{"id":"https://openalex.org/W7162400332","doi":"https://doi.org/10.1145/3788853.3801608","title":"BDI-Kit Demo: A Toolkit for Programmable and Conversational Data Harmonization","display_name":"BDI-Kit Demo: A Toolkit for Programmable and Conversational Data Harmonization","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162400332","doi":"https://doi.org/10.1145/3788853.3801608"},"language":null,"primary_location":{"id":"doi:10.1145/3788853.3801608","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788853.3801608","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":"Companion of the International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3788853.3801608","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125737123","display_name":"Roque Lopez","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roque Lopez","raw_affiliation_strings":["New York University, New York City, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-3484-1783","affiliations":[{"raw_affiliation_string":"New York University, New York City, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564223","display_name":"Yurong Liu","orcid":"https://orcid.org/0000-0002-7974-9449"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yurong Liu","raw_affiliation_strings":["New York University, New York City, NY, USA"],"raw_orcid":"https://orcid.org/0009-0007-9455-7254","affiliations":[{"raw_affiliation_string":"New York University, New York City, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137025937","display_name":"Christos Koutras","orcid":"https://orcid.org/0000-0003-3015-154X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christos Koutras","raw_affiliation_strings":["New York University, New York City, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-3015-154X","affiliations":[{"raw_affiliation_string":"New York University, New York City, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006773757","display_name":"Juliana Freire","orcid":"https://orcid.org/0000-0003-3915-7075"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juliana Freire","raw_affiliation_strings":["New York University, New York City, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-3915-7075","affiliations":[{"raw_affiliation_string":"New York University, New York City, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84166975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"94","last_page":"97"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.42419999837875366,"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":0.42419999837875366,"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":0.0502999983727932,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.03500000014901161,"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/standardization","display_name":"Standardization","score":0.2745000123977661},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27410000562667847},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.26809999346733093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692300021648407},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.34209999442100525},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29120001196861267},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2858999967575073},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2378000020980835},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.225600004196167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3788853.3801608","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788853.3801608","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":"Companion of the International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3788853.3801608","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788853.3801608","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":"Companion of the International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2140116426","https://openalex.org/W2889003264","https://openalex.org/W3006211741","https://openalex.org/W3174181645","https://openalex.org/W3199725740","https://openalex.org/W4385738280","https://openalex.org/W4385796046","https://openalex.org/W4413943454"],"related_works":[],"abstract_inverted_index":{"Data":[0],"harmonization":[1,46],"remains":[2],"a":[3,39,83],"major":[4],"bottleneck":[5],"for":[6,24],"integrative":[7],"analysis":[8],"due":[9],"to":[10,35,44,57,72,102,122],"heterogeneity":[11],"in":[12,119],"schemas,":[13],"value":[14,27,80],"representations,":[15],"and":[16,26,49,76,79,90,109,112,126],"domain-specific":[17],"conventions.":[18],"BDI-Kit":[19,71],"provides":[20],"an":[21,50],"extensible":[22],"toolkit":[23],"schema":[25,78],"matching.":[28],"It":[29],"exposes":[30],"two":[31,95],"complementary":[32],"interfaces":[33],"tailored":[34],"different":[36],"user":[37],"needs:":[38],"Python":[40,100],"API":[41,101],"enabling":[42],"developers":[43],"construct":[45],"pipelines":[47],"programmatically,":[48],"AI-assisted":[51,88],"chat":[52],"interface":[53],"allowing":[54],"domain":[55],"experts":[56],"harmonize":[58],"data":[59],"through":[60,82],"natural":[61,120],"language":[62,121],"dialogue.":[63],"This":[64],"demonstration":[65],"showcases":[66],"how":[67],"users":[68],"interact":[69],"with":[70,115],"iteratively":[73,127],"explore,":[74],"validate,":[75],"refine":[77,128],"matches":[81],"combination":[84],"of":[85],"automated":[86],"matching,":[87],"reasoning,":[89],"user-driven":[91],"refinement.":[92],"We":[93],"present":[94],"scenarios:":[96],"(i)":[97],"using":[98],"the":[99,116,132],"programmatically":[103],"compose":[104],"primitives,":[105],"examine":[106],"intermediate":[107],"outputs,":[108],"reuse":[110],"transformations;":[111],"(ii)":[113],"conversing":[114],"AI":[117],"assistant":[118],"access":[123],"BDI-Kit's":[124],"capabilities":[125],"outputs":[129],"based":[130],"on":[131],"assistant's":[133],"suggestions.":[134]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-27T00:00:00"}
