{"id":"https://openalex.org/W4381621958","doi":"https://doi.org/10.14778/3594512.3594518","title":"Pollock: A Data Loading Benchmark","display_name":"Pollock: A Data Loading Benchmark","publication_year":2023,"publication_date":"2023-04-01","ids":{"openalex":"https://openalex.org/W4381621958","doi":"https://doi.org/10.14778/3594512.3594518"},"language":"en","primary_location":{"id":"doi:10.14778/3594512.3594518","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3594512.3594518","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5049909455","display_name":"Gerardo Vitagliano","orcid":"https://orcid.org/0000-0001-7782-2596"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerardo Vitagliano","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032761397","display_name":"Mazhar Hameed","orcid":"https://orcid.org/0000-0002-4821-4417"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mazhar Hameed","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079795665","display_name":"Lan Jiang","orcid":"https://orcid.org/0000-0002-4735-3845"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lan Jiang","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042872229","display_name":"Lucas Reisener","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lucas Reisener","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049016095","display_name":"Eugene Wu","orcid":"https://orcid.org/0000-0003-4254-6688"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Wu","raw_affiliation_strings":["Columbia University, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053028480","display_name":"Felix Naumann","orcid":"https://orcid.org/0000-0002-4483-1389"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5213,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94986276,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"16","issue":"8","first_page":"1870","last_page":"1882"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9993000030517578,"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":0.9993000030517578,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9984999895095825,"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/T11719","display_name":"Data Quality and Management","score":0.9977999925613403,"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":0.8258615732192993},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7316648960113525},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6977334022521973},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6090971231460571},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.5322800874710083},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4965105652809143},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.49333420395851135},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.45615875720977783},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4251117408275604},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3420103192329407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21401768922805786},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21385040879249573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8258615732192993},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7316648960113525},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6977334022521973},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6090971231460571},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5322800874710083},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4965105652809143},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.49333420395851135},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.45615875720977783},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4251117408275604},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3420103192329407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21401768922805786},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21385040879249573},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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":2,"locations":[{"id":"doi:10.14778/3594512.3594518","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3594512.3594518","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:kobv.de-opus4-uni-potsdam:64364","is_oa":false,"landing_page_url":"https://publishup.uni-potsdam.de/frontdoor/index/index/docId/64364","pdf_url":null,"source":{"id":"https://openalex.org/S4306400594","display_name":"publish.UP (University of Potsdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I176453806","host_organization_name":"University of Potsdam","host_organization_lineage":["https://openalex.org/I176453806"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1983423379","https://openalex.org/W2124479173","https://openalex.org/W2249895122","https://openalex.org/W2296703446","https://openalex.org/W2498523297","https://openalex.org/W2522705507","https://openalex.org/W2582743722","https://openalex.org/W2898192927","https://openalex.org/W2902696364","https://openalex.org/W2920753677","https://openalex.org/W3047259347","https://openalex.org/W3082162291","https://openalex.org/W3099161928","https://openalex.org/W3111439114","https://openalex.org/W3199669024","https://openalex.org/W4210251636","https://openalex.org/W4251033482","https://openalex.org/W4300782170","https://openalex.org/W6950020668"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2087343574","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Any":[0],"system":[1],"at":[2],"play":[3],"in":[4,66],"a":[5,9,58,80,95,158],"data-driven":[6],"project":[7],"has":[8],"fundamental":[10],"requirement:":[11],"the":[12,30,62,84,109,113,130,136],"ability":[13],"to":[14,21,44,60,82,93,99],"load":[15,48],"data.":[16],"The":[17],"de-facto":[18],"standard":[19],"format":[20,38],"distribute":[22],"and":[23,33,46,73,90,143,157],"consume":[24],"raw":[25],"data":[26,53,68,159],"is":[27],"csv.":[28],"Yet,":[29],"plain":[31],"text":[32],"flexible":[34],"nature":[35],"of":[36,64,123,138],"this":[37],"make":[39],"such":[40],"files":[41,89],"often":[42],"difficult":[43],"parse":[45],"correctly":[47],"their":[49],"content,":[50],"requiring":[51],"cumbersome":[52],"preparation":[54],"steps.":[55],"We":[56,134],"propose":[57],"benchmark":[59,107,140],"assess":[61],"robustness":[63],"systems":[65],"loading":[67],"from":[69],"non-standard":[70],"csv":[71,114,127,149],"formats":[72],"with":[74],"structural":[75],"inconsistencies.":[76],"First,":[77],"we":[78,119,132],"formalize":[79],"model":[81],"describe":[83],"issues":[85],"that":[86],"affect":[87],"real-world":[88],"use":[91],"it":[92],"derive":[94],"systematic":[96],"\"pollution\"":[97],"process":[98],"generate":[100],"dialects":[101],"for":[102,112],"any":[103],"given":[104],"grammar.":[105],"Our":[106],"leverages":[108],"pollution":[110],"framework":[111],"format.":[115],"To":[116],"guide":[117],"pollution,":[118],"have":[120],"surveyed":[121],"thousands":[122],"real-world,":[124],"publicly":[125],"available":[126],"files,":[128],"recording":[129],"problems":[131],"encountered.":[133],"demonstrate":[135],"applicability":[137],"our":[139],"by":[141],"testing":[142],"scoring":[144],"16":[145],"different":[146],"systems:":[147],"popular":[148],"parsing":[150],"frameworks,":[151],"relational":[152],"database":[153],"tools,":[154],"spreadsheet":[155],"systems,":[156],"visualization":[160],"tool.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
