{"id":"https://openalex.org/W4281384181","doi":"https://doi.org/10.1145/3533028.3533310","title":"dcbench","display_name":"dcbench","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4281384181","doi":"https://doi.org/10.1145/3533028.3533310"},"language":"en","primary_location":{"id":"doi:10.1145/3533028.3533310","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3533028.3533310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth Workshop on Data Management for End-To-End Machine Learning","raw_type":"proceedings-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/A5011478764","display_name":"Sabri Eyuboglu","orcid":"https://orcid.org/0000-0002-8412-0266"},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sabri Eyuboglu","raw_affiliation_strings":["Stanford"],"affiliations":[{"raw_affiliation_string":"Stanford","institution_ids":["https://openalex.org/I4210137306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025073517","display_name":"Bojan Karla\u0161","orcid":"https://orcid.org/0000-0002-6462-3579"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Bojan Karla\u0161","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103852640","display_name":"Christopher R\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher R\u00e9","raw_affiliation_strings":["Stanford"],"affiliations":[{"raw_affiliation_string":"Stanford","institution_ids":["https://openalex.org/I4210137306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383731","display_name":"Ce Zhang","orcid":"https://orcid.org/0000-0002-8105-7505"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ce Zhang","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005779176","display_name":"James Zou","orcid":"https://orcid.org/0000-0001-8880-4764"},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Zou","raw_affiliation_strings":["Stanford"],"affiliations":[{"raw_affiliation_string":"Stanford","institution_ids":["https://openalex.org/I4210137306"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5011478764"],"corresponding_institution_ids":["https://openalex.org/I4210137306"],"apc_list":null,"apc_paid":null,"fwci":1.9893,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88153733,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9987999796867371,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9987999796867371,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9973000288009644,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9922000169754028,"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/workflow","display_name":"Workflow","score":0.8871810436248779},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7701544761657715},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423226833343506},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6401908993721008},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4555581212043762},{"id":"https://openalex.org/keywords/workflow-management-system","display_name":"Workflow management system","score":0.4479128122329712},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4123762249946594},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.367467999458313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35847389698028564},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.22223114967346191},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.21987390518188477},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14671030640602112}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8871810436248779},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7701544761657715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423226833343506},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6401908993721008},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4555581212043762},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.4479128122329712},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4123762249946594},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.367467999458313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35847389698028564},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.22223114967346191},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21987390518188477},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14671030640602112},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3533028.3533310","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3533028.3533310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth Workshop on Data Management for End-To-End Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2548122763","https://openalex.org/W2998506323","https://openalex.org/W3008591352","https://openalex.org/W3043571714","https://openalex.org/W3100350094","https://openalex.org/W4243565423","https://openalex.org/W4287588535"],"related_works":["https://openalex.org/W2081035100","https://openalex.org/W1421698118","https://openalex.org/W2107464366","https://openalex.org/W1596279713","https://openalex.org/W2169936168","https://openalex.org/W1948034404","https://openalex.org/W122022082","https://openalex.org/W4210712782","https://openalex.org/W2355868926","https://openalex.org/W2137920171"],"abstract_inverted_index":{"The":[0],"development":[1],"workflow":[2,17,54],"for":[3,59,65,99,102],"today's":[4],"AI":[5,66,104],"applications":[6],"has":[7,55],"grown":[8],"far":[9],"beyond":[10],"the":[11,111,123],"standard":[12],"model":[13,24],"training":[14,36],"task.":[15],"This":[16,52],"typically":[18],"consists":[19],"of":[20,130],"various":[21],"data":[22],"and":[23,38,63,83,126],"management":[25],"tasks.":[26],"It":[27],"includes":[28],"a":[29,39,57,70,86,97,127],"\"data":[30],"cycle\"":[31,41],"aimed":[32,42],"at":[33,43],"producing":[34],"high-quality":[35],"data,":[37],"\"model":[40],"managing":[44],"trained":[45],"models":[46],"on":[47],"their":[48],"way":[49],"to":[50,79,89],"production.":[51],"broadened":[53],"opened":[56],"space":[58],"already":[60],"emerging":[61],"tools":[62,82],"systems":[64,101],"development.":[67,105],"However,":[68],"as":[69],"research":[71],"community,":[72],"we":[73,94,109,120],"are":[74],"still":[75],"missing":[76],"standardized":[77],"ways":[78],"evaluate":[80],"these":[81],"systems.":[84],"In":[85,106],"humble":[87],"effort":[88],"get":[90],"this":[91,107],"wheel":[92],"turning,":[93],"developed":[95],"dcbench,":[96,115],"benchmark":[98,117],"evaluating":[100],"data-centric":[103],"report,":[108],"present":[110],"main":[112],"ideas":[113],"behind":[114],"some":[116],"tasks":[118],"that":[119],"included":[121],"in":[122],"initial":[124],"release,":[125],"short":[128],"summary":[129],"its":[131],"implementation.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-05-25T00:00:00"}