{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YF545KIPYVFFXNDUAFE6FO74IA","short_pith_number":"pith:YF545KIP","schema_version":"1.0","canonical_sha256":"c17bcea90fc54a5bb4740149e2bbfc4029846c4c522d2ec6bcff4f2d362b6bfe","source":{"kind":"arxiv","id":"2406.00356","version":2},"attestation_state":"computed","paper":{"title":"AudioLCM: Text-to-Audio Generation with Latent Consistency Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hengyuan Cao, Huadai Liu, Jialei Wang, Rongjie Huang, Siqi Zheng, Xize Cheng, Yang Liu, Zhou Zhao","submitted_at":"2024-06-01T08:19:56Z","abstract_excerpt":"Recent advancements in Latent Diffusion Models (LDMs) have propelled them to the forefront of various generative tasks. However, their iterative sampling process poses a significant computational burden, resulting in slow generation speeds and limiting their application in text-to-audio generation deployment. In this work, we introduce AudioLCM, a novel consistency-based model tailored for efficient and high-quality text-to-audio generation. AudioLCM integrates Consistency Models into the generation process, facilitating rapid inference through a mapping from any point at any time step to 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":"2406.00356","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-01T08:19:56Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"d12fe511425d9f1a2bedf5b4fe973436f2a5c86f65df391f6d48d9d5950170fa","abstract_canon_sha256":"c2469b18b2229eb33c4fab13a00c21f71937398b4d81a32668bc6f1c43f28518"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:45.448842Z","signature_b64":"fVspn7WcSSAPWJ9Gqiv041ZW6+CihbEjzW6RyaGvB9ljraCcrSS8AKPwaXlDa3z8ONTSLo6ScriVuJBCOggODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c17bcea90fc54a5bb4740149e2bbfc4029846c4c522d2ec6bcff4f2d362b6bfe","last_reissued_at":"2026-07-05T08:41:45.448404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:45.448404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudioLCM: Text-to-Audio Generation with Latent Consistency Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hengyuan Cao, Huadai Liu, Jialei Wang, Rongjie Huang, Siqi Zheng, Xize Cheng, Yang Liu, Zhou Zhao","submitted_at":"2024-06-01T08:19:56Z","abstract_excerpt":"Recent advancements in Latent Diffusion Models (LDMs) have propelled them to the forefront of various generative tasks. However, their iterative sampling process poses a significant computational burden, resulting in slow generation speeds and limiting their application in text-to-audio generation deployment. In this work, we introduce AudioLCM, a novel consistency-based model tailored for efficient and high-quality text-to-audio generation. AudioLCM integrates Consistency Models into the generation process, facilitating rapid inference through a mapping from any point at any time step to the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00356","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/2406.00356/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":"2406.00356","created_at":"2026-07-05T08:41:45.448460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00356v2","created_at":"2026-07-05T08:41:45.448460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00356","created_at":"2026-07-05T08:41:45.448460+00:00"},{"alias_kind":"pith_short_12","alias_value":"YF545KIPYVFF","created_at":"2026-07-05T08:41:45.448460+00:00"},{"alias_kind":"pith_short_16","alias_value":"YF545KIPYVFFXNDU","created_at":"2026-07-05T08:41:45.448460+00:00"},{"alias_kind":"pith_short_8","alias_value":"YF545KIP","created_at":"2026-07-05T08:41:45.448460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05196","citing_title":"Unified Audio Intelligence Without Regressing on Text Intelligence","ref_index":180,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23080","citing_title":"AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YF545KIPYVFFXNDUAFE6FO74IA","json":"https://pith.science/pith/YF545KIPYVFFXNDUAFE6FO74IA.json","graph_json":"https://pith.science/api/pith-number/YF545KIPYVFFXNDUAFE6FO74IA/graph.json","events_json":"https://pith.science/api/pith-number/YF545KIPYVFFXNDUAFE6FO74IA/events.json","paper":"https://pith.science/paper/YF545KIP"},"agent_actions":{"view_html":"https://pith.science/pith/YF545KIPYVFFXNDUAFE6FO74IA","download_json":"https://pith.science/pith/YF545KIPYVFFXNDUAFE6FO74IA.json","view_paper":"https://pith.science/paper/YF545KIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00356&json=true","fetch_graph":"https://pith.science/api/pith-number/YF545KIPYVFFXNDUAFE6FO74IA/graph.json","fetch_events":"https://pith.science/api/pith-number/YF545KIPYVFFXNDUAFE6FO74IA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YF545KIPYVFFXNDUAFE6FO74IA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YF545KIPYVFFXNDUAFE6FO74IA/action/storage_attestation","attest_author":"https://pith.science/pith/YF545KIPYVFFXNDUAFE6FO74IA/action/author_attestation","sign_citation":"https://pith.science/pith/YF545KIPYVFFXNDUAFE6FO74IA/action/citation_signature","submit_replication":"https://pith.science/pith/YF545KIPYVFFXNDUAFE6FO74IA/action/replication_record"}},"created_at":"2026-07-05T08:41:45.448460+00:00","updated_at":"2026-07-05T08:41:45.448460+00:00"}