{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MGAANRMQ7UC6ADH4B2RFWZTPQX","short_pith_number":"pith:MGAANRMQ","schema_version":"1.0","canonical_sha256":"618006c590fd05e00cfc0ea25b666f85e896f9449bf7f8658163f7376bc59eb6","source":{"kind":"arxiv","id":"2302.02257","version":4},"attestation_state":"computed","paper":{"title":"Multi-Source Diffusion Models for Simultaneous Music Generation and Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Emanuele Rodol\\`a, Emilian Postolache, Giorgio Mariani, Irene Tallini, Luca Cosmo, Michele Mancusi","submitted_at":"2023-02-04T23:18:36Z","abstract_excerpt":"In this work, we define a diffusion-based generative model capable of both music synthesis and source separation by learning the score of the joint probability density of sources sharing a context. Alongside the classic total inference tasks (i.e., generating a mixture, separating the sources), we also introduce and experiment on the partial generation task of source imputation, where we generate a subset of the sources given the others (e.g., play a piano track that goes well with the drums). Additionally, we introduce a novel inference method for the separation task based on Dirac likelihood"},"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":"2302.02257","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-02-04T23:18:36Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"9b1e9f1b0aa80c3f69841221814d328ee02e97efb1d5a433ea4deabd81f58209","abstract_canon_sha256":"b7e6b6a73d1843a208e9c84e333c39c766a33ac25b98321b6e83e9f393c8ff72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:46.635255Z","signature_b64":"vRLZWu2ycdN7rG+r8PlGp8Q2sSpCWzFfMdnx5fd83LSFfH4j/gWymCy7g7uMtKOIupSb+WPB3/v8i30MK+4VDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"618006c590fd05e00cfc0ea25b666f85e896f9449bf7f8658163f7376bc59eb6","last_reissued_at":"2026-07-05T07:56:46.634833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:46.634833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Source Diffusion Models for Simultaneous Music Generation and Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Emanuele Rodol\\`a, Emilian Postolache, Giorgio Mariani, Irene Tallini, Luca Cosmo, Michele Mancusi","submitted_at":"2023-02-04T23:18:36Z","abstract_excerpt":"In this work, we define a diffusion-based generative model capable of both music synthesis and source separation by learning the score of the joint probability density of sources sharing a context. Alongside the classic total inference tasks (i.e., generating a mixture, separating the sources), we also introduce and experiment on the partial generation task of source imputation, where we generate a subset of the sources given the others (e.g., play a piano track that goes well with the drums). Additionally, we introduce a novel inference method for the separation task based on Dirac likelihood"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02257","kind":"arxiv","version":4},"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/2302.02257/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":"2302.02257","created_at":"2026-07-05T07:56:46.634895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.02257v4","created_at":"2026-07-05T07:56:46.634895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02257","created_at":"2026-07-05T07:56:46.634895+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGAANRMQ7UC6","created_at":"2026-07-05T07:56:46.634895+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGAANRMQ7UC6ADH4","created_at":"2026-07-05T07:56:46.634895+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGAANRMQ","created_at":"2026-07-05T07:56:46.634895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09259","citing_title":"Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09803","citing_title":"MAGE: Modality-Agnostic Music Generation and Target-Source Extraction","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MGAANRMQ7UC6ADH4B2RFWZTPQX","json":"https://pith.science/pith/MGAANRMQ7UC6ADH4B2RFWZTPQX.json","graph_json":"https://pith.science/api/pith-number/MGAANRMQ7UC6ADH4B2RFWZTPQX/graph.json","events_json":"https://pith.science/api/pith-number/MGAANRMQ7UC6ADH4B2RFWZTPQX/events.json","paper":"https://pith.science/paper/MGAANRMQ"},"agent_actions":{"view_html":"https://pith.science/pith/MGAANRMQ7UC6ADH4B2RFWZTPQX","download_json":"https://pith.science/pith/MGAANRMQ7UC6ADH4B2RFWZTPQX.json","view_paper":"https://pith.science/paper/MGAANRMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.02257&json=true","fetch_graph":"https://pith.science/api/pith-number/MGAANRMQ7UC6ADH4B2RFWZTPQX/graph.json","fetch_events":"https://pith.science/api/pith-number/MGAANRMQ7UC6ADH4B2RFWZTPQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGAANRMQ7UC6ADH4B2RFWZTPQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGAANRMQ7UC6ADH4B2RFWZTPQX/action/storage_attestation","attest_author":"https://pith.science/pith/MGAANRMQ7UC6ADH4B2RFWZTPQX/action/author_attestation","sign_citation":"https://pith.science/pith/MGAANRMQ7UC6ADH4B2RFWZTPQX/action/citation_signature","submit_replication":"https://pith.science/pith/MGAANRMQ7UC6ADH4B2RFWZTPQX/action/replication_record"}},"created_at":"2026-07-05T07:56:46.634895+00:00","updated_at":"2026-07-05T07:56:46.634895+00:00"}