{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZEXA2VSGM6ENROS4S6YTR7CQXI","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":"00ecc7d5848f8c4e46318ffb06c1a701826d8f27450f80807bbf358c4db0c835","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-08T18:57:13Z","title_canon_sha256":"5139d841eab2de03c401352a01e8838642bf906f653e4e6d2b6f3a9671139564"},"schema_version":"1.0","source":{"id":"2406.05551","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05551","created_at":"2026-07-05T08:29:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05551v1","created_at":"2026-07-05T08:29:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05551","created_at":"2026-07-05T08:29:29Z"},{"alias_kind":"pith_short_12","alias_value":"ZEXA2VSGM6EN","created_at":"2026-07-05T08:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"ZEXA2VSGM6ENROS4","created_at":"2026-07-05T08:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"ZEXA2VSG","created_at":"2026-07-05T08:29:29Z"}],"graph_snapshots":[{"event_id":"sha256:5711604b40b56bfbd3f0c9d2d532efca5ea467c92b1d09ea11e358fbd9cc6d10","target":"graph","created_at":"2026-07-05T08:29:29Z","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/2406.05551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio language models have recently emerged as a promising approach for various audio generation tasks, relying on audio tokenizers to encode waveforms into sequences of discrete symbols. Audio tokenization often poses a necessary compromise between code bitrate and reconstruction accuracy. When dealing with low-bitrate audio codes, language models are constrained to process only a subset of the information embedded in the audio, which in turn restricts their generative capabilities. To circumvent these issues, we propose encoding audio as vector sequences in continuous space $\\mathbb R^d$ and","authors_text":"Haizhou Li, Qibing Bai, Sho Inoue, Shuai Wang, Zhijun Liu","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-08T18:57:13Z","title":"Autoregressive Diffusion Transformer for Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05551","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:b4437d2dc04c3db2764dc6f27f32bb9e94e62b29b083747d4f716c8a97d83f19","target":"record","created_at":"2026-07-05T08:29:29Z","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":"00ecc7d5848f8c4e46318ffb06c1a701826d8f27450f80807bbf358c4db0c835","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-08T18:57:13Z","title_canon_sha256":"5139d841eab2de03c401352a01e8838642bf906f653e4e6d2b6f3a9671139564"},"schema_version":"1.0","source":{"id":"2406.05551","kind":"arxiv","version":1}},"canonical_sha256":"c92e0d56466788d8ba5c97b138fc50ba29689216b5aa7fcd3be451572eaf2153","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c92e0d56466788d8ba5c97b138fc50ba29689216b5aa7fcd3be451572eaf2153","first_computed_at":"2026-07-05T08:29:29.786726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:29.786726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Br7XiwWhkVF6cjrBZbeaJ3Ne90kv40XNuNHW4NGBAbD/lPfSCdtNI7ub4gfGXKin1RVf1OjXTxOqG00b8V29Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:29.787155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.05551","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4437d2dc04c3db2764dc6f27f32bb9e94e62b29b083747d4f716c8a97d83f19","sha256:5711604b40b56bfbd3f0c9d2d532efca5ea467c92b1d09ea11e358fbd9cc6d10"],"state_sha256":"39b578d55e5f18fca2dc0a7080e3c1eacf2e47fc58a6c405684fbfd81eec7e7c"}