{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A7REK5XUYWFQX2RRSZWNQ34245","short_pith_number":"pith:A7REK5XU","schema_version":"1.0","canonical_sha256":"07e24576f4c58b0bea31966cd86f9ae757d4d4919eec693d4fc62be6dd5eb4d3","source":{"kind":"arxiv","id":"2407.14358","version":2},"attestation_state":"computed","paper":{"title":"Stable Audio Open","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"CJ Carr, Jordi Pons, Josiah Taylor, Julian D. Parker, Zach Evans, Zack Zukowski","submitted_at":"2024-07-19T14:40:23Z","abstract_excerpt":"Open generative models are vitally important for the community, allowing for fine-tunes and serving as baselines when presenting new models. However, most current text-to-audio models are private and not accessible for artists and researchers to build upon. Here we describe the architecture and training process of a new open-weights text-to-audio model trained with Creative Commons data. Our evaluation shows that the model's performance is competitive with the state-of-the-art across various metrics. Notably, the reported FDopenl3 results (measuring the realism of the generations) showcase its"},"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":"2407.14358","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-19T14:40:23Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"1a1487618d69d34422088eba010a7bc967ee3ddcc4d5b144869d6355c6e94a1d","abstract_canon_sha256":"56403ab698b6165af4ffd723e102bd96464f2b1909a65722312ad2a801cb5fde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:31.269267Z","signature_b64":"IbJeGXCOPxltiWJKRHNiXd0cR3ybuzoQxmAuShCL0JMQ5KForHiRuiH3+tFVomvoRKJlIyVosHxFaovkFQclCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07e24576f4c58b0bea31966cd86f9ae757d4d4919eec693d4fc62be6dd5eb4d3","last_reissued_at":"2026-07-05T08:50:31.268824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:31.268824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stable Audio Open","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"CJ Carr, Jordi Pons, Josiah Taylor, Julian D. Parker, Zach Evans, Zack Zukowski","submitted_at":"2024-07-19T14:40:23Z","abstract_excerpt":"Open generative models are vitally important for the community, allowing for fine-tunes and serving as baselines when presenting new models. However, most current text-to-audio models are private and not accessible for artists and researchers to build upon. Here we describe the architecture and training process of a new open-weights text-to-audio model trained with Creative Commons data. Our evaluation shows that the model's performance is competitive with the state-of-the-art across various metrics. Notably, the reported FDopenl3 results (measuring the realism of the generations) showcase its"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14358","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/2407.14358/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":"2407.14358","created_at":"2026-07-05T08:50:31.268883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14358v2","created_at":"2026-07-05T08:50:31.268883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14358","created_at":"2026-07-05T08:50:31.268883+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7REK5XUYWFQ","created_at":"2026-07-05T08:50:31.268883+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7REK5XUYWFQX2RR","created_at":"2026-07-05T08:50:31.268883+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7REK5XU","created_at":"2026-07-05T08:50:31.268883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05196","citing_title":"Unified Audio Intelligence Without Regressing on Text Intelligence","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24307","citing_title":"Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18072","citing_title":"One-Step Token-to-Waveform Generation with MeanFlow in Latent Space","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12555","citing_title":"AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10046","citing_title":"Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07271","citing_title":"Where Flow Matching Leaks: Characterising Membership Signals Along the Interpolation Path","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05852","citing_title":"UniVoice: A Unified Model for Speech and Singing Voice Generation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00641","citing_title":"What's a Credit Worth? A Market Framework for Attribution-Aware Compensation in Generative Music","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13931","citing_title":"FSD50K-Solo: Automated Curation of Single-Source Sound Events","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29148","citing_title":"GPC: Large-Scale Generative Pretraining for Transferable Motor Control","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2502.04230","citing_title":"XAttnMark: Learning Robust Audio Watermarking with Cross-Attention","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21433","citing_title":"Instrumental Text-to-Music Generation with Auxiliary Conditioning Branches","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08794","citing_title":"Deterministic Decomposition of Stochastic Generative Dynamics","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13931","citing_title":"FSD50K-Solo: Automated Curation of Single-Source Sound Events","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01929","citing_title":"Woosh: A Sound Effects Foundation Model","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2410.00037","citing_title":"Moshi: a speech-text foundation model for real-time dialogue","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08794","citing_title":"Deterministic Decomposition of Stochastic Generative Dynamics","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10708","citing_title":"Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16254","citing_title":"ArtifactNet: Detecting AI-Generated Music via Forensic Residual Physics","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A7REK5XUYWFQX2RRSZWNQ34245","json":"https://pith.science/pith/A7REK5XUYWFQX2RRSZWNQ34245.json","graph_json":"https://pith.science/api/pith-number/A7REK5XUYWFQX2RRSZWNQ34245/graph.json","events_json":"https://pith.science/api/pith-number/A7REK5XUYWFQX2RRSZWNQ34245/events.json","paper":"https://pith.science/paper/A7REK5XU"},"agent_actions":{"view_html":"https://pith.science/pith/A7REK5XUYWFQX2RRSZWNQ34245","download_json":"https://pith.science/pith/A7REK5XUYWFQX2RRSZWNQ34245.json","view_paper":"https://pith.science/paper/A7REK5XU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14358&json=true","fetch_graph":"https://pith.science/api/pith-number/A7REK5XUYWFQX2RRSZWNQ34245/graph.json","fetch_events":"https://pith.science/api/pith-number/A7REK5XUYWFQX2RRSZWNQ34245/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7REK5XUYWFQX2RRSZWNQ34245/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7REK5XUYWFQX2RRSZWNQ34245/action/storage_attestation","attest_author":"https://pith.science/pith/A7REK5XUYWFQX2RRSZWNQ34245/action/author_attestation","sign_citation":"https://pith.science/pith/A7REK5XUYWFQX2RRSZWNQ34245/action/citation_signature","submit_replication":"https://pith.science/pith/A7REK5XUYWFQX2RRSZWNQ34245/action/replication_record"}},"created_at":"2026-07-05T08:50:31.268883+00:00","updated_at":"2026-07-05T08:50:31.268883+00:00"}