{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:F7TYXEMIXHBE4MR7RZNLBAT65Q","short_pith_number":"pith:F7TYXEMI","schema_version":"1.0","canonical_sha256":"2fe78b9188b9c24e323f8e5ab0827eec033ef1b8109641b7cc1a7ec07b4274aa","source":{"kind":"arxiv","id":"2103.16091","version":2},"attestation_state":"computed","paper":{"title":"Symbolic Music Generation with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Curtis Hawthorne, Gautam Mittal, Ian Simon, Jesse Engel","submitted_at":"2021-03-30T05:48:05Z","abstract_excerpt":"Score-based generative models and diffusion probabilistic models have been successful at generating high-quality samples in continuous domains such as images and audio. However, due to their Langevin-inspired sampling mechanisms, their application to discrete and sequential data has been limited. In this work, we present a technique for training diffusion models on sequential data by parameterizing the discrete domain in the continuous latent space of a pre-trained variational autoencoder. Our method is non-autoregressive and learns to generate sequences of latent embeddings through the revers"},"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":"2103.16091","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-03-30T05:48:05Z","cross_cats_sorted":["cs.LG","eess.AS","stat.ML"],"title_canon_sha256":"468b504ee142e6e96d3deb8b4362434d4c98d40e84a073ddbd1dedf1f0d9afbf","abstract_canon_sha256":"b70dd9f8f4b2d12ef712ad2640f7b51cc8473c0996c0ff91a3180c482e47f3fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:09.001158Z","signature_b64":"LCa8N/LueuqGHhTSZXVhTWEG3Xhqyo0otl7hRNla1ekX4aCZCdmwzFbhoHm5qN+cIbpVxRo79froDqNV702qCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fe78b9188b9c24e323f8e5ab0827eec033ef1b8109641b7cc1a7ec07b4274aa","last_reissued_at":"2026-07-05T03:35:09.000685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:09.000685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symbolic Music Generation with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Curtis Hawthorne, Gautam Mittal, Ian Simon, Jesse Engel","submitted_at":"2021-03-30T05:48:05Z","abstract_excerpt":"Score-based generative models and diffusion probabilistic models have been successful at generating high-quality samples in continuous domains such as images and audio. However, due to their Langevin-inspired sampling mechanisms, their application to discrete and sequential data has been limited. In this work, we present a technique for training diffusion models on sequential data by parameterizing the discrete domain in the continuous latent space of a pre-trained variational autoencoder. Our method is non-autoregressive and learns to generate sequences of latent embeddings through the revers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16091","kind":"arxiv","version":2},"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/2103.16091/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":"2103.16091","created_at":"2026-07-05T03:35:09.000745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.16091v2","created_at":"2026-07-05T03:35:09.000745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16091","created_at":"2026-07-05T03:35:09.000745+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7TYXEMIXHBE","created_at":"2026-07-05T03:35:09.000745+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7TYXEMIXHBE4MR7","created_at":"2026-07-05T03:35:09.000745+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7TYXEMI","created_at":"2026-07-05T03:35:09.000745+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2112.10752","citing_title":"High-Resolution Image Synthesis with Latent Diffusion Models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2209.03003","citing_title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7TYXEMIXHBE4MR7RZNLBAT65Q","json":"https://pith.science/pith/F7TYXEMIXHBE4MR7RZNLBAT65Q.json","graph_json":"https://pith.science/api/pith-number/F7TYXEMIXHBE4MR7RZNLBAT65Q/graph.json","events_json":"https://pith.science/api/pith-number/F7TYXEMIXHBE4MR7RZNLBAT65Q/events.json","paper":"https://pith.science/paper/F7TYXEMI"},"agent_actions":{"view_html":"https://pith.science/pith/F7TYXEMIXHBE4MR7RZNLBAT65Q","download_json":"https://pith.science/pith/F7TYXEMIXHBE4MR7RZNLBAT65Q.json","view_paper":"https://pith.science/paper/F7TYXEMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.16091&json=true","fetch_graph":"https://pith.science/api/pith-number/F7TYXEMIXHBE4MR7RZNLBAT65Q/graph.json","fetch_events":"https://pith.science/api/pith-number/F7TYXEMIXHBE4MR7RZNLBAT65Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7TYXEMIXHBE4MR7RZNLBAT65Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7TYXEMIXHBE4MR7RZNLBAT65Q/action/storage_attestation","attest_author":"https://pith.science/pith/F7TYXEMIXHBE4MR7RZNLBAT65Q/action/author_attestation","sign_citation":"https://pith.science/pith/F7TYXEMIXHBE4MR7RZNLBAT65Q/action/citation_signature","submit_replication":"https://pith.science/pith/F7TYXEMIXHBE4MR7RZNLBAT65Q/action/replication_record"}},"created_at":"2026-07-05T03:35:09.000745+00:00","updated_at":"2026-07-05T03:35:09.000745+00:00"}