{"id":"https://openalex.org/W6949540800","doi":"https://doi.org/10.5281/zenodo.15571083","title":"PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processing","display_name":"PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processing","publication_year":2025,"publication_date":"2025-06-01","ids":{"openalex":"https://openalex.org/W6949540800","doi":"https://doi.org/10.5281/zenodo.15571083"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.15571083","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15571083","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":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.15571083","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Long, Phillip","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Long, Phillip","raw_affiliation_strings":["University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Novack, Zachary","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Novack, Zachary","raw_affiliation_strings":["University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":null,"display_name":"McAuley, Julian","orcid":"https://orcid.org/0000-0003-0955-7588"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"McAuley, Julian","raw_affiliation_strings":["University of California, San Diego"],"raw_orcid":"https://orcid.org/0000-0003-0955-7588","affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":null,"display_name":"Berg-Kirkpatrick, Taylor","orcid":"https://orcid.org/0000-0002-1283-4075"},"institutions":[{"id":"https://openalex.org/I4210140792","display_name":"Universidad Cat\u00f3lica Santo Domingo","ror":"https://ror.org/04ytq6y86","country_code":"DO","type":"education","lineage":["https://openalex.org/I4210140792"]}],"countries":["DO"],"is_corresponding":false,"raw_author_name":"Berg-Kirkpatrick, Taylor","raw_affiliation_strings":["UCSD"],"raw_orcid":"https://orcid.org/0000-0002-1283-4075","affiliations":[{"raw_affiliation_string":"UCSD","institution_ids":["https://openalex.org/I4210140792"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.8568999767303467},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8072999715805054},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5257999897003174},{"id":"https://openalex.org/keywords/public-domain","display_name":"Public domain","score":0.5059999823570251},{"id":"https://openalex.org/keywords/unicode","display_name":"Unicode","score":0.3953999876976013},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.38609999418258667}],"concepts":[{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.8568999767303467},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8072999715805054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7736999988555908},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5414000153541565},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5257999897003174},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4722000062465668},{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.38609999418258667},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2565000057220459},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.15571083","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15571083","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":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.15571083","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15571083","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":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,83,108,122],"introduce":[1],"PDMX:":[2],"a":[3,56],"Public":[4],"Domain":[5],"MusicXML":[6,162],"dataset":[7,40],"for":[8,16,23,44,138],"symbolic":[9],"music":[10,165],"processing.":[11],"Refer":[12],"to":[13,86,157,174,196],"our":[14,20,30,33,42],"paper":[15,31,35],"more":[17,45],"information,":[18],"and":[19,32,67,149,167,199,204],"GitHub":[21,43],"repository":[22],"any":[24],"code-related":[25],"details.":[26],"Please":[27],"cite":[28],"both":[29],"collaborators'":[34],"if":[36],"you":[37],"use":[38,49],"this":[39,98],"(see":[41],"information).":[46],"Upon":[47],"further":[48],"of":[50,72,120,128,177,179,211],"the":[51,59,64,68,73,89,101,117,125,147,159,175,180,202,214],"PDMX":[52,129,212],"dataset,":[53],"we":[54,143,154],"discovered":[55],"discrepancy":[57],"between":[58],"public-facing":[60],"copyright":[61,70],"metadata":[62,150,205],"on":[63,95],"MuseScore":[65,74,102,182],"website":[66,103],"internal":[69,114],"data":[71],"files":[75,111,170,189,219],"themselves,":[76],"which":[77],"affected":[78],"31,221":[79],"(12.29%":[80],"of)":[81],"songs.":[82],"have":[84,109],"decided":[85],"proceed":[87],"with":[88,112],"former":[90],"given":[91],"its":[92,105],"public":[93],"visibility":[94],"Musescore":[96],"(i.e.":[97],"is":[99],"what":[100],"presents":[104],"users":[106],"with).":[107],"noted":[110],"conflicting":[113],"licenses":[115],"in":[116,141],"license_conflict":[118],"column":[119],"PDMX.":[121],"recommend":[123],"using":[124],"no_license_conflict":[126],"subset":[127,210],"(which":[130],"still":[131],"includes":[132],"222,856":[133],"songs)":[134],"moving":[135],"forward.":[136],"Additionally,":[137],"each":[139],"song":[140],"PDMX,":[142],"not":[144,193],"only":[145,200],"provide":[146],"MusicRender":[148,203],"JSON":[151,206],"files,":[152,183],"but":[153],"also":[155],"try":[156],"include":[158,201],"associated":[160,188,218],"compressed":[161],"(MXL),":[163],"sheet":[164],"(PDF),":[166],"MIDI":[168],"(MID)":[169],"when":[171],"available.":[172],"Due":[173],"corruption":[176],"42":[178],"original":[181],"these":[184],"songs":[185,215],"lack":[186],"those":[187,197],"(since":[190],"they":[191],"could":[192],"be":[194],"converted":[195],"formats)":[198],"files.":[207],"The":[208],"all_valid":[209],"describes":[213],"where":[216],"all":[217],"are":[220],"valid.":[221]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
