{"id":"https://openalex.org/W4399397688","doi":"https://doi.org/10.1145/3665601.3669846","title":"CMDBench: A Benchmark for Coarse-to-fine Multimodal Data Discovery in Compound AI Systems","display_name":"CMDBench: A Benchmark for Coarse-to-fine Multimodal Data Discovery in Compound AI Systems","publication_year":2024,"publication_date":"2024-06-07","ids":{"openalex":"https://openalex.org/W4399397688","doi":"https://doi.org/10.1145/3665601.3669846"},"language":"en","primary_location":{"id":"doi:10.1145/3665601.3669846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3665601.3669846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Governance, Understanding and Integration of Data for Effective and Responsible AI","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.00583","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yanlin Feng","orcid":"https://orcid.org/0009-0006-7696-9020"},"institutions":[{"id":"https://openalex.org/I4210107479","display_name":"Paragon Genomics (United States)","ror":"https://ror.org/01gjgcg03","country_code":"US","type":"company","lineage":["https://openalex.org/I4210107479"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanlin Feng","raw_affiliation_strings":["Megagon Labs, USA","; Eser Kandogan, Megagon Labs, USA,","Megagon Labs, Japan ESER KANDOGAN, Megagon Labs, USA","; Sajjadur Rahman, Megagon Labs, USA,","Megagon Labs, Japan","Megagon Labs, USA,","Megagon Labs, Japan,"],"raw_orcid":"https://orcid.org/0009-0006-7696-9020","affiliations":[{"raw_affiliation_string":"Megagon Labs, USA","institution_ids":[]},{"raw_affiliation_string":"; Eser Kandogan, Megagon Labs, USA,","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, Japan ESER KANDOGAN, Megagon Labs, USA","institution_ids":[]},{"raw_affiliation_string":"; Sajjadur Rahman, Megagon Labs, USA,","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, Japan","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, USA,","institution_ids":["https://openalex.org/I4210107479"]},{"raw_affiliation_string":"Megagon Labs, Japan,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040390469","display_name":"Sajjadur Rahman","orcid":"https://orcid.org/0000-0003-4210-1582"},"institutions":[{"id":"https://openalex.org/I4210107479","display_name":"Paragon Genomics (United States)","ror":"https://ror.org/01gjgcg03","country_code":"US","type":"company","lineage":["https://openalex.org/I4210107479"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sajjadur Rahman","raw_affiliation_strings":["Megagon Labs, USA","Megagon Labs, Japan ESER KANDOGAN, Megagon Labs, USA","Megagon Labs, Japan,","Megagon Labs, Japan","; Eser Kandogan, Megagon Labs, USA,","Megagon Labs, USA,","; Sajjadur Rahman, Megagon Labs, USA,"],"raw_orcid":"https://orcid.org/0000-0003-4210-1582","affiliations":[{"raw_affiliation_string":"Megagon Labs, USA","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, Japan ESER KANDOGAN, Megagon Labs, USA","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, Japan,","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, Japan","institution_ids":[]},{"raw_affiliation_string":"; Eser Kandogan, Megagon Labs, USA,","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, USA,","institution_ids":["https://openalex.org/I4210107479"]},{"raw_affiliation_string":"; Sajjadur Rahman, Megagon Labs, USA,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048599697","display_name":"Aaron Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107479","display_name":"Paragon Genomics (United States)","ror":"https://ror.org/01gjgcg03","country_code":"US","type":"company","lineage":["https://openalex.org/I4210107479"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron Feng","raw_affiliation_strings":["Megagon Labs, Japan","Megagon Labs, Japan ESER KANDOGAN, Megagon Labs, USA","; Sajjadur Rahman, Megagon Labs, USA,","Megagon Labs, Japan,","Megagon Labs, USA","Megagon Labs, USA,","; Eser Kandogan, Megagon Labs, USA,"],"raw_orcid":"https://orcid.org/0009-0008-2918-1462","affiliations":[{"raw_affiliation_string":"Megagon Labs, Japan","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, Japan ESER KANDOGAN, Megagon Labs, USA","institution_ids":[]},{"raw_affiliation_string":"; Sajjadur Rahman, Megagon Labs, USA,","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, Japan,","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, USA","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, USA,","institution_ids":["https://openalex.org/I4210107479"]},{"raw_affiliation_string":"; Eser Kandogan, Megagon Labs, USA,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038230353","display_name":"Vincent Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107479","display_name":"Paragon Genomics (United States)","ror":"https://ror.org/01gjgcg03","country_code":"US","type":"company","lineage":["https://openalex.org/I4210107479"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent Chen","raw_affiliation_strings":["Megagon Labs, Japan","Megagon Labs, Japan ESER KANDOGAN, Megagon Labs, USA","Megagon Labs, Japan,","; Sajjadur Rahman, Megagon Labs, USA,","Megagon Labs, USA,","; Eser Kandogan, Megagon Labs, USA,","Megagon Labs, USA"],"raw_orcid":"https://orcid.org/0009-0007-9111-2401","affiliations":[{"raw_affiliation_string":"Megagon Labs, Japan","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, Japan ESER KANDOGAN, Megagon Labs, USA","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, Japan,","institution_ids":[]},{"raw_affiliation_string":"; Sajjadur Rahman, Megagon Labs, USA,","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, USA,","institution_ids":["https://openalex.org/I4210107479"]},{"raw_affiliation_string":"; Eser Kandogan, Megagon Labs, USA,","institution_ids":[]},{"raw_affiliation_string":"Megagon Labs, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012111319","display_name":"Eser Kandogan","orcid":"https://orcid.org/0009-0004-3509-5502"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eser Kandogan","raw_affiliation_strings":["Megagon Labs, USA"],"raw_orcid":"https://orcid.org/0009-0004-3509-5502","affiliations":[{"raw_affiliation_string":"Megagon Labs, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9164,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78063421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9994000196456909,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.7935237884521484},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6302814483642578},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5668851137161255},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5515173673629761},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5004637241363525},{"id":"https://openalex.org/keywords/enterprise-data-management","display_name":"Enterprise data management","score":0.4434787333011627},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.42064934968948364},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41952720284461975},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.347179114818573},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.2532704174518585},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18795570731163025},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.1153188943862915},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09071990847587585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7935237884521484},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6302814483642578},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5668851137161255},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5515173673629761},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5004637241363525},{"id":"https://openalex.org/C136227091","wikidata":"https://www.wikidata.org/wiki/Q5380376","display_name":"Enterprise data management","level":3,"score":0.4434787333011627},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42064934968948364},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41952720284461975},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.347179114818573},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2532704174518585},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18795570731163025},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.1153188943862915},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09071990847587585},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C27295321","wikidata":"https://www.wikidata.org/wiki/Q831795","display_name":"Enterprise information system","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3665601.3669846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3665601.3669846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Governance, Understanding and Integration of Data for Effective and Responsible AI","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.00583","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.00583","pdf_url":"https://arxiv.org/pdf/2406.00583","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.00583","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.00583","pdf_url":"https://arxiv.org/pdf/2406.00583","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399397688.pdf","grobid_xml":"https://content.openalex.org/works/W4399397688.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2072627547","https://openalex.org/W2075418818","https://openalex.org/W2080133951","https://openalex.org/W2106743565","https://openalex.org/W2162020046","https://openalex.org/W2469798230","https://openalex.org/W2584261443","https://openalex.org/W2804776208","https://openalex.org/W2889787757","https://openalex.org/W2912924812","https://openalex.org/W2954268688","https://openalex.org/W2963339397","https://openalex.org/W3027879771","https://openalex.org/W3097986428","https://openalex.org/W3169283738","https://openalex.org/W3172335055","https://openalex.org/W4252076394","https://openalex.org/W4285147034","https://openalex.org/W4375928372","https://openalex.org/W4380433117","https://openalex.org/W4386123414","https://openalex.org/W4389910919","https://openalex.org/W4391156274"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W1943883986","https://openalex.org/W2137701185"],"abstract_inverted_index":{"Compound":[0],"AI":[1,27],"systems":[2,31],"(CASs)":[3],"that":[4,57],"employ":[5],"LLMs":[6],"as":[7],"agents":[8,225],"to":[9,35,51,81,163,171,217,221],"accomplish":[10],"knowledge-intensive":[11],"tasks":[12,162],"via":[13],"interactions":[14],"with":[15],"tools":[16],"and":[17,26,73,101,151,159,174,178,209,226],"data":[18,41,45,54,68,84,93,104,122,127,145,169,176,188,207],"retrievers":[19,128,227],"have":[20,32,59],"garnered":[21],"significant":[22],"interest":[23],"within":[24,75,131],"database":[25],"communities.":[28],"While":[29],"these":[30],"the":[33,52,62,88,121,141,185,215],"potential":[34],"supplement":[36],"typical":[37],"analysis":[38],"workflows":[39],"of":[40,66,103,108,125,143,187,231],"analysts":[42,58],"in":[43,129,153,198],"enterprise":[44,144,234],"platforms,":[46],"unfortunately,":[47],"CASs":[48,109,130,232],"are":[49],"subject":[50],"same":[53],"discovery":[55,94,123,177],"challenges":[56],"encountered":[60],"over":[61,167,233],"years":[63],"\u2014":[64,155,170,195,203],"silos":[65],"multimodal":[67,126],"sources,":[69,208],"created":[70],"across":[71,204],"teams":[72],"departments":[74],"an":[76],"organization,":[77],"make":[78],"it":[79],"difficult":[80],"identify":[82,222],"appropriate":[83,223],"sources":[85],"for":[86,228],"accomplishing":[87],"task":[89,114,179,193,199,210],"at":[90],"hand.":[91],"Existing":[92],"benchmarks":[95,107,152],"do":[96],"not":[97],"model":[98],"such":[99],"multimodality":[100],"multiplicity":[102],"sources.":[105],"Moreover,":[106],"prioritize":[110],"only":[111],"evaluating":[112,120],"end-to-end":[113],"performance.":[115,181],"To":[116],"catalyze":[117],"research":[118],"on":[119,191,201],"performance":[124,194],"a":[132,138],"real-world":[133],"setting,":[134],"we":[135],"propose":[136],"CMDBench,":[137],"benchmark":[139],"modeling":[140],"complexity":[142],"platforms.":[146],"We":[147],"adapt":[148],"existing":[149],"datasets":[150],"open-domain":[154],"from":[156],"question":[157],"answering":[158],"complex":[160],"reasoning":[161],"natural":[164],"language":[165],"querying":[166],"structured":[168],"evaluate":[172],"coarse-":[173],"fine-grained":[175],"execution":[180,230],"Our":[182],"experiments":[183],"reveal":[184],"impact":[186],"retriever":[189],"design":[190],"downstream":[192],"46%":[196],"drop":[197],"accuracy":[200],"average":[202],"various":[205],"modalities,":[206],"difficulty.":[211],"The":[212],"results":[213],"indicate":[214],"need":[216],"develop":[218],"optimization":[219],"strategies":[220],"LLM":[224],"efficient":[229],"data.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2024-06-07T00:00:00"}