{"id":"https://openalex.org/W2096657610","doi":"https://doi.org/10.1145/2660193.2660226","title":"Using web corpus statistics for program analysis","display_name":"Using web corpus statistics for program analysis","publication_year":2014,"publication_date":"2014-10-15","ids":{"openalex":"https://openalex.org/W2096657610","doi":"https://doi.org/10.1145/2660193.2660226","mag":"2096657610"},"language":"en","primary_location":{"id":"doi:10.1145/2660193.2660226","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2660193.2660226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM International Conference on Object Oriented Programming Systems Languages & Applications","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/A5016514999","display_name":"Chun-Hung Hsiao","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chun-Hung Hsiao","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039133265","display_name":"Michael Cafarella","orcid":"https://orcid.org/0000-0001-6122-0590"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Cafarella","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075649670","display_name":"Satish Narayanasamy","orcid":"https://orcid.org/0000-0001-5016-1214"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satish Narayanasamy","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016514999"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":13.9238,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.98541895,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"65"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9905999898910522,"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":0.8318859338760376},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5921643376350403},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5422384142875671},{"id":"https://openalex.org/keywords/semantic-analysis","display_name":"Semantic analysis (machine learning)","score":0.4705018699169159},{"id":"https://openalex.org/keywords/program-analysis","display_name":"Program analysis","score":0.4607779383659363},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.45963814854621887},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.44489023089408875},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.42617279291152954},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.42047759890556335},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4167208671569824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4129427671432495},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3497107923030853},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.19642260670661926}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8318859338760376},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5921643376350403},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5422384142875671},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.4705018699169159},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.4607779383659363},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.45963814854621887},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.44489023089408875},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.42617279291152954},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.42047759890556335},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4167208671569824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4129427671432495},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3497107923030853},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.19642260670661926},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2660193.2660226","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2660193.2660226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM International Conference on Object Oriented Programming Systems Languages & Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.650.4507","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.650.4507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.eecs.umich.edu/~michjc/papers/oopsla14_chunhung.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2434760427","display_name":null,"funder_award_id":"CAREER-1149773","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W1564657277","https://openalex.org/W1593203335","https://openalex.org/W1993301141","https://openalex.org/W1994573369","https://openalex.org/W2013497015","https://openalex.org/W2019096529","https://openalex.org/W2027943354","https://openalex.org/W2048693719","https://openalex.org/W2101156500","https://openalex.org/W2103807550","https://openalex.org/W2104301886","https://openalex.org/W2106858176","https://openalex.org/W2107697055","https://openalex.org/W2109664771","https://openalex.org/W2110034858","https://openalex.org/W2111295912","https://openalex.org/W2111607365","https://openalex.org/W2114067856","https://openalex.org/W2119887272","https://openalex.org/W2125260159","https://openalex.org/W2128782367","https://openalex.org/W2142403498","https://openalex.org/W2143861926","https://openalex.org/W2144211451","https://openalex.org/W2144344516","https://openalex.org/W2146659255","https://openalex.org/W2162376048","https://openalex.org/W2171168235","https://openalex.org/W2753679530","https://openalex.org/W3090556797","https://openalex.org/W3104103145","https://openalex.org/W4233319527","https://openalex.org/W4233347627","https://openalex.org/W4256238177","https://openalex.org/W6681648988"],"related_works":["https://openalex.org/W2906970013","https://openalex.org/W3126081632","https://openalex.org/W2625039379","https://openalex.org/W2902593166","https://openalex.org/W1555968995","https://openalex.org/W2617035575","https://openalex.org/W2118467784","https://openalex.org/W2769915287","https://openalex.org/W1535216022","https://openalex.org/W2115848326"],"abstract_inverted_index":{"Several":[0],"program":[1,52],"analysis":[2,53],"tools":[3],"-":[4,12],"such":[5],"as":[6],"plagiarism":[7,26],"detection":[8],"and":[9,58,85],"bug":[10],"finding":[11,56],"rely":[13],"on":[14],"knowing":[15],"a":[16,25,71,82],"piece":[17],"of":[18,73,92],"code's":[19],"relative":[20],"semantic":[21],"importance.":[22],"For":[23],"example,":[24],"detector":[27],"should":[28,43],"not":[29,65],"bother":[30],"reporting":[31],"two":[32],"programs":[33,45],"that":[34,46],"have":[35,80],"an":[36,89],"identical":[37],"simple":[38],"loop":[39],"counter":[40],"test,":[41],"but":[42,63],"report":[44],"share":[47],"more":[48],"distinctive":[49],"code.":[50],"Traditional":[51],"techniques":[54],"(e.g.,":[55],"data":[57],"control":[59],"dependencies)":[60],"are":[61],"useful,":[62],"do":[64],"say":[66],"how":[67],"surprising":[68],"or":[69],"common":[70],"line":[72],"code":[74],"is.":[75],"Natural":[76],"language":[77],"processing":[78],"researchers":[79],"encountered":[81],"similar":[83],"problem":[84],"addressed":[86],"it":[87],"using":[88],"n-gram":[90],"model":[91],"text":[93,100],"frequency,":[94],"derived":[95],"from":[96],"statistics":[97],"computed":[98],"over":[99],"corpora.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}