{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SYJARE7A42TAUOYP467VM426FG","short_pith_number":"pith:SYJARE7A","schema_version":"1.0","canonical_sha256":"96120893e0e6a60a3b0fe7bf56735e29b19a2c9f1a82cd331f2b5631323642c0","source":{"kind":"arxiv","id":"2302.04456","version":2},"attestation_state":"computed","paper":{"title":"ERNIE-Music: Text-to-Waveform Music Generation with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chao Pang, Hao Tian, Hua Wu, Lei Li, Pengfei Zhu, Shuohuan Wang, Yekun Chai, Yu Sun","submitted_at":"2023-02-09T06:27:09Z","abstract_excerpt":"In recent years, the burgeoning interest in diffusion models has led to significant advances in image and speech generation. Nevertheless, the direct synthesis of music waveforms from unrestricted textual prompts remains a relatively underexplored domain. In response to this lacuna, this paper introduces a pioneering contribution in the form of a text-to-waveform music generation model, underpinned by the utilization of diffusion models. Our methodology hinges on the innovative incorporation of free-form textual prompts as conditional factors to guide the waveform generation process within the"},"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":"2302.04456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-02-09T06:27:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","eess.AS"],"title_canon_sha256":"99dd37e2fb33a2877cf91a819f6028bfa4d555b94611b7874b872eb75204e719","abstract_canon_sha256":"94c7ba522aca7bc0d7c8c62342d7baca44fafa609bc50095ac35b21df907ad6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:45.747713Z","signature_b64":"+85OCtNg/TiCwRdUKGJPc8dyZG0KXxBYg/8QvyyNhSkRLYDLxeMpIxGvS0IfViNZl3t7Nr158uEzDnsUDAc3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96120893e0e6a60a3b0fe7bf56735e29b19a2c9f1a82cd331f2b5631323642c0","last_reissued_at":"2026-07-05T06:52:45.747184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:45.747184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ERNIE-Music: Text-to-Waveform Music Generation with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chao Pang, Hao Tian, Hua Wu, Lei Li, Pengfei Zhu, Shuohuan Wang, Yekun Chai, Yu Sun","submitted_at":"2023-02-09T06:27:09Z","abstract_excerpt":"In recent years, the burgeoning interest in diffusion models has led to significant advances in image and speech generation. Nevertheless, the direct synthesis of music waveforms from unrestricted textual prompts remains a relatively underexplored domain. In response to this lacuna, this paper introduces a pioneering contribution in the form of a text-to-waveform music generation model, underpinned by the utilization of diffusion models. Our methodology hinges on the innovative incorporation of free-form textual prompts as conditional factors to guide the waveform generation process within the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04456","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/2302.04456/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":"2302.04456","created_at":"2026-07-05T06:52:45.747242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04456v2","created_at":"2026-07-05T06:52:45.747242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04456","created_at":"2026-07-05T06:52:45.747242+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYJARE7A42TA","created_at":"2026-07-05T06:52:45.747242+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYJARE7A42TAUOYP","created_at":"2026-07-05T06:52:45.747242+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYJARE7A","created_at":"2026-07-05T06:52:45.747242+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01703","citing_title":"JenBridge: Adaptive Long-Form Video Soundtracking across Scene Transitions","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SYJARE7A42TAUOYP467VM426FG","json":"https://pith.science/pith/SYJARE7A42TAUOYP467VM426FG.json","graph_json":"https://pith.science/api/pith-number/SYJARE7A42TAUOYP467VM426FG/graph.json","events_json":"https://pith.science/api/pith-number/SYJARE7A42TAUOYP467VM426FG/events.json","paper":"https://pith.science/paper/SYJARE7A"},"agent_actions":{"view_html":"https://pith.science/pith/SYJARE7A42TAUOYP467VM426FG","download_json":"https://pith.science/pith/SYJARE7A42TAUOYP467VM426FG.json","view_paper":"https://pith.science/paper/SYJARE7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04456&json=true","fetch_graph":"https://pith.science/api/pith-number/SYJARE7A42TAUOYP467VM426FG/graph.json","fetch_events":"https://pith.science/api/pith-number/SYJARE7A42TAUOYP467VM426FG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYJARE7A42TAUOYP467VM426FG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYJARE7A42TAUOYP467VM426FG/action/storage_attestation","attest_author":"https://pith.science/pith/SYJARE7A42TAUOYP467VM426FG/action/author_attestation","sign_citation":"https://pith.science/pith/SYJARE7A42TAUOYP467VM426FG/action/citation_signature","submit_replication":"https://pith.science/pith/SYJARE7A42TAUOYP467VM426FG/action/replication_record"}},"created_at":"2026-07-05T06:52:45.747242+00:00","updated_at":"2026-07-05T06:52:45.747242+00:00"}