{"id":"https://openalex.org/W6930617179","doi":"https://doi.org/10.5281/zenodo.14889671","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":"2025-02-18","ids":{"openalex":"https://openalex.org/W6930617179","doi":"https://doi.org/10.5281/zenodo.14889671"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14889671","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14889671","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.14889671","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/metadata","display_name":"Metadata","score":0.8331000208854675},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.7749999761581421},{"id":"https://openalex.org/keywords/public-domain","display_name":"Public domain","score":0.5410000085830688},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.534500002861023},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.42730000615119934},{"id":"https://openalex.org/keywords/visibility","display_name":"Visibility","score":0.39469999074935913}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8331000208854675},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878999710083008},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.7749999761581421},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.5410000085830688},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.534500002861023},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4410000145435333},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.42730000615119934},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.39660000801086426},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C2225880","wikidata":"https://www.wikidata.org/wiki/Q579047","display_name":"Journaling file system","level":3,"score":0.34630000591278076},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2953000068664551},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14889671","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14889671","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.14889671","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14889671","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,72,97,111],"introduce":[1],"PDMX:":[2],"a":[3,45],"Public":[4],"Domain":[5],"MusicXML":[6,151],"dataset":[7],"for":[8,16,23,127],"symbolic":[9],"music":[10,155],"processing.":[11],"Refer":[12],"to":[13,75,146,161,185],"our":[14,20,29],"paper":[15,30],"more":[17],"information,":[18],"and":[19,56,138,153,176,188,193,209],"GitHub":[21],"repository":[22],"any":[24],"code-related":[25],"details.":[26],"Please":[27],"cite":[28],"if":[31],"you":[32],"use":[33,38],"this":[34,87],"dataset.":[35],"Upon":[36],"further":[37],"of":[39,61,109,117,164,166,200],"the":[40,48,53,57,62,78,90,106,114,136,148,162,167,191],"PDMX":[41,118,201],"dataset,":[42],"we":[43,132,143],"discovered":[44],"discrepancy":[46],"between":[47],"public-facing":[49],"copyright":[50,59],"metadata":[51,139,194],"on":[52,84],"MuseScore":[54,63,91,169],"website":[55,92],"internal":[58,103],"data":[60],"files":[64,100,157,178],"themselves,":[65],"which":[66],"affected":[67],"31,221":[68],"(12.29%":[69],"of)":[70],"songs.":[71],"have":[73,98],"decided":[74],"proceed":[76],"with":[77,101,205],"former":[79],"given":[80],"its":[81,94],"public":[82],"visibility":[83],"Musescore":[85],"(i.e.":[86],"is":[88],"what":[89],"presents":[93],"users":[95],"with).":[96],"noted":[99],"conflicting":[102],"licenses":[104],"in":[105,130],"license_conflict":[107],"column":[108],"PDMX.":[110],"recommend":[112],"using":[113],"no_license_conflict":[115],"subset":[116,199],"(which":[119],"still":[120],"includes":[121],"222,856":[122],"songs)":[123],"moving":[124],"forward.":[125],"Additionally,":[126],"each":[128],"song":[129],"PDMX,":[131],"not":[133,182],"only":[134,189],"provide":[135],"MusicRender":[137,192],"JSON":[140,195],"files,":[141,170],"but":[142],"also":[144],"try":[145],"include":[147,190],"associated":[149,174,207],"compressed":[150],"(MXL)":[152],"sheet":[154],"(PDF)":[156],"when":[158],"available.":[159],"Due":[160],"corruption":[163],"42":[165],"original":[168],"these":[171,186],"songs":[172,204],"lack":[173],"MXL":[175,208],"PDF":[177,210],"(since":[179],"they":[180],"could":[181],"be":[183],"converted":[184],"formats)":[187],"files.":[196,211],"The":[197],"valid_mxl_pdf":[198],"describes":[202],"all":[203],"valid":[206]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
