{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TSVVDHV2MZQKY77CTASRZKONXY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6b7430b2e8b50cfe784b3a000aafb2c190df6f507b5fd99934c56941c1fe00dc","cross_cats_sorted":["cs.LG","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-19T16:36:33Z","title_canon_sha256":"f2438bd723bd246f38d2259e67011eebf1ab1e0b963b0aa11590cec34916a1dd"},"schema_version":"1.0","source":{"id":"2309.10740","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10740","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10740v3","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10740","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"pith_short_12","alias_value":"TSVVDHV2MZQK","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"pith_short_16","alias_value":"TSVVDHV2MZQKY77C","created_at":"2026-07-05T08:35:36Z"},{"alias_kind":"pith_short_8","alias_value":"TSVVDHV2","created_at":"2026-07-05T08:35:36Z"}],"graph_snapshots":[{"event_id":"sha256:f392dfc9656cb63a7bcb04e2ff946d0818df644690ab7b931f6131e661a0b387","target":"graph","created_at":"2026-07-05T08:35:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.10740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models are instrumental in text-to-audio (TTA) generation. Unfortunately, they suffer from slow inference due to an excessive number of queries to the underlying denoising network per generation. To address this bottleneck, we introduce ConsistencyTTA, a framework requiring only a single non-autoregressive network query, thereby accelerating TTA by hundreds of times. We achieve so by proposing \"CFG-aware latent consistency model,\" which adapts consistency generation into a latent space and incorporates classifier-free guidance (CFG) into model training. Moreover, unlike diffusion mod","authors_text":"Dung Tran, Kazuhito Koishida, Somayeh Sojoudi, Trung Dang, Yatong Bai","cross_cats":["cs.LG","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-19T16:36:33Z","title":"ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10740","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9718963edb6bf81f6a231d193434986fa74b26f7a02076c3ceba54633d2a3067","target":"record","created_at":"2026-07-05T08:35:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6b7430b2e8b50cfe784b3a000aafb2c190df6f507b5fd99934c56941c1fe00dc","cross_cats_sorted":["cs.LG","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-19T16:36:33Z","title_canon_sha256":"f2438bd723bd246f38d2259e67011eebf1ab1e0b963b0aa11590cec34916a1dd"},"schema_version":"1.0","source":{"id":"2309.10740","kind":"arxiv","version":3}},"canonical_sha256":"9cab519eba6660ac7fe298251ca9cdbe2930de0bbd1161f2390f1beb6e80fd56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cab519eba6660ac7fe298251ca9cdbe2930de0bbd1161f2390f1beb6e80fd56","first_computed_at":"2026-07-05T08:35:36.924705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:36.924705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8LNtRVh1OXSb+aZ7bIzSoZos7Z4uB2xb4NfBe++mcxTuv2YtsYFIVxHaAQ5xxspSgAPlNWosLDQsyk530fjxBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:36.925200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10740","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9718963edb6bf81f6a231d193434986fa74b26f7a02076c3ceba54633d2a3067","sha256:f392dfc9656cb63a7bcb04e2ff946d0818df644690ab7b931f6131e661a0b387"],"state_sha256":"d65a016e681804a9dc62ddd835cb6005a742e789f18fe97df15d63079628c207"}