{"id":"https://openalex.org/W7131086855","doi":"https://doi.org/10.1145/3785021.3787981","title":"Reproducibility Report for ACM SIGMOD 2025 Paper: 'PLM4NDV: Minimizing Data Access for Number of Distinct Values Estimation with Pre-trained Language Models'","display_name":"Reproducibility Report for ACM SIGMOD 2025 Paper: 'PLM4NDV: Minimizing Data Access for Number of Distinct Values Estimation with Pre-trained Language Models'","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W7131086855","doi":"https://doi.org/10.1145/3785021.3787981"},"language":null,"primary_location":{"id":"doi:10.1145/3785021.3787981","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785021.3787981","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":"Reproducibility Reports of the 2025 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3785021.3787981","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126602939","display_name":"Qihao Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihao Cheng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-5228-3835","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feng Yu","orcid":"https://orcid.org/0009-0007-2207-8465"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Feng Yu","raw_affiliation_strings":["National University of Singapore, Singapore City, Singapore"],"raw_orcid":"https://orcid.org/0009-0007-2207-8465","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore City, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126614684","display_name":"Xianghong Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianghong Xu","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2447-4107","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126582927","display_name":"Xiao He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao He","raw_affiliation_strings":["Bytedance, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7959-2157","affiliations":[{"raw_affiliation_string":"Bytedance, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126616522","display_name":"Tieying Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tieying Zhang","raw_affiliation_strings":["ByteDance, San Jose, USA"],"raw_orcid":"https://orcid.org/0009-0003-2250-5528","affiliations":[{"raw_affiliation_string":"ByteDance, San Jose, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.13519999384880066,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.13519999384880066,"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/T10028","display_name":"Topic Modeling","score":0.10300000011920929,"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/T11719","display_name":"Data Quality and Management","score":0.09839999675750732,"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/key","display_name":"Key (lock)","score":0.680899977684021},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.5232999920845032},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4043999910354614},{"id":"https://openalex.org/keywords/public-access","display_name":"Public access","score":0.3736000061035156},{"id":"https://openalex.org/keywords/reproducibility","display_name":"Reproducibility","score":0.27390000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8633000254631042},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.680899977684021},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.5232999920845032},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5078999996185303},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C2982933515","wikidata":"https://www.wikidata.org/wiki/Q104381823","display_name":"Public access","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3562000095844269},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26910001039505005},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C70000936","wikidata":"https://www.wikidata.org/wiki/Q4672467","display_name":"Access method","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3785021.3787981","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785021.3787981","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":"Reproducibility Reports of the 2025 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3785021.3787981","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785021.3787981","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":"Reproducibility Reports of the 2025 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4411403539"],"related_works":[],"abstract_inverted_index":{"We":[0,41],"successfully":[1],"reproduced":[2],"the":[3,13,25,35,39,43],"key":[4],"performance":[5],"results":[6],"that":[7,23],"presented":[8],"in":[9,38],"Tables~3":[10],"and~4":[11],"of":[12],"original":[14],"paper.":[15],"The":[16],"authors":[17],"provided":[18],"a":[19],"GitHub":[20],"repository.":[21],"https://github.com/bytedance/plm4ndv":[22],"includes":[24],"implementation,":[26],"detailed":[27],"build":[28],"and":[29,32,49],"execution":[30],"instructions,":[31],"links":[33],"to":[34],"datasets":[36],"used":[37],"experiments.":[40],"appreciate":[42],"authors'":[44],"assistance":[45],"with":[46],"environment":[47],"setup":[48],"debugging.":[50]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-24T00:00:00"}