{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UHKJ2V3C5TPI7TITNPZJZPT5ID","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":"aba807873f70155a079878d870f39aa621d05aae0b7117db0fa992de4d24be56","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-14T17:43:55Z","title_canon_sha256":"6d1f4195889983820a8d9e1ea2913a54bf1ab1869e75a647dac2b03a55cf9687"},"schema_version":"1.0","source":{"id":"2401.07333","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.07333","created_at":"2026-07-05T07:33:35Z"},{"alias_kind":"arxiv_version","alias_value":"2401.07333v1","created_at":"2026-07-05T07:33:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07333","created_at":"2026-07-05T07:33:35Z"},{"alias_kind":"pith_short_12","alias_value":"UHKJ2V3C5TPI","created_at":"2026-07-05T07:33:35Z"},{"alias_kind":"pith_short_16","alias_value":"UHKJ2V3C5TPI7TIT","created_at":"2026-07-05T07:33:35Z"},{"alias_kind":"pith_short_8","alias_value":"UHKJ2V3C","created_at":"2026-07-05T07:33:35Z"}],"graph_snapshots":[{"event_id":"sha256:92bde9dd90280ca6ef218fa29936ccbebab03511f085bdc44460f45de3bc35bd","target":"graph","created_at":"2026-07-05T07:33:35Z","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/2401.07333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The language model (LM) approach based on acoustic and linguistic prompts, such as VALL-E, has achieved remarkable progress in the field of zero-shot audio generation. However, existing methods still have some limitations: 1) repetitions, transpositions, and omissions in the output synthesized speech due to limited alignment constraints between audio and phoneme tokens; 2) challenges of fine-grained control over the synthesized speech with autoregressive (AR) language model; 3) infinite silence generation due to the nature of AR-based decoding, especially under the greedy strategy. To alleviat","authors_text":"Xiaofei Wang, Xie Chen, Yakun Song, Zhuo Chen, Ziyang Ma","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-14T17:43:55Z","title":"ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07333","kind":"arxiv","version":1},"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":"sha256:24c3036e57bf5b4935e9f6a950f2fabe2161dd2e33c6584a5c6ab91122bec412","target":"record","created_at":"2026-07-05T07:33:35Z","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":"aba807873f70155a079878d870f39aa621d05aae0b7117db0fa992de4d24be56","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-14T17:43:55Z","title_canon_sha256":"6d1f4195889983820a8d9e1ea2913a54bf1ab1869e75a647dac2b03a55cf9687"},"schema_version":"1.0","source":{"id":"2401.07333","kind":"arxiv","version":1}},"canonical_sha256":"a1d49d5762ecde8fcd136bf29cbe7d40e23ce4ab49d64bda68f8e95d5542ea23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1d49d5762ecde8fcd136bf29cbe7d40e23ce4ab49d64bda68f8e95d5542ea23","first_computed_at":"2026-07-05T07:33:35.655352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:33:35.655352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"glztxFUwEOcuYyjrKy3uUG9NgmbqLzOD+ADb/7ovKOzk+PM5Z6A9/NEk22r6yRo61ziZIjTI4oqIXUsHapolDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:33:35.655724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.07333","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24c3036e57bf5b4935e9f6a950f2fabe2161dd2e33c6584a5c6ab91122bec412","sha256:92bde9dd90280ca6ef218fa29936ccbebab03511f085bdc44460f45de3bc35bd"],"state_sha256":"dc42b136661cff2ae41bc97013a7f3bb212d86ac7d0c0e608a767c39f6bdf248"}