{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T7WQMN44URU4O4T5IUJB3HDTUZ","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":"c84187c979e988dc0065ee34c615a12fbdeb3df488910004cfca6259f9ae6d88","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-26T19:20:01Z","title_canon_sha256":"c58b5a9d6f45e8f398b7bbdf92b81e84ece0037c71a9179dfd69ae8fd2d3fde1"},"schema_version":"1.0","source":{"id":"2607.23811","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23811","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23811v1","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23811","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"pith_short_12","alias_value":"T7WQMN44URU4","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"pith_short_16","alias_value":"T7WQMN44URU4O4T5","created_at":"2026-07-28T01:23:12Z"},{"alias_kind":"pith_short_8","alias_value":"T7WQMN44","created_at":"2026-07-28T01:23:12Z"}],"graph_snapshots":[{"event_id":"sha256:61e7bebe125d53ea1ba31220bbe5468dd5c9701ba9c4bd12014291719cdbbd86","target":"graph","created_at":"2026-07-28T01:23:12Z","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/2607.23811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple's most powerful on-device foundation model. This work presents the memory-efficient audio synthesis architecture behind that capability: a detokenizer that converts the semantic audio tokens emitted by the foundation model into high-fidelity audio within the tight compute and memory budget of the Apple Matrix Coprocessor (AMX). We convert semantic audio tokens to a residual vector quantization (RVQ) representation with a three-component design, a streaming enco","authors_text":"Chung-Cheng Chiu, Dipjyoti Paul, Dongseong Hwang, Emad Soroush, Kaan Elgin, Prasanth Yadla, Ramya Rasipuram, Shifas Padinjaru Veettil, Sivanand Achanta, Tyler Johnson, Zhifeng Chen","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-26T19:20:01Z","title":"Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23811","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:ffc76c7f5b24cc8c910ca6f2c492b2655295ff163cc7028cb18563645796f98f","target":"record","created_at":"2026-07-28T01:23:12Z","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":"c84187c979e988dc0065ee34c615a12fbdeb3df488910004cfca6259f9ae6d88","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-26T19:20:01Z","title_canon_sha256":"c58b5a9d6f45e8f398b7bbdf92b81e84ece0037c71a9179dfd69ae8fd2d3fde1"},"schema_version":"1.0","source":{"id":"2607.23811","kind":"arxiv","version":1}},"canonical_sha256":"9fed06379ca469c7727d45121d9c73a654c425df6de3492a9885b6bdb9969b64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fed06379ca469c7727d45121d9c73a654c425df6de3492a9885b6bdb9969b64","first_computed_at":"2026-07-28T01:23:12.380862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:12.380862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IWGH8Hj0Ne65o4zDhqvkrNPdtM5vSOZOrJfJ9hq+x5UShAsMn3rZjsidEXOgirGhN5ksy9qg5GYggjSnFghCAA==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:12.381677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23811","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffc76c7f5b24cc8c910ca6f2c492b2655295ff163cc7028cb18563645796f98f","sha256:61e7bebe125d53ea1ba31220bbe5468dd5c9701ba9c4bd12014291719cdbbd86"],"state_sha256":"f06a003d04ca6c434eb124573a9d7074511e33d1aa746bdd84a5f869a66995e9"}