{"id":"https://openalex.org/W2055193886","doi":"https://doi.org/10.1109/msr.2013.6624055","title":"A dataset for evaluating identifier splitters","display_name":"A dataset for evaluating identifier splitters","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2055193886","doi":"https://doi.org/10.1109/msr.2013.6624055","mag":"2055193886"},"language":"en","primary_location":{"id":"doi:10.1109/msr.2013.6624055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2013.6624055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 10th Working Conference on Mining Software Repositories (MSR)","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/A5008760456","display_name":"David Binkley","orcid":"https://orcid.org/0000-0003-0059-4024"},"institutions":[{"id":"https://openalex.org/I165556055","display_name":"Loyola University Maryland","ror":"https://ror.org/01by1wp65","country_code":"US","type":"education","lineage":["https://openalex.org/I165556055"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dave Binkley","raw_affiliation_strings":["Loyola University Maryland, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Loyola University Maryland, Baltimore, MD, USA","institution_ids":["https://openalex.org/I165556055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037074105","display_name":"Dawn Lawrie","orcid":"https://orcid.org/0000-0001-7347-7086"},"institutions":[{"id":"https://openalex.org/I165556055","display_name":"Loyola University Maryland","ror":"https://ror.org/01by1wp65","country_code":"US","type":"education","lineage":["https://openalex.org/I165556055"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dawn Lawrie","raw_affiliation_strings":["Loyola University Maryland, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Loyola University Maryland, Baltimore, MD, USA","institution_ids":["https://openalex.org/I165556055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068927917","display_name":"Lori Pollock","orcid":"https://orcid.org/0000-0002-4388-4892"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lori Pollock","raw_affiliation_strings":["University of Delaware, Newark, DE, USA","University of Delaware, Newark, DE. USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of Delaware, Newark, DE. USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000817140","display_name":"Emily Hill","orcid":null},"institutions":[{"id":"https://openalex.org/I166088655","display_name":"Montclair State University","ror":"https://ror.org/01nxc2t48","country_code":"US","type":"education","lineage":["https://openalex.org/I166088655"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emily Hill","raw_affiliation_strings":["Montclair State University, Montclair, NJ, USA","Montclair State University,Montclair,NJ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montclair State University, Montclair, NJ, USA","institution_ids":["https://openalex.org/I166088655"]},{"raw_affiliation_string":"Montclair State University,Montclair,NJ,USA","institution_ids":["https://openalex.org/I166088655"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027009667","display_name":"K. Vijay\u2010Shanker","orcid":"https://orcid.org/0000-0003-0958-3073"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Vijay-Shanker","raw_affiliation_strings":["University of Delaware, Newark, DE, USA","University of Delaware, Newark, DE. USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of Delaware, Newark, DE. USA","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"401","last_page":"404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9908999800682068,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9775999784469604,"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/identifier","display_name":"Identifier","score":0.9467266798019409},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7496625185012817},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6194602251052856},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5462597608566284},{"id":"https://openalex.org/keywords/unique-identifier","display_name":"Unique identifier","score":0.4842112064361572},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42061564326286316},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3541385531425476},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25987333059310913},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.15161973237991333}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.9467266798019409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7496625185012817},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6194602251052856},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5462597608566284},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.4842112064361572},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42061564326286316},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3541385531425476},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25987333059310913},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.15161973237991333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/msr.2013.6624055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2013.6624055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 10th Working Conference on Mining Software Repositories (MSR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"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":16,"referenced_works":["https://openalex.org/W53653089","https://openalex.org/W1490674333","https://openalex.org/W1966216063","https://openalex.org/W1973681806","https://openalex.org/W2022675432","https://openalex.org/W2045922551","https://openalex.org/W2077155146","https://openalex.org/W2099294614","https://openalex.org/W2119109877","https://openalex.org/W2128737833","https://openalex.org/W2144517582","https://openalex.org/W2154027310","https://openalex.org/W4240565647","https://openalex.org/W6602176100","https://openalex.org/W6629329164","https://openalex.org/W6681198100"],"related_works":["https://openalex.org/W2413568490","https://openalex.org/W1913624564","https://openalex.org/W3130054399","https://openalex.org/W4301062032","https://openalex.org/W2319837024","https://openalex.org/W2343500026","https://openalex.org/W2390627310","https://openalex.org/W2413664130","https://openalex.org/W2051731675","https://openalex.org/W2033159440"],"abstract_inverted_index":{"Software":[0],"engineering":[1],"and":[2,83,92],"evolution":[3],"techniques":[4],"have":[5],"recently":[6],"started":[7],"to":[8,41],"exploit":[9],"the":[10,48],"natural":[11],"language":[12],"information":[13],"in":[14,20,32],"source":[15],"code.":[16],"A":[17,68],"key":[18],"step":[19],"doing":[21],"so":[22],"is":[23],"splitting":[24,35,45,66,81],"identifiers":[25,74],"into":[26],"their":[27],"constituent":[28],"words.":[29],"While":[30],"simple":[31],"concept,":[33],"identifier":[34,65],"raises":[36],"several":[37],"challenging":[38],"issues,":[39],"leading":[40],"a":[42,54,57],"range":[43],"of":[44,64,71],"techniques.":[46,67],"Consequently,":[47],"research":[49],"community":[50],"would":[51],"benefit":[52],"from":[53,77,87],"dataset":[55],"(i.e.,":[56],"gold":[58,69],"set)":[59],"that":[60],"facilitates":[61],"comparative":[62],"studies":[63],"set":[70],"2,663":[72],"split":[73],"was":[75],"constructed":[76],"8,522":[78],"individual":[79],"human":[80],"judgements":[82],"can":[84],"be":[85],"obtained":[86],"www.cs.loyola.edu/~binkley/ludiso.":[88],"This":[89],"set's":[90],"construction":[91],"observations":[93],"aimed":[94],"at":[95],"its":[96],"effective":[97],"use":[98],"are":[99],"described.":[100]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}