{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TYL3QKMKHSVAPSLVBY3LHTBJOO","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":"3158fd5f0b268fcaf5f02016e11c7e314ab29d532f4093cac79be44ef2bd63de","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-14T00:14:54Z","title_canon_sha256":"4bff5ac948854f8b1a3678e1462759f1df780ac4522883f6fbffaf51593e0504"},"schema_version":"1.0","source":{"id":"2507.09834","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09834","created_at":"2026-07-05T11:36:40Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09834v1","created_at":"2026-07-05T11:36:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09834","created_at":"2026-07-05T11:36:40Z"},{"alias_kind":"pith_short_12","alias_value":"TYL3QKMKHSVA","created_at":"2026-07-05T11:36:40Z"},{"alias_kind":"pith_short_16","alias_value":"TYL3QKMKHSVAPSLV","created_at":"2026-07-05T11:36:40Z"},{"alias_kind":"pith_short_8","alias_value":"TYL3QKMK","created_at":"2026-07-05T11:36:40Z"}],"graph_snapshots":[{"event_id":"sha256:840efcd5f88840de488d16879ce3c2cce47a968ad2b823520867a4b0741140fe","target":"graph","created_at":"2026-07-05T11:36:40Z","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/2507.09834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language Processing (NLP) at scale. Extending this paradigm to audio poses unique challenges due to its inherently continuous nature. We research audio generation with a causal language model (LM) without discrete tokens. We leverage token-wise diffusion to model the continuous distribution of the next continuous-valued token. Our approach delivers significant improvements over previous discrete solution, AudioGen, achieving 2","authors_text":"Bo-Ru Lu, Byeonggeun Kim, Chao Wang, Chieh-Chi Kao, Harsha Sundar, Hung-yi Lee, Huy Phan, Kuan-Po Huang, Qingming Tang, Shalini Ghosh, Shu-wen Yang","cross_cats":["cs.CV","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-14T00:14:54Z","title":"Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09834","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:e1a15d1b83056bf5016299ae4e1cf4ceb5be92079cec4c8222c03c055cfadbdb","target":"record","created_at":"2026-07-05T11:36:40Z","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":"3158fd5f0b268fcaf5f02016e11c7e314ab29d532f4093cac79be44ef2bd63de","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-14T00:14:54Z","title_canon_sha256":"4bff5ac948854f8b1a3678e1462759f1df780ac4522883f6fbffaf51593e0504"},"schema_version":"1.0","source":{"id":"2507.09834","kind":"arxiv","version":1}},"canonical_sha256":"9e17b8298a3caa07c9750e36b3cc2973bf759b2de12579a76e5e294dd6ef5209","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e17b8298a3caa07c9750e36b3cc2973bf759b2de12579a76e5e294dd6ef5209","first_computed_at":"2026-07-05T11:36:40.544939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:40.544939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jkt0x9V0wg//AvczaG4bFsow78ohXATw8qPgjF6WOmhT7OIGhFNLahzOJ6U/YMduS4qIdOf1yMrAGNFAIaOCDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:40.545505Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09834","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1a15d1b83056bf5016299ae4e1cf4ceb5be92079cec4c8222c03c055cfadbdb","sha256:840efcd5f88840de488d16879ce3c2cce47a968ad2b823520867a4b0741140fe"],"state_sha256":"81209128a8fa7c84bf9c27f5ab48676e148a2d30a37b933f41b2ad78e9a18f97"}