{"id":"https://openalex.org/W7225831065","doi":"https://doi.org/10.21203/rs.3.rs-11083018/v1","title":"StemGround: Source-Interventional Auditing and Selective Response Alignment for Instrument Grounding in Music Foundation Model Readouts","display_name":"StemGround: Source-Interventional Auditing and Selective Response Alignment for Instrument Grounding in Music Foundation Model Readouts","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225831065","doi":"https://doi.org/10.21203/rs.3.rs-11083018/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11083018/v1","doi":"https://doi.org/10.21203/rs.3.rs-11083018/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11083018/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21203/rs.3.rs-11083018/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161474840","display_name":"Chao Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63354593","display_name":"Sichuan Normal University","ror":"https://ror.org/043dxc061","country_code":"CN","type":"education","lineage":["https://openalex.org/I63354593"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Guo","raw_affiliation_strings":["Sichuan Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan Normal University","institution_ids":["https://openalex.org/I63354593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100619907","display_name":"Junxiang Wang","orcid":"https://orcid.org/0009-0004-3484-0283","observed_orcids":["https://orcid.org/0009-0004-3484-0283","https://orcid.org/0000-0001-9612-921X"]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junxiang Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100619907"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"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":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"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"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6376000046730042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6036999821662903},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.5670999884605408},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5026000142097473},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42719998955726624},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4189999997615814},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36160001158714294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C96608239","wikidata":"https://www.wikidata.org/wiki/Q1199823","display_name":"Statistical power","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11083018/v1","doi":"https://doi.org/10.21203/rs.3.rs-11083018/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11083018/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11083018/v1","doi":"https://doi.org/10.21203/rs.3.rs-11083018/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11083018/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"An":[1],"accurate":[2],"instrument":[3,9],"tag":[4],"can":[5],"persist":[6],"after":[7],"the":[8,80,123],"is":[10],"removed,":[11],"exposing":[12],"a":[13,75,90,196,206],"distinction":[14,26],"between":[15,211],"recognition":[16,221],"and":[17,27,41,49,60,89,106,151,169,188,199,208,215,223],"source":[18,213],"grounding.":[19],"We":[20,84],"introduce":[21],"StemGround":[22,203],"to":[23,141],"measure":[24],"this":[25],"train":[28],"source-aligned":[29],"readouts":[30],"using":[31],"ground-truth":[32],"multitrack":[33],"recordings.":[34],"Same-recording":[35],"target":[36],"removal,":[37],"ordered":[38],"gain":[39],"changes,":[40],"target-by-context":[42],"interventions":[43,135],"specify":[44],"which":[45,50],"outputs":[46],"should":[47,53],"change":[48],"label":[51],"truths":[52],"be":[54],"preserved.":[55],"Loudness":[56],"matching,":[57],"whole-mixture":[58],"gain,":[59],"unrelated-source":[61],"controls":[62],"test":[63],"acoustic":[64],"alternatives.":[65],"Selective":[66],"response":[67],"alignment":[68],"(SRA)":[69],"implements":[70],"these":[71],"require-":[72],"ments":[73],"through":[74],"263,171-parameter":[76],"residual":[77],"head,":[78],"leaving":[79],"music":[81],"encoder":[82],"fixed.":[83],"audit":[85],"MERT,":[86],"MuQ,":[87],"MusicFM,":[88],"MuQ-MuLan":[91],"zero-shot":[92],"reference,":[93],"then":[94],"compare":[95],"SRA":[96,144],"with":[97,133],"an":[98],"ordinary":[99,142],"head":[100],"matched":[101],"for":[102],"capacity,":[103],"input":[104],"data,":[105],"selected":[107],"training":[108],"updates.":[109],"Both":[110],"heads":[111],"receive":[112],"labeled":[113],"interven-":[114],"tions.":[115],"Improvements":[116],"on":[117,122],"artist-disjoint":[118],"MoisesDB":[119],"evaluation":[120],"replicate":[121],"frozen":[124],"MUSDB18":[125],"official":[126],"test:":[127],"50":[128],"tracks":[129],"from":[130,219],"46":[131],"artists,":[132],"13,361":[134],"across":[136],"49":[137],"eligible":[138],"tracks.":[139],"Relative":[140],"training,":[143],"increases":[145],"standardized":[146,170],"target-removal":[147,197],"efect":[148,173],"by":[149,154,161,167,174],"0.664":[150],"dose-order":[152],"consistency":[153],"0.043.":[155],"It":[156],"reduces":[157],"target-absent":[158,171],"false":[159,165],"positives":[160,166],"0.161,":[162],"net":[163],"context-induced":[164],"0.300,":[168],"context":[172],"0.756.":[175],"All":[176],"five":[177],"endpoint-wise":[178],"95%":[179],"artist-cluster":[180],"con-":[181],"fidence":[182],"intervals":[183],"favor":[184],"SRA;":[185],"cross-model":[186],"natural-task":[187],"of-target":[189],"noninferiority":[190],"criteria":[191],"are":[192],"met.":[193],"MusicFM":[194],"exhibits":[195],"trade-of,":[198],"probability":[200,224],"reliability":[201],"worsens.":[202],"estab-":[204],"lishes":[205],"measurable":[207],"trainable":[209],"connection":[210],"physical":[212],"changes":[214],"instrument-label":[216],"responses,":[217],"distinct":[218],"natural":[220],"accuracy":[222],"calibration.":[225]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}