{"id":"https://openalex.org/W7026915465","doi":null,"title":"Bottom-Up Standardization For Data Preparation","display_name":"Bottom-Up Standardization For Data Preparation","publication_year":2024,"publication_date":"2024-02-01","ids":{"openalex":"https://openalex.org/W7026915465"},"language":"en","primary_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/153866","doi":null,"is_oa":true,"landing_page_url":"https://orcid.org/0009-0005-1349-1376","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/153866/1/lai-eylai-sm-eecs-2024-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.mit.edu/bitstream/1721.1/153866/1/lai-eylai-sm-eecs-2024-thesis.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lai, Eugenie Y.","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Lai, Eugenie Y.","raw_affiliation_strings":["University Of British Columbia , 2021"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Of British Columbia , 2021","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.7221999764442444,"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":0.7221999764442444,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.16519999504089355,"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":0.037300001829862595,"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/data-preparation","display_name":"data preparation","score":0.9259999990463257},{"id":"https://openalex.org/keywords/script-standardization","display_name":"script standardization","score":0.925000011920929},{"id":"https://openalex.org/keywords/user-intent","display_name":"user intention","score":0.5189999938011169},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.609000027179718},{"id":"https://openalex.org/keywords/gpt-4-comparison","display_name":"GPT-4 comparison","score":0.7200000286102295}],"concepts":[{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.8858000040054321},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.8799999952316284},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540000081062317},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6855999827384949},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5866000056266785},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5526000261306763},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4447000026702881},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3393999934196472},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.30059999227523804},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C104582849","wikidata":"https://www.wikidata.org/wiki/Q787282","display_name":"Automatic identification and data capture","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C1232282","wikidata":"https://www.wikidata.org/wiki/Q1783551","display_name":"Data conversion","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2459000051021576},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.2425999939441681},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.24230000376701355},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.23389999568462372},{"id":"https://openalex.org/C49895821","wikidata":"https://www.wikidata.org/wiki/Q5227368","display_name":"Data verification","level":2,"score":0.2337999939918518},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2313999980688095},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.23109999299049377},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.22589999437332153},{"id":"https://openalex.org/C13926793","wikidata":"https://www.wikidata.org/wiki/Q3507155","display_name":"Group method of data handling","level":2,"score":0.22429999709129333},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.22040000557899475},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.20880000293254852},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.20730000734329224},{"id":"https://openalex.org/C153876917","wikidata":"https://www.wikidata.org/wiki/Q899704","display_name":"Traceability","level":2,"score":0.2054000049829483},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.20229999721050262},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.19930000603199005},{"id":"https://openalex.org/C2985331491","wikidata":"https://www.wikidata.org/wiki/Q5227298","display_name":"Data format","level":2,"score":0.19920000433921814},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.19529999792575836},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.1940000057220459},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19290000200271606},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.19220000505447388},{"id":"https://openalex.org/C2778625365","wikidata":"https://www.wikidata.org/wiki/Q5227393","display_name":"Database application","level":2,"score":0.18490000069141388}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:dspace.mit.edu:1721.1/153866","doi":null,"is_oa":true,"landing_page_url":"https://orcid.org/0009-0005-1349-1376","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/153866/1/lai-eylai-sm-eecs-2024-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/153866","doi":null,"is_oa":true,"landing_page_url":"https://orcid.org/0009-0005-1349-1376","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/153866/1/lai-eylai-sm-eecs-2024-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7026915465.pdf","grobid_xml":"https://content.openalex.org/works/W7026915465.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1984566373","https://openalex.org/W2113411758","https://openalex.org/W2126650630","https://openalex.org/W2151763080","https://openalex.org/W2427822648","https://openalex.org/W2798578675","https://openalex.org/W2896457183","https://openalex.org/W2914436728","https://openalex.org/W2949431720","https://openalex.org/W2980180246","https://openalex.org/W2989021453","https://openalex.org/W3021274480","https://openalex.org/W3029504795","https://openalex.org/W3030163527","https://openalex.org/W3082849379","https://openalex.org/W3126805032","https://openalex.org/W3128261063","https://openalex.org/W3175745378","https://openalex.org/W3177813494","https://openalex.org/W3196575278","https://openalex.org/W4288057685","https://openalex.org/W4327810158"],"related_works":["https://openalex.org/W4404181030","https://openalex.org/W7097158037","https://openalex.org/W3102639644","https://openalex.org/W6962848163","https://openalex.org/W7155619038","https://openalex.org/W4250886560","https://openalex.org/W4392865366","https://openalex.org/W2790700396","https://openalex.org/W6977331406","https://openalex.org/W6892403041"],"abstract_inverted_index":{"Data":[0],"preparation":[1,22,48,76,92,125],"is":[2,23],"an":[3,149,166],"essential":[4],"step":[5],"in":[6,13,18,61],"every":[7],"data-related":[8],"effort,":[9],"from":[10],"scientific":[11],"projects":[12],"academia":[14],"to":[15,53,68],"data-driven":[16],"decision-making":[17],"industry.":[19],"Typically,":[20],"data":[21,37,47,75,91,124],"not":[24,147,195],"the":[25,101,143,160,198],"novel":[26],"or":[27],"interesting":[28],"piece":[29],"of":[30,138,152,159],"a":[31,39,73,81,115,122,131,156,171],"project":[32],"\u2014":[33,97],"it":[34,129],"transforms":[35,128],"raw":[36],"into":[38,130],"format":[40],"that":[41,120],"enables":[42],"further":[43],"innovative":[44],"work.":[45],"Because":[46],"scripts":[49,77,93],"are":[50,56,59,94],"never":[51],"intended":[52],"be":[54,66,105],"interesting,":[55],"project-specific,":[57],"and":[58,70,87,108,127,169],"written":[60],"general-purpose":[62],"languages,":[63],"they":[64,98],"can":[65,78],"tedious":[67],"understand":[69],"check.":[71],"As":[72],"result,":[74],"easily":[79],"become":[80],"breeding":[82],"ground":[83],"for":[84],"poor":[85],"engineering":[86],"statistical":[88],"practices.":[89],"Ideally,":[90],"\u201cadmirably":[95],"boring\u201d":[96],"should":[99],"serve":[100],"project,":[102],"but":[103,154],"otherwise":[104],"as":[106,109,111,148,155],"simple":[107],"standard":[110],"possible.":[112],"We":[113,164,174],"propose":[114],"bottom-up":[116],"script":[117,126,146,190],"standardization":[118,191],"framework":[119,141,168],"takes":[121,142],"user\u2019s":[123,144,161,199],"simpler,":[132],"more":[133,135],"standardized,":[134],"boring":[136],"version":[137],"itself.":[139],"Our":[140,187],"input":[145],"unchangeable":[150],"definition":[151],"correctness,":[153],"semantic":[157],"sketch":[158],"overall":[162],"intent.":[163],"present":[165],"algorithmic":[167],"implemented":[170],"prototype":[172],"system.":[173],"evaluate":[175],"our":[176],"approach":[177,188],"against":[178],"state-of-the-art":[179],"methods,":[180],"including":[181],"GPT-4,":[182],"on":[183],"six":[184],"real-world":[185],"datasets.":[186],"improves":[189],"by":[192],"39.5%":[193],"while":[194,201],"meaningfully":[196],"changing":[197],"intent,":[200],"GPT-4":[202],"achieves":[203],"2.9%.":[204]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}