{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VJDDRG4QQHKAIU4J7XCFW4DBMI","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":"7f23aeaefc5d68c2bfbad74073acb42b645582bbe5186337b06d9f1c4b534f57","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-22T09:30:02Z","title_canon_sha256":"a7b4ba98bd44104fc6575455e105a6fe023a75c8bd6d28fb0a0cd2a5cb8d0aca"},"schema_version":"1.0","source":{"id":"2606.23080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23080","created_at":"2026-06-23T03:14:09Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23080v1","created_at":"2026-06-23T03:14:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23080","created_at":"2026-06-23T03:14:09Z"},{"alias_kind":"pith_short_12","alias_value":"VJDDRG4QQHKA","created_at":"2026-06-23T03:14:09Z"},{"alias_kind":"pith_short_16","alias_value":"VJDDRG4QQHKAIU4J","created_at":"2026-06-23T03:14:09Z"},{"alias_kind":"pith_short_8","alias_value":"VJDDRG4Q","created_at":"2026-06-23T03:14:09Z"}],"graph_snapshots":[{"event_id":"sha256:d411d75f1fe967176fd1fa1856949bb46431d7f1c15af1bea84a378a79baa104","target":"graph","created_at":"2026-06-23T03:14:09Z","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/2606.23080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unifying speech, sound, and music generation in one model is hindered by tradeoffs between fidelity, end-to-end training, in-context conditioning, and variable-length synthesis that no current paradigm fully resolves. To address this challenge, we present AudioCALM, a universal audio generation framework that extends autoregressive (AR) next-token prediction from discrete tokens to continuous audio latents: a thin flow-matching head replaces the softmax to predict rectified-flow velocities at each position, and a block-causal AR-Flow attention pattern produces arbitrary-length output. Joint tr","authors_text":"Bin Ma, Huadai Liu, Kaicheng Luo, Qian Chen, Wei Xue, Wen Wang, Xiangang Li","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-22T09:30:02Z","title":"AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23080","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":"sha256:5c1b90c65082fdeb14cd00af7d6c0c010fe35a83d0c2ab4e32c229d6fc8cb6d2","target":"record","created_at":"2026-06-23T03:14:09Z","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":"7f23aeaefc5d68c2bfbad74073acb42b645582bbe5186337b06d9f1c4b534f57","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-22T09:30:02Z","title_canon_sha256":"a7b4ba98bd44104fc6575455e105a6fe023a75c8bd6d28fb0a0cd2a5cb8d0aca"},"schema_version":"1.0","source":{"id":"2606.23080","kind":"arxiv","version":1}},"canonical_sha256":"aa46389b9081d4045389fdc45b7061621210f950e111f33c967127942e9e66b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa46389b9081d4045389fdc45b7061621210f950e111f33c967127942e9e66b8","first_computed_at":"2026-06-23T03:14:09.297855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:09.297855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/0hTQ8OVlGFEf5ynTLaUv3HBkiBAQj1EitmhAljIfSfesRgoM6hplWUFtKzWZN7QexkpJhTO1CWrwFsxU4PPBw==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:09.298266Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c1b90c65082fdeb14cd00af7d6c0c010fe35a83d0c2ab4e32c229d6fc8cb6d2","sha256:d411d75f1fe967176fd1fa1856949bb46431d7f1c15af1bea84a378a79baa104"],"state_sha256":"9a5f117a9f77c4309704dc21fadd2b09ee60ccf6e1143daf1e9fa6f7b012e737"}