{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OOPAD5L242XTGWEHUBJPSRMIRI","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":"928db175791b5d07c13a2abdfdf88e1dd582ad320dcb1e5586aa2ddb76d26521","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-05T15:38:08Z","title_canon_sha256":"f6385a9f3112208cd87b54a705081add9dcdec8a39dc432d6b69f1826000e8d7"},"schema_version":"1.0","source":{"id":"2606.07397","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07397","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07397v1","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07397","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"OOPAD5L242XT","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"OOPAD5L242XTGWEH","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"OOPAD5L2","created_at":"2026-06-08T01:05:24Z"}],"graph_snapshots":[{"event_id":"sha256:7fd37cc1dc4acac4851c58780a2e60459a9859d252b7dafc0ef878951fd9c1d4","target":"graph","created_at":"2026-06-08T01:05:24Z","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/2606.07397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, audio generation has made significant progress in tasks such as text-to-speech (TTS), text-to-audio (TTA) and text-to-music (TTM). However, generating long-form and controllable audio from complex audio scene descriptions remains a significant challenge, as such scenes often require coordinated speech, sound effects, music, songs, temporal structure, and post-production. In this work, we introduce \\textbf{Audio-Oscar}, a multi-agent framework for generating audio from complex descriptions. Audio-Oscar coordinates a set of specialist agents, each responsible for a different asp","authors_text":"Hengtao Wu, Junxi Liu, Kelu Xu, Qixiang Xu, Wenhao Guan, Xie Chen, Yifan Duan, Zhanxun Liu, Ziyang Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-05T15:38:08Z","title":"Audio-Oscar: A Multi-Agent System for Complex Audio Scene Generation, Orchestration, and Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07397","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":"sha256:9bc1eccf96595d4d6fdebf1d3e2bb01bc241c0df6c65a9219b825a7fc4e46ff0","target":"record","created_at":"2026-06-08T01:05:24Z","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":"928db175791b5d07c13a2abdfdf88e1dd582ad320dcb1e5586aa2ddb76d26521","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-05T15:38:08Z","title_canon_sha256":"f6385a9f3112208cd87b54a705081add9dcdec8a39dc432d6b69f1826000e8d7"},"schema_version":"1.0","source":{"id":"2606.07397","kind":"arxiv","version":1}},"canonical_sha256":"739e01f57ae6af335887a052f945888a10f1577494868adb0f1e14c4293fe8d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"739e01f57ae6af335887a052f945888a10f1577494868adb0f1e14c4293fe8d5","first_computed_at":"2026-06-08T01:05:24.744570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:05:24.744570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h7IYPJHWlo0/w9NIL8nl1tI8OBvGrBBU6IaK4LUlW/wkTX3EUrk9GQtKKVx/Tju2J/CkMmLVoVrQmFtkbpAgDg==","signature_status":"signed_v1","signed_at":"2026-06-08T01:05:24.745933Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07397","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bc1eccf96595d4d6fdebf1d3e2bb01bc241c0df6c65a9219b825a7fc4e46ff0","sha256:7fd37cc1dc4acac4851c58780a2e60459a9859d252b7dafc0ef878951fd9c1d4"],"state_sha256":"b2588316548da8db2cb9ef7a39214518f26bce1df07496abe72ead55ed8de456"}