{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D653BWCJILWHIRMKXIGRA6O6IX","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":"3bf39a626b2f734ea0ebe00c575ec23d468719d92daa9d23b55044be99c8255e","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-08-12T08:46:28Z","title_canon_sha256":"5f378a3c5306a3707e2a25f6e8f614b18909e4bea03ccfb0933525100c085b79"},"schema_version":"1.0","source":{"id":"2608.11804","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11804","created_at":"2026-08-13T01:28:17Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11804v1","created_at":"2026-08-13T01:28:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11804","created_at":"2026-08-13T01:28:17Z"},{"alias_kind":"pith_short_12","alias_value":"D653BWCJILWH","created_at":"2026-08-13T01:28:17Z"},{"alias_kind":"pith_short_16","alias_value":"D653BWCJILWHIRMK","created_at":"2026-08-13T01:28:17Z"},{"alias_kind":"pith_short_8","alias_value":"D653BWCJ","created_at":"2026-08-13T01:28:17Z"}],"graph_snapshots":[{"event_id":"sha256:5dae707cbb2219e5ff05eac743c80f4ac573310124b0545271608066b447e326","target":"graph","created_at":"2026-08-13T01:28:17Z","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/2608.11804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating coherent audio scenes that simultaneously blend speech, music, and sound effects remains a significant challenge. Current approaches typically rely on a disjointed pipeline where a frozen, decoupled text encoder feeds a separate audio decoder, limiting cross-modal optimization and leading to poor speech intelligibility. To overcome these limitations, we introduce MiDashengLM-Gen, an end-to-end framework that couples a pre-trained Large Language Model (LLM) with per-token conditional flow matching for autoregressive, variable-length mixed-audio scene generation. MiDashengLM-Gen repre","authors_text":"Gang Li, Heinrich Dinkel, Jiahao Mei, Jiahao Zhou, Jian Luan, Lichun Fan, Xingwei Sun, Yadong Niu, Yuepeng Jiang, Zerui Han","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-08-12T08:46:28Z","title":"MiDashengLM-Gen: Unified Audio Scene Generation via LLM-Driven Autoregressive Flow Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11804","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:fe70642cf495435e4bfd532760ef4b8c781e64f91e0390e3c1a64e4da5f6f605","target":"record","created_at":"2026-08-13T01:28:17Z","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":"3bf39a626b2f734ea0ebe00c575ec23d468719d92daa9d23b55044be99c8255e","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-08-12T08:46:28Z","title_canon_sha256":"5f378a3c5306a3707e2a25f6e8f614b18909e4bea03ccfb0933525100c085b79"},"schema_version":"1.0","source":{"id":"2608.11804","kind":"arxiv","version":1}},"canonical_sha256":"1fbbb0d84942ec74458aba0d1079de45d6915c6de8b7679d0af1f8a0b08ed957","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fbbb0d84942ec74458aba0d1079de45d6915c6de8b7679d0af1f8a0b08ed957","first_computed_at":"2026-08-13T01:28:17.521177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T01:28:17.521177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"evmH22CqqHbZMAvaW72DhTHftCMpV4RTKjWOSA0G55YV7ZFG1E9BgASXPSdFDxUnu/u1KtLGLhb0JRY9RmegBw==","signature_status":"signed_v1","signed_at":"2026-08-13T01:28:17.523394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11804","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe70642cf495435e4bfd532760ef4b8c781e64f91e0390e3c1a64e4da5f6f605","sha256:5dae707cbb2219e5ff05eac743c80f4ac573310124b0545271608066b447e326"],"state_sha256":"f0fad1bcbb8c3c0d5a997d8e0bfc816e7d688f1a69f4a1f5a18209acac3f81ba"}