{"id":"https://openalex.org/W3010935331","doi":"https://doi.org/10.1007/s10618-020-00680-1","title":"ptype: probabilistic type inference","display_name":"ptype: probabilistic type inference","publication_year":2020,"publication_date":"2020-03-16","ids":{"openalex":"https://openalex.org/W3010935331","doi":"https://doi.org/10.1007/s10618-020-00680-1","mag":"3010935331"},"language":"en","primary_location":{"id":"doi:10.1007/s10618-020-00680-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-020-00680-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-020-00680-1.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10618-020-00680-1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Taha Ceritli","orcid":"https://orcid.org/0000-0002-5059-8421"},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Taha Ceritli","raw_affiliation_strings":["Alan Turing Institute, London, UK","School of Informatics, University of Edinburgh, Edinburgh, UK"],"raw_orcid":"https://orcid.org/0000-0002-5059-8421","affiliations":[{"raw_affiliation_string":"Alan Turing Institute, London, UK","institution_ids":["https://openalex.org/I4210128584"]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Christopher K. I. Williams","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christopher K. I. Williams","raw_affiliation_strings":["Alan Turing Institute, London, UK","School of Informatics, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alan Turing Institute, London, UK","institution_ids":["https://openalex.org/I4210128584"]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":null,"display_name":"James Geddes","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Geddes","raw_affiliation_strings":["Alan Turing Institute, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alan Turing Institute, London, UK","institution_ids":["https://openalex.org/I4210128584"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210128584","https://openalex.org/I98677209"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.7435,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74330772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"34","issue":"3","first_page":"870","last_page":"904"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.39640000462532043,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.39640000462532043,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.21130000054836273,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.05689999833703041,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/inference","display_name":"Inference","score":0.7307999730110168},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6607999801635742},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5764999985694885},{"id":"https://openalex.org/keywords/fiducial-inference","display_name":"Fiducial inference","score":0.4860999882221222},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.46790000796318054},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4593000113964081},{"id":"https://openalex.org/keywords/type","display_name":"Type (biology)","score":0.4487999975681305},{"id":"https://openalex.org/keywords/predictive-inference","display_name":"Predictive inference","score":0.3788999915122986}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7307999730110168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6973999738693237},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6607999801635742},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5764999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5011000037193298},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4997999966144562},{"id":"https://openalex.org/C95167961","wikidata":"https://www.wikidata.org/wiki/Q4483495","display_name":"Fiducial inference","level":5,"score":0.4860999882221222},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4593000113964081},{"id":"https://openalex.org/C2777299769","wikidata":"https://www.wikidata.org/wiki/Q3707858","display_name":"Type (biology)","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41519999504089355},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.3788999915122986},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.3319999873638153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30320000648498535},{"id":"https://openalex.org/C18998212","wikidata":"https://www.wikidata.org/wiki/Q7246856","display_name":"Probabilistic logic network","level":5,"score":0.3000999987125397},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C198370458","wikidata":"https://www.wikidata.org/wiki/Q586459","display_name":"Type inference","level":3,"score":0.25279998779296875},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10618-020-00680-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-020-00680-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-020-00680-1.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/29aa1b5d-1050-4ca2-b0ec-071ebfabf2a8","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/29aa1b5d-1050-4ca2-b0ec-071ebfabf2a8","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ceritli, T, Williams, C K I & Geddes, J 2020, 'ptype: probabilistic type inference', Data Mining and Knowledge Discovery, vol. 34, no. 3, pp. 870-904. https://doi.org/10.1007/s10618-020-00680-1","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:1911.10081","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.10081","pdf_url":"https://arxiv.org/pdf/1911.10081","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:pure.ed.ac.uk:publications/29aa1b5d-1050-4ca2-b0ec-071ebfabf2a8","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/29aa1b5d-1050-4ca2-b0ec-071ebfabf2a8","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ceritli, T, Williams, C K I & Geddes, J 2020, 'ptype: probabilistic type inference', Data Mining and Knowledge Discovery, vol. 34, no. 3, pp. 870-904. https://doi.org/10.1007/s10618-020-00680-1","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1007/s10618-020-00680-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-020-00680-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-020-00680-1.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1633672591","display_name":null,"funder_award_id":"N510129","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1929909371","display_name":null,"funder_award_id":"TU/C/000018","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G3855435662","display_name":null,"funder_award_id":"N510129","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G4072067573","display_name":null,"funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G444630160","display_name":null,"funder_award_id":"EP/N510129/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4500485203","display_name":"The Alan Turing Institute","funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6517908713","display_name":null,"funder_award_id":"TU/C/000018","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8597009950","display_name":null,"funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320313467","display_name":"Alan Turing Institute","ror":"https://ror.org/035dkdb55"},{"id":"https://openalex.org/F4320314707","display_name":"Government of the United Kingdom","ror":"https://ror.org/05wnh3t63"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3010935331.pdf","grobid_xml":"https://content.openalex.org/works/W3010935331.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1554186908","https://openalex.org/W1877570817","https://openalex.org/W1982280055","https://openalex.org/W2001179000","https://openalex.org/W2020144989","https://openalex.org/W2046793639","https://openalex.org/W2054801208","https://openalex.org/W2064766209","https://openalex.org/W2102804087","https://openalex.org/W2111869785","https://openalex.org/W2122092249","https://openalex.org/W2122646361","https://openalex.org/W2132667707","https://openalex.org/W2140890425","https://openalex.org/W2167277498","https://openalex.org/W2386500332","https://openalex.org/W2623925395","https://openalex.org/W2808833850","https://openalex.org/W2963368172","https://openalex.org/W4212875940","https://openalex.org/W4246839229","https://openalex.org/W4253103663"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Type":[1],"inference":[2,48],"refers":[3],"to":[4,53],"the":[5,9,65],"task":[6],"of":[7,12,16],"inferring":[8],"data":[10,23,26,35,59],"type":[11,47],"a":[13,44],"given":[14],"column":[15],"data.":[17],"Current":[18],"approaches":[19],"often":[20],"fail":[21],"when":[22],"contains":[24],"missing":[25],"and":[27,57],"anomalies,":[28],"which":[29],"are":[30],"found":[31],"commonly":[32],"in":[33],"real-world":[34],"sets.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"propose":[41],"ptype":[42],",":[43],"probabilistic":[45],"robust":[46],"method":[49,67],"that":[50,64],"allows":[51],"us":[52],"detect":[54],"such":[55],"entries,":[56],"infer":[58],"types.":[60],"We":[61],"further":[62],"show":[63],"proposed":[66],"outperforms":[68],"existing":[69],"methods.":[70]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2020-03-23T00:00:00"}