{"id":"https://openalex.org/W7108599929","doi":"https://doi.org/10.5281/zenodo.17811316","title":"On the de-duplication of the Lakh MIDI dataset","display_name":"On the de-duplication of the Lakh MIDI dataset","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108599929","doi":"https://doi.org/10.5281/zenodo.17811316"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811316","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811316","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811316","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Eunjin Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Eunjin Choi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hyerin Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyerin Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiwoo Ryu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiwoo Ryu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Juhan Nam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Dasaem Jeong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dasaem Jeong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.6210765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9560999870300293,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9560999870300293,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.009200000204145908,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13996","display_name":"Diverse Musicological Studies","score":0.004000000189989805,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.8508999943733215},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5408999919891357},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5013999938964844},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4968999922275543},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4171999990940094},{"id":"https://openalex.org/keywords/lakh","display_name":"Lakh","score":0.3752000033855438}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.8508999943733215},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6777999997138977},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5408999919891357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5084999799728394},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4968999922275543},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39980000257492065},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39320001006126404},{"id":"https://openalex.org/C82896369","wikidata":"https://www.wikidata.org/wiki/Q949243","display_name":"Lakh","level":3,"score":0.3752000033855438},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32589998841285706},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3255999982357025},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29660001397132874},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.27720001339912415},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811316","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811316","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811316","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811316","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4174967110157013}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"A":[0],"large-scale":[1],"dataset":[2,61,77],"is":[3],"essential":[4],"for":[5,105,144],"training":[6,53],"a":[7,118,150,163],"well-generalized":[8],"deep":[9],"learning":[10],"model.":[11],"Most":[12],"such":[13,50],"datasets":[14],"are":[15,130],"collected":[16],"via":[17],"scraping":[18],"from":[19,36,55],"various":[20,156],"internet":[21],"sources,":[22],"inevitably":[23],"introducing":[24],"duplicated":[25,106],"data.":[26],"In":[27],"the":[28,70,76,87,93,101,110,115,127],"symbolic":[29,94,140],"music":[30,95,141],"domain,":[31],"these":[32],"duplicates":[33],"often":[34],"come":[35],"multiple":[37],"user":[38],"arrangements":[39],"and":[40,99,138,146],"metadata":[41],"changes":[42],"after":[43],"simple":[44],"editing.":[45],"However,":[46],"despite":[47],"critical":[48],"issues":[49,79],"as":[51,117],"unreliable":[52],"evaluation":[54],"data":[56],"leakage":[57],"during":[58],"random":[59],"splitting,":[60],"duplication":[62,78],"has":[63],"yet":[64],"to":[65,158],"be":[66],"discussed":[67],"seriously":[68],"in":[69,92,122,182],"MIR":[71],"community.":[72],"This":[73],"study":[74],"investigates":[75],"regarding":[80],"Lakh":[81],"MIDI":[82,112],"Dataset":[83],"(LMD),":[84],"one":[85],"of":[86,114,126,170,173],"largest":[88],"publicly":[89],"available":[90],"sources":[91],"domain.":[96],"To":[97],"find":[98,159],"evaluate":[100],"best":[102],"retrieval":[103,142],"method":[104],"data,":[107],"we":[108,165],"employed":[109],"Clean":[111],"subset":[113],"LMD":[116],"benchmark":[119],"test":[120],"set,":[121],"which":[123,175],"different":[124,168],"versions":[125,169],"same":[128],"songs":[129],"grouped":[131],"together.":[132],"We":[133],"first":[134],"evaluated":[135],"rule-based":[136],"approaches":[137],"previous":[139],"models":[143],"de-duplication":[145],"also":[147],"investigated":[148],"with":[149,155],"contrastive":[151],"learning-based":[152],"BERT":[153],"model":[154],"augmentations":[157],"duplicate":[160],"files.":[161,188],"As":[162],"result,":[164],"propose":[166],"three":[167],"filtered":[171],"list":[172],"LMD,":[174],"filters":[176],"out":[177],"at":[178],"least":[179],"38,134":[180],"samples":[181],"most":[183],"conservative":[184],"settings":[185],"among":[186],"178,561":[187]},"counts_by_year":[],"updated_date":"2025-12-05T23:25:22.460635","created_date":"2025-12-05T00:00:00"}