{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PCCIB7KFPZGTJHIS5PWLGMCXAV","short_pith_number":"pith:PCCIB7KF","schema_version":"1.0","canonical_sha256":"788480fd457e4d349d12ebecb3305705665b1c695514e269f3b38980b1939586","source":{"kind":"arxiv","id":"2505.22106","version":1},"attestation_state":"computed","paper":{"title":"AudioTurbo: Fast Text-to-Audio Generation with Rectified Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haohe Liu, Jinzheng Zhao, Junqi Zhao, Lu Han, Mark Plumbley, Wenwu Wang, Xubo Liu, Yun Chen","submitted_at":"2025-05-28T08:33:58Z","abstract_excerpt":"Diffusion models have significantly improved the quality and diversity of audio generation but are hindered by slow inference speed. Rectified flow enhances inference speed by learning straight-line ordinary differential equation (ODE) paths. However, this approach requires training a flow-matching model from scratch and tends to perform suboptimally, or even poorly, at low step counts. To address the limitations of rectified flow while leveraging the advantages of advanced pre-trained diffusion models, this study integrates pre-trained models with the rectified diffusion method to improve 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":"2505.22106","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T08:33:58Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"7f9d75decf84ca884dbd9c54ba9b3202b4255258170ceba4d2d2afc1b0617b48","abstract_canon_sha256":"4037d11d6386e6f6880c222b7565b8b34da92b83774ec6effe1e99fea9c298d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:10.036239Z","signature_b64":"wPO13fDFP+xC2Y9jIwzS8X0x3rlbQQotRrw5zv7uOQeT8g+BLHErZ2l/esq1wNIIAa6ARUkZAJpV+gBIgvvKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"788480fd457e4d349d12ebecb3305705665b1c695514e269f3b38980b1939586","last_reissued_at":"2026-07-05T11:11:10.035725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:10.035725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudioTurbo: Fast Text-to-Audio Generation with Rectified Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haohe Liu, Jinzheng Zhao, Junqi Zhao, Lu Han, Mark Plumbley, Wenwu Wang, Xubo Liu, Yun Chen","submitted_at":"2025-05-28T08:33:58Z","abstract_excerpt":"Diffusion models have significantly improved the quality and diversity of audio generation but are hindered by slow inference speed. Rectified flow enhances inference speed by learning straight-line ordinary differential equation (ODE) paths. However, this approach requires training a flow-matching model from scratch and tends to perform suboptimally, or even poorly, at low step counts. To address the limitations of rectified flow while leveraging the advantages of advanced pre-trained diffusion models, this study integrates pre-trained models with the rectified diffusion method to improve the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22106","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/2505.22106/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":"2505.22106","created_at":"2026-07-05T11:11:10.035778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22106v1","created_at":"2026-07-05T11:11:10.035778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22106","created_at":"2026-07-05T11:11:10.035778+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCCIB7KFPZGT","created_at":"2026-07-05T11:11:10.035778+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCCIB7KFPZGTJHIS","created_at":"2026-07-05T11:11:10.035778+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCCIB7KF","created_at":"2026-07-05T11:11:10.035778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00329","citing_title":"Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCCIB7KFPZGTJHIS5PWLGMCXAV","json":"https://pith.science/pith/PCCIB7KFPZGTJHIS5PWLGMCXAV.json","graph_json":"https://pith.science/api/pith-number/PCCIB7KFPZGTJHIS5PWLGMCXAV/graph.json","events_json":"https://pith.science/api/pith-number/PCCIB7KFPZGTJHIS5PWLGMCXAV/events.json","paper":"https://pith.science/paper/PCCIB7KF"},"agent_actions":{"view_html":"https://pith.science/pith/PCCIB7KFPZGTJHIS5PWLGMCXAV","download_json":"https://pith.science/pith/PCCIB7KFPZGTJHIS5PWLGMCXAV.json","view_paper":"https://pith.science/paper/PCCIB7KF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22106&json=true","fetch_graph":"https://pith.science/api/pith-number/PCCIB7KFPZGTJHIS5PWLGMCXAV/graph.json","fetch_events":"https://pith.science/api/pith-number/PCCIB7KFPZGTJHIS5PWLGMCXAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCCIB7KFPZGTJHIS5PWLGMCXAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCCIB7KFPZGTJHIS5PWLGMCXAV/action/storage_attestation","attest_author":"https://pith.science/pith/PCCIB7KFPZGTJHIS5PWLGMCXAV/action/author_attestation","sign_citation":"https://pith.science/pith/PCCIB7KFPZGTJHIS5PWLGMCXAV/action/citation_signature","submit_replication":"https://pith.science/pith/PCCIB7KFPZGTJHIS5PWLGMCXAV/action/replication_record"}},"created_at":"2026-07-05T11:11:10.035778+00:00","updated_at":"2026-07-05T11:11:10.035778+00:00"}