{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/slakh2100","name":"Slakh2100","full_name":"Synthesized Lakh Dataset","description_markdown":"The Synthesized Lakh (Slakh) Dataset is a dataset for audio source separation that is synthesized from the Lakh MIDI Dataset v0.1 using professional-grade sample-based virtual instruments. This first release of Slakh, called **Slakh2100**, contains 2100 automatically mixed tracks and accompanying MIDI files synthesized using a professional-grade sampling engine. The tracks in Slakh2100 are split into training (1500 tracks), validation (375 tracks), and test (225 tracks) subsets, totaling 145 hours of mixtures.\n\nSource: [http://www.slakh.com/](http://www.slakh.com/)\nImage Source: [http://www.slakh.com/](http://www.slakh.com/)\nAudio Source: [http://www.slakh.com/](http://www.slakh.com/)","description_withheld":null,"homepage":"http://www.slakh.com/","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/cutting-music-source-separation-some-slakh-a","title":"Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity","first_author":"Ethan Manilow","url":null},"license":null,"modalities":[{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Midi","url":"/datasets/modality/midi"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Music Transcription","url":"/task/music-transcription","datasets_with_task":"/datasets/task/music-transcription"},{"name":"Data Augmentation","url":"/task/data-augmentation","datasets_with_task":"/datasets/task/data-augmentation"},{"name":"Music Source Separation","url":"/task/music-source-separation","datasets_with_task":"/datasets/task/music-source-separation"},{"name":"Multi-instrument Music Transcription","url":"/task/multi-instrument-music-transcription","datasets_with_task":"/datasets/task/multi-instrument-music-transcription"}],"languages":[],"variants":["Slakh2100"],"data_loaders":[],"num_papers_in_archive":38,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/music-transcription-on-slakh2100","task":"Music Transcription","dataset_variant":"Slakh2100","rows":6,"metrics":["note-level F-measure-no-offset (Fno)","Onset F1"],"first_row_in_archive_order":{"model":"YourMT3+ (YPTF.MoE+M)","paper":"/paper/yourmt3-multi-instrument-music-transcription","metrics":{"Onset F1":"84.56","note-level F-measure-no-offset (Fno)":"0.8456"},"code_links":[{"title":"mimbres/yourmt3","url":"https://github.com/mimbres/yourmt3"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-instrument-music-transcription-on","task":"Multi-instrument Music Transcription","dataset_variant":"Slakh2100","rows":5,"metrics":["Multi F1"],"first_row_in_archive_order":{"model":"YourMT3+ (YPTF.MoE+M)","paper":"/paper/yourmt3-multi-instrument-music-transcription","metrics":{"Multi F1":"74.84"},"code_links":[{"title":"mimbres/yourmt3","url":"https://github.com/mimbres/yourmt3"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/music-source-separation-on-slakh2100","task":"Music Source Separation","dataset_variant":"Slakh2100","rows":2,"metrics":["SDR (bass)","SDR (drums)","SI-SDRi (Bass)","Si-SDRi (Drums)","Si-SDRi (Guitar)","Si-SDRi (Piano)"],"first_row_in_archive_order":{"model":"LQ-VAE + Scalable Transformer","paper":"/paper/unsupervised-source-separation-via-bayesian","metrics":{"SDR (bass)":"7.42","SDR (drums)":"5.83"},"code_links":[{"title":"michelemancusi/LQVAE-separation","url":"https://github.com/michelemancusi/LQVAE-separation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":6,"of":6,"counts":{"papers_with_a_benchmark_row":6,"with_a_code_link":5,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":6,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/yourmt3-multi-instrument-music-transcription","slug":"yourmt3-multi-instrument-music-transcription","title":"YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation","date":"2024-07-05","arxiv_id":"2407.04822","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/the-chamber-ensemble-generator-limitless-high","slug":"the-chamber-ensemble-generator-limitless-high","title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","date":"2022-09-28","arxiv_id":"2209.14458","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["lukewys/chamber-ensemble-generator"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/the-chamber-ensemble-generator-limitless-high#ran","syntology_url":"https://syntology.ai/paper/2209.14458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.14458"}}}},{"paper":"/paper/jointist-joint-learning-for-multi-instrument","slug":"jointist-joint-learning-for-multi-instrument","title":"Jointist: Joint Learning for Multi-instrument Transcription and Its Applications","date":"2022-06-22","arxiv_id":"2206.10805","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-lightweight-instrument-agnostic-model-for","slug":"a-lightweight-instrument-agnostic-model-for","title":"A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation","date":"2022-03-18","arxiv_id":"2203.09893","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["spotify/basic-pitch"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-lightweight-instrument-agnostic-model-for#ran","syntology_url":"https://syntology.ai/paper/2203.09893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09893"}}}},{"paper":"/paper/mt3-multi-task-multitrack-music-transcription-1","slug":"mt3-multi-task-multitrack-music-transcription-1","title":"MT3: Multi-Task Multitrack Music Transcription","date":"2021-11-04","arxiv_id":"2111.03017","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["magenta/mt3"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mt3-multi-task-multitrack-music-transcription-1#ran","syntology_url":"https://syntology.ai/paper/2111.03017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03017"}}}},{"paper":"/paper/unsupervised-source-separation-via-bayesian","slug":"unsupervised-source-separation-via-bayesian","title":"Unsupervised Source Separation via Bayesian Inference in the Latent Domain","date":"2021-10-11","arxiv_id":"2110.05313","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/yourmt3-multi-instrument-music-transcription","slug":"yourmt3-multi-instrument-music-transcription","title":"YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation","date":"2024-07-05","arxiv_id":"2407.04822","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/the-chamber-ensemble-generator-limitless-high","slug":"the-chamber-ensemble-generator-limitless-high","title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","date":"2022-09-28","arxiv_id":"2209.14458","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["lukewys/chamber-ensemble-generator"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/the-chamber-ensemble-generator-limitless-high#ran","syntology_url":"https://syntology.ai/paper/2209.14458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.14458"}}}},{"paper":"/paper/jointist-joint-learning-for-multi-instrument","slug":"jointist-joint-learning-for-multi-instrument","title":"Jointist: Joint Learning for Multi-instrument Transcription and Its Applications","date":"2022-06-22","arxiv_id":"2206.10805","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-lightweight-instrument-agnostic-model-for","slug":"a-lightweight-instrument-agnostic-model-for","title":"A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation","date":"2022-03-18","arxiv_id":"2203.09893","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["spotify/basic-pitch"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-lightweight-instrument-agnostic-model-for#ran","syntology_url":"https://syntology.ai/paper/2203.09893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09893"}}}},{"paper":"/paper/mt3-multi-task-multitrack-music-transcription-1","slug":"mt3-multi-task-multitrack-music-transcription-1","title":"MT3: Multi-Task Multitrack Music Transcription","date":"2021-11-04","arxiv_id":"2111.03017","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["magenta/mt3"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mt3-multi-task-multitrack-music-transcription-1#ran","syntology_url":"https://syntology.ai/paper/2111.03017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03017"}}}},{"paper":"/paper/unsupervised-source-separation-via-bayesian","slug":"unsupervised-source-separation-via-bayesian","title":"Unsupervised Source Separation via Bayesian Inference in the Latent Domain","date":"2021-10-11","arxiv_id":"2110.05313","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/slakh2100/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/slakh2100/papers/ran/1","json":"/dataset/slakh2100/papers/ran/1.json","rows":2}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":3,"samples_harvested":22,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":15,"samples_ran_instrument_failed":0,"samples_unverified":7,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"ca268d1f52763210fe89adc2cce8d24c1ae37ef726fa0d62f0d40afee0f14bbc","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}