806"],"abstract_inverted_index":{"A":[0],"fundamental":[1],"challenge":[2],"in":[3],"automated":[4],"reasoning":[5],"about":[6],"programming":[7,179],"assignments":[8,180],"at":[9],"scale":[10],"is":[11,68,78],"clustering":[12,21,191],"student":[13],"submissions":[14],"based":[15,58],"on":[16,59,172],"their":[17,60,109],"underlying":[18],"algorithms.":[19],"State-of-the-art":[20],"techniques":[22],"are":[23,97,105],"sensitive":[24],"to":[25,122,129,177],"control":[26],"structure":[27],"variations,":[28],"cannot":[29],"cluster":[30,54],"buggy":[31],"solutions":[32,176],"with":[33],"similar":[34],"correct":[35],"solutions,":[36],"and":[37,73,199],"either":[38],"require":[39],"expensive":[40],"pair-wise":[41],"program":[42,94,206],"analyses":[43],"or":[44],"training":[45],"efforts.":[46],"We":[47,85],"propose":[48],"a":[49,100,153,160,210],"novel":[50],"technique":[51],"that":[52,96,182],"can":[53],"small":[55,178],"imperative":[56],"programs":[57],"algorithmic":[61,88],"essence:":[62],"(A)":[63],"how":[64,75],"the":[65,76,124,142,148,202],"input":[66,131],"space":[67],"partitioned":[69],"into":[70,99],"equivalence":[71,83,132],"classes":[72],"(B)":[74],"problem":[77],"uniquely":[79],"addressed":[80],"within":[81,209],"individual":[82],"classes.":[84],"capture":[86],"these":[87],"aspects":[89],"as":[90],"two":[91],"quantitative":[92],"semantic":[93,117,139],"features":[95],"merged":[98],"program's":[101,143],"vector":[102,110],"representation.":[103],"Programs":[104],"then":[106],"clustered":[107],"using":[108],"representations.":[111],"The":[112,134,165],"computation":[113,135],"of":[114,126,136,150,152,156,159,168,204,213],"our":[115,137,169],"first":[116],"feature":[118,140],"leverages":[119],"model":[120],"counting":[121],"identify":[123],"number":[125,149],"inputs":[127],"belonging":[128],"an":[130],"class.":[133],"second":[138],"abstracts":[141],"data":[144],"flow":[145],"by":[146],"tracking":[147],"occurrences":[151],"unique":[154],"pair":[155],"consecutive":[157],"values":[158],"variable":[161],"during":[162],"its":[163],"lifetime.":[164],"comprehensive":[166],"evaluation":[167],"tool":[170],"SemCluster":[171,183],"benchmarks":[173],"drawn":[174],"from":[175],"shows":[181],"(1)":[184],"generates":[185],"far":[186],"fewer":[187],"clusters":[188],"than":[189],"other":[190],"techniques,":[192],"(2)":[193],"precisely":[194],"identifies":[195],"distinct":[196],"solution":[197],"strategies,":[198],"(3)":[200],"boosts":[201],"performance":[203],"clustering-based":[205],"repair,":[207],"all":[208],"reasonable":[211],"amount":[212],"time.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}