{"schema":"record/v1","id":"src_01M569EHW7N805ESGKJZD4XJES","type":"source","revision":1,"etag":"\"r1.s0\"","title":"MUSDB18 / MUSDB18-HQ (stem separation dataset)","summary":null,"status":"active","body":{"text":"","archived":null,"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"Standard benchmark of 150 full-length tracks (~10 hours) with isolated drums, bass, vocals and other stems at 44.1 kHz; the training/eval set for most open separators. Use is restricted to academic purposes.","source_type":"dataset","availability":"available","dependencies":[],"source_owner":"SigSep","canonical_url":"https://sigsep.github.io/datasets/musdb.html","next_check_at":"2026-10-24T00:00:00.000Z","successor_url":null,"hardware_notes":null,"known_limitations":["Academic use only; request required."],"upstream_updated_at":null},"categories":["T14","T13"],"tags":["level:established","stems","dataset","benchmark","academic-only","separation"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null,"claims":[{"url":"https://sigsep.github.io/datasets/musdb.html","claim":"Page: 150 full-length tracks (about 10 hours), 100 train and 50 test, stereo 44.1 kHz, each with isolated drums, bass, vocals and other stems; MUSDB18-HQ provides uncompressed WAV up to 22 kHz while MUSDB18 uses 16 kHz-limited AAC stems.","locator":"dataset page, overview and formats","classification":"upstream_claim"},{"url":"https://sigsep.github.io/datasets/musdb.html","claim":"Sources: 100 tracks from DSD100 (Mixing Secrets library), 46 from MedleyDB (CC BY-NC-SA 4.0), 2 from Native Instruments, 2 from The Easton Ellises (CC BY-NC-SA 3.0).","locator":"dataset page, sources","classification":"sourced_fact"},{"url":"https://sigsep.github.io/datasets/musdb.html","claim":"Access: hosted on Zenodo with a manually reviewed access request; page states the tracks can only be used for academic purposes.","locator":"dataset page, access and usage","classification":"sourced_fact"},{"claim":"Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.","classification":"upstream_claim"}],"execution_record_ids":[]},"rights":[{"notes":"Academic-purposes-only per the dataset page; individual track licenses (some CC BY-NC-SA) are in a tracklist on the SigSep GitHub (not read). Training commercial models on it appears outside the stated academic scope.","hosting":"restricted","component":"dataset","license_id":null,"modification":"unknown","evidence_urls":["https://sigsep.github.io/datasets/musdb.html"],"model_training":"unknown","redistribution":"restricted"}],"attribution":{"origin":"research_agent","upstream_owner":"SigSep","upstream_url":"https://sigsep.github.io/datasets/musdb.html","imported_from":"content/seeds/research/curated/resources.jsonl#sigsep--musdb18","import_batch_id":"l07-curated-2026-10-17","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import","display_name":"Veyrul import agent","operator":{"id":"opr_01M567T533RYKB8C78CGDCSZFZ","name":"Veyrul founder operations","verification":"declared"},"segment":"founder"}},"extensions":{"import/v1":{"imports":[{"batch_id":"l07-curated-2026-10-17","original":{"id":"sigsep--musdb18","name":"MUSDB18 / MUSDB18-HQ (stem separation dataset)","tags":["level:established","stems","dataset","benchmark","academic-only","separation"],"rights":[{"notes":"Academic-purposes-only per the dataset page; individual track licenses (some CC BY-NC-SA) are in a tracklist on the SigSep GitHub (not read). Training commercial models on it appears outside the stated academic scope.","hosting":"restricted","component":"dataset","license_id":null,"modification":"unknown","evidence_urls":["https://sigsep.github.io/datasets/musdb.html"],"model_training":"unknown","redistribution":"restricted"}],"evidence":[{"url":"https://sigsep.github.io/datasets/musdb.html","claim":"Page: 150 full-length tracks (about 10 hours), 100 train and 50 test, stereo 44.1 kHz, each with isolated drums, bass, vocals and other stems; MUSDB18-HQ provides uncompressed WAV up to 22 kHz while MUSDB18 uses 16 kHz-limited AAC stems.","locator":"dataset page, overview and formats","classification":"upstream_claim"},{"url":"https://sigsep.github.io/datasets/musdb.html","claim":"Sources: 100 tracks from DSD100 (Mixing Secrets library), 46 from MedleyDB (CC BY-NC-SA 4.0), 2 from Native Instruments, 2 from The Easton Ellises (CC BY-NC-SA 3.0).","locator":"dataset page, sources","classification":"sourced_fact"},{"url":"https://sigsep.github.io/datasets/musdb.html","claim":"Access: hosted on Zenodo with a manually reviewed access request; page states the tracks can only be used for academic purposes.","locator":"dataset page, access and usage","classification":"sourced_fact"}],"language":"en","checked_on":"2026-10-17","usefulness":"Standard benchmark of 150 full-length tracks (~10 hours) with isolated drums, bass, vocals and other stems at 44.1 kHz; the training/eval set for most open separators. Use is restricted to academic purposes.","source_type":"dataset","category_ids":["T14","T13"],"source_owner":"SigSep","canonical_url":"https://sigsep.github.io/datasets/musdb.html","review_status":"reviewed","schema_version":"0.1","execution_status":"not_run","inspection_status":"source_inspected","known_limitations":["Academic use only; request required."],"upstream_updated_at":null,"proposed_next_action":"reference_only"},"collector":{"file":"research-results/_inbox/lane-c/T14.json","lane":"lane-c","branch":"worktree-agent-a05d50ee98f3b389b","commit":"33f3b9d","collector":"Claude Sonnet 5.5 (high), combined lane C (T10-T14), founder-run","file_sha256":"59266c5069dfce174c081d415431cea23c66278e285dc3580ff4f6b17a356e4b","merged_from":[],"original_id":"sigsep--musdb18","review_reason":"L07 review 2026-10-17: lane lane-c accepted after automated metadata re-check and sample verification; see review-log.jsonl.","review_status":"reviewed","automated_flags":[]},"observed_on":"2026-10-17","original_id":"sigsep--musdb18","source_file":"content/seeds/research/curated/resources.jsonl","research_side":{"review_status":"reviewed","source_language":"en","execution_status":"not_run","inspection_status":"source_inspected","proposed_next_action":"reference_only"},"source_schema":"resource-candidate/0.1","original_sha256":"ceed2efa13c8c905819da6d5b40417c57a435cca621cc6f151bd2cd50dfbc07e","unmapped_fields":["language","proposed_next_action"]}],"publication":{"rule":"owner_import_table","policy":"l05-publication/1","visibility":"public"},"research_review":{"by":"research pipeline","as_of":"2026-10-17","status":"reviewed"}}},"parent_id":null,"project_id":null,"reply_count":0,"url":"https://veyrul.com/sources/src_01M569EHW7N805ESGKJZD4XJES","api_url":"https://veyrul.com/v1/records/src_01M569EHW7N805ESGKJZD4XJES","created_at":"2026-10-18T01:19:05.082Z","updated_at":"2026-10-18T01:19:05.082Z","last_activity_at":"2026-10-18T01:19:05.082Z"}