{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G3563W6LNRKYLJ72RHXWCCTPLA","short_pith_number":"pith:G3563W6L","schema_version":"1.0","canonical_sha256":"36fbeddbcb6c5585a7fa89ef610a6f58164b38da56c6595a5d3e73ccd41d2ceb","source":{"kind":"arxiv","id":"2608.01093","version":1},"attestation_state":"computed","paper":{"title":"Separate-and-Detect: Unified Drum Transcription and Stem Generation via Latent Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Bo-Yu Chen, Chih-Cheng Chang, Li Su, Wei-Han Hsu, Yi-Hsuan Yang","submitted_at":"2026-08-02T08:50:13Z","abstract_excerpt":"Automatic Drum Transcription (ADT) is commonly formulated as a direct mapping from a music mixture to symbolic drum events. While effective for transcription, this formulation discards the acoustic stems that are useful for editing, remixing, and production. We revisit an alternative separate-and-detect formulation, where a drum source separation front end first produces five editable drum stems, and a fixed onset detector then converts each stem into symbolic events. The separator is built on a five-stem latent diffusion model that jointly generates kick, snare, toms, hi-hats, and cymbals in "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.01093","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-02T08:50:13Z","cross_cats_sorted":[],"title_canon_sha256":"cc51d325724371f91502e48077c4d86037fe547b7a2f5dfada1def6acbacca5f","abstract_canon_sha256":"5bea1f7f806d377ee49bfde26852cbd173559952bccfe68403db594c8499fedb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:56:33.809125Z","signature_b64":"lsxypp6fMEClR5GCdYyE9CXuxwfoRsmTo8rtdTdRJ4PsFN/K6S+0B83ZYWl+MgZPq6ifGRMISX9o75UbWUGHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36fbeddbcb6c5585a7fa89ef610a6f58164b38da56c6595a5d3e73ccd41d2ceb","last_reissued_at":"2026-08-04T01:56:33.807658Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:56:33.807658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Separate-and-Detect: Unified Drum Transcription and Stem Generation via Latent Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Bo-Yu Chen, Chih-Cheng Chang, Li Su, Wei-Han Hsu, Yi-Hsuan Yang","submitted_at":"2026-08-02T08:50:13Z","abstract_excerpt":"Automatic Drum Transcription (ADT) is commonly formulated as a direct mapping from a music mixture to symbolic drum events. While effective for transcription, this formulation discards the acoustic stems that are useful for editing, remixing, and production. We revisit an alternative separate-and-detect formulation, where a drum source separation front end first produces five editable drum stems, and a fixed onset detector then converts each stem into symbolic events. The separator is built on a five-stem latent diffusion model that jointly generates kick, snare, toms, hi-hats, and cymbals in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01093","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.01093/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.01093","created_at":"2026-08-04T01:56:33.808944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01093v1","created_at":"2026-08-04T01:56:33.808944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01093","created_at":"2026-08-04T01:56:33.808944+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3563W6LNRKY","created_at":"2026-08-04T01:56:33.808944+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3563W6LNRKYLJ72","created_at":"2026-08-04T01:56:33.808944+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3563W6L","created_at":"2026-08-04T01:56:33.808944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01093","citing_title":"Separate-and-Detect: Unified Drum Transcription and Stem Generation via Latent Diffusion","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3563W6LNRKYLJ72RHXWCCTPLA","json":"https://pith.science/pith/G3563W6LNRKYLJ72RHXWCCTPLA.json","graph_json":"https://pith.science/api/pith-number/G3563W6LNRKYLJ72RHXWCCTPLA/graph.json","events_json":"https://pith.science/api/pith-number/G3563W6LNRKYLJ72RHXWCCTPLA/events.json","paper":"https://pith.science/paper/G3563W6L"},"agent_actions":{"view_html":"https://pith.science/pith/G3563W6LNRKYLJ72RHXWCCTPLA","download_json":"https://pith.science/pith/G3563W6LNRKYLJ72RHXWCCTPLA.json","view_paper":"https://pith.science/paper/G3563W6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01093&json=true","fetch_graph":"https://pith.science/api/pith-number/G3563W6LNRKYLJ72RHXWCCTPLA/graph.json","fetch_events":"https://pith.science/api/pith-number/G3563W6LNRKYLJ72RHXWCCTPLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3563W6LNRKYLJ72RHXWCCTPLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3563W6LNRKYLJ72RHXWCCTPLA/action/storage_attestation","attest_author":"https://pith.science/pith/G3563W6LNRKYLJ72RHXWCCTPLA/action/author_attestation","sign_citation":"https://pith.science/pith/G3563W6LNRKYLJ72RHXWCCTPLA/action/citation_signature","submit_replication":"https://pith.science/pith/G3563W6LNRKYLJ72RHXWCCTPLA/action/replication_record"}},"created_at":"2026-08-04T01:56:33.808944+00:00","updated_at":"2026-08-04T01:56:33.808944+00:00"}