{"id":"https://openalex.org/W7078127361","doi":"https://doi.org/10.48550/arxiv.2508.19807","title":"Bootstrapping Learned Cost Models with Synthetic SQL Queries","display_name":"Bootstrapping Learned Cost Models with Synthetic SQL Queries","publication_year":2025,"publication_date":"2025-08-27","ids":{"openalex":"https://openalex.org/W7078127361","doi":"https://doi.org/10.48550/arxiv.2508.19807"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.19807","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.19807","pdf_url":"https://arxiv.org/pdf/2508.19807","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.19807","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086245548","display_name":"Michael Nidd","orcid":"https://orcid.org/0000-0001-7379-2852","observed_orcids":["https://orcid.org/0000-0001-7379-2852"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nidd, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012998759","display_name":"Christoph Miksovic","orcid":"https://orcid.org/0000-0002-7846-3668","observed_orcids":["https://orcid.org/0000-0002-7846-3668"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miksovic, Christoph","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076293356","display_name":"Thomas Gschwind","orcid":"https://orcid.org/0000-0003-0212-4800","observed_orcids":["https://orcid.org/0000-0003-0212-4800"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gschwind, Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063888848","display_name":"Francesco Fusco","orcid":"https://orcid.org/0000-0003-1186-5555","observed_orcids":["https://orcid.org/0000-0003-1186-5555"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fusco, Francesco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135894420","display_name":"Andrea Giovannini","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giovannini, Andrea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014197053","display_name":"Ioana Giurgiu","orcid":"https://orcid.org/0000-0001-7434-7873","observed_orcids":["https://orcid.org/0000-0001-7434-7873"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giurgiu, Ioana","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9937000274658203,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9937000274658203,"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/T11106","display_name":"Data Management and Algorithms","score":0.00139999995008111,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.0005000000237487257,"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/synthetic-data-generation","display_name":"synthetic data generation","score":0.8569999933242798},{"id":"https://openalex.org/keywords/training-data-efficiency","display_name":"training data efficiency","score":0.5860000252723694},{"id":"https://openalex.org/keywords/generative-ai","display_name":"generative AI","score":0.628000020980835},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7400000095367432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8593999743461609},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.5875999927520752},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4864000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46810001134872437},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.430400013923645},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C93983250","wikidata":"https://www.wikidata.org/wiki/Q795053","display_name":"Cost estimate","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.31310001015663147},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.2702000141143799}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2508.19807","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.19807","pdf_url":"https://arxiv.org/pdf/2508.19807","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.2508.19807","doi":"https://doi.org/10.48550/arxiv.2508.19807","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.19807","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.19807","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.19807","pdf_url":"https://arxiv.org/pdf/2508.19807","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Having":[0],"access":[1],"to":[2,13,22,84],"realistic":[3],"workloads":[4],"for":[5,24],"a":[6,54,58,104],"given":[7,55],"database":[8,60],"instance":[9],"is":[10],"extremely":[11],"important":[12],"enable":[14],"stress":[15],"and":[16,26,47,81],"vulnerability":[17],"testing,":[18],"as":[19,21],"well":[20],"optimize":[23],"cost":[25,32,51,95,106],"performance.":[27],"Recent":[28],"advances":[29],"in":[30,69],"learned":[31,94,105],"models":[33],"have":[34],"shown":[35],"that":[36,100],"when":[37,118],"enough":[38],"diverse":[39],"SQL":[40],"queries":[41,116],"are":[42],"available,":[43],"one":[44],"can":[45,102],"effectively":[46],"efficiently":[48],"predict":[49],"the":[50,78,89],"of":[52,92],"running":[53],"query":[56],"against":[57],"specific":[59],"engine.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,101],"describe":[66],"our":[67],"experience":[68],"exploiting":[70],"modern":[71],"synthetic":[72],"data":[73],"generation":[74,121],"techniques,":[75],"inspired":[76],"by":[77,110],"generative":[79],"AI":[80],"LLM":[82],"community,":[83],"create":[85],"high-quality":[86],"datasets":[87],"enabling":[88],"effective":[90],"training":[91,111],"such":[93],"models.":[96],"Initial":[97],"results":[98],"show":[99],"improve":[103],"model's":[107],"predictive":[108],"accuracy":[109],"it":[112],"with":[113],"45%":[114],"fewer":[115],"than":[117],"using":[119],"competitive":[120],"approaches.":[122]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}