{"id":"https://openalex.org/W4403577861","doi":"https://doi.org/10.1145/3627673.3679157","title":"A Generative Benchmark Creation Framework for Detecting Common Data Table Versions","display_name":"A Generative Benchmark Creation Framework for Detecting Common Data Table Versions","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403577861","doi":"https://doi.org/10.1145/3627673.3679157"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679157","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679157","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3627673.3679157","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108302275","display_name":"D. Fox","orcid":"https://orcid.org/0009-0004-7622-7196"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel C. Fox","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, USA"],"raw_orcid":"https://orcid.org/0009-0004-7622-7196","affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047161025","display_name":"Aamod Khatiwada","orcid":"https://orcid.org/0000-0001-5720-1207"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aamod Khatiwada","raw_affiliation_strings":["Northeastern University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0001-5720-1207","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002899918","display_name":"Roee Shraga","orcid":"https://orcid.org/0000-0001-8803-8481"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roee Shraga","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, USA"],"raw_orcid":"https://orcid.org/0000-0001-8803-8481","affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, USA","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108302275"],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":0.3364,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6172906,"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":"5365","last_page":"5369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.796227216720581},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7512654066085815},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.7192451357841492},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.588032066822052},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4477611780166626},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.41841864585876465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4071934223175049},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39590758085250854},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3372359275817871},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.203314870595932}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796227216720581},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7512654066085815},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7192451357841492},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.588032066822052},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4477611780166626},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.41841864585876465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4071934223175049},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39590758085250854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3372359275817871},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.203314870595932},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679157","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679157","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3627673.3679157","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679157","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W297231882","https://openalex.org/W2424304400","https://openalex.org/W2798664493","https://openalex.org/W2806276686","https://openalex.org/W2970992672","https://openalex.org/W3123788974","https://openalex.org/W3173442755","https://openalex.org/W3185341429","https://openalex.org/W3201524081","https://openalex.org/W4309674289","https://openalex.org/W4361230065","https://openalex.org/W4380433117","https://openalex.org/W4389539730","https://openalex.org/W4400910547","https://openalex.org/W4404437288"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"Multiple":[0],"versions":[1,49],"of":[2,20,26,67,80,133],"the":[3,21,130,134],"same":[4],"dataset":[5],"can":[6],"exist":[7],"in":[8,51],"a":[9,65,78,87],"data":[10,13,15,27,42,52,54,73,94],"repository":[11],"(e.g.,":[12],"warehouses,":[14],"lakes,":[16],"etc.),":[17],"mainly":[18],"because":[19],"interactive":[22],"and":[23,35,56,71,119,140],"collaborative":[24],"nature":[25],"science.":[28],"Data":[29],"creators":[30],"generally":[31],"update":[32],"existing":[33,109,144],"datasets":[34,40],"upload":[36],"them":[37],"as":[38],"new":[39],"to":[41,69,90,143],"repositories":[43],"without":[44],"proper":[45,115],"documentation.":[46],"Identifying":[47],"such":[48],"helps":[50],"management,":[53],"governance,":[55],"making":[57],"better":[58],"decisions":[59],"using":[60,96],"data.":[61],"However,":[62],"there":[63],"is":[64],"dearth":[66],"benchmarks":[68,92,110],"develop":[70],"evaluate":[72],"versioning":[74,95],"techniques,":[75],"which":[76],"requires":[77],"lot":[79],"human":[81],"effort.":[82],"Thus,":[83],"this":[84],"work":[85],"introduces":[86],"novel":[88],"framework":[89,105],"generate":[91],"for":[93],"Generative":[97],"AI":[98],"(specifically":[99],"Large":[100],"Language":[101],"Models).":[102],"The":[103],"proposed":[104],"offers":[106],"properties":[107],"that":[108,136],"do":[111],"not":[112],"have,":[113],"including":[114],"documentation,":[116],"version":[117,132],"lineage,":[118],"complex":[120],"transformations":[121],"generated":[122],"by":[123],"an":[124],"LLM.":[125],"We":[126],"also":[127],"share":[128],"VerLLM-v1,":[129],"first":[131],"benchmark":[135],"features":[137],"these":[138],"properties,":[139],"compare":[141],"it":[142],"benchmarks.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
