{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZWBTOYKBJPY6DUHGM2VY3FBTAL","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":"31d3dc7dbc359f46be0fe013d485f3f30858053b6620764a6e7416c8a55999b5","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-17T17:51:50Z","title_canon_sha256":"54bd80f75577bfb2e9e91d208c69c1367ef0c8fe755cce000b8c06b510edec85"},"schema_version":"1.0","source":{"id":"2606.19325","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19325","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19325v1","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19325","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZWBTOYKBJPY6","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"ZWBTOYKBJPY6DUHG","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"ZWBTOYKB","created_at":"2026-06-19T16:12:11Z"}],"graph_snapshots":[{"event_id":"sha256:342c4f082029d9d90d770a3f0a0c83f1ee88cdb79b4da68759c2decf93a34248","target":"graph","created_at":"2026-06-19T16:12:11Z","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/2606.19325/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings. These systems operate within speech-only pipelines that produce clean vocal sequences without the ambient texture of real conversations. We take a different approach. Our method, ScenA, conditions a text-to-audio flow-matching foundation model, pretrained on large-scale in-the-wild data, directly on multiple reference voices and a free-form natural language prompt that describes an entire multi-speaker audio scene. Leve","authors_text":"Benjamin Brazowski, Daniel Segal, Eitan Richardson, Michael Finkelson, Nani Goldring, Nir Zabari, Or Patashnik, Poriya Panet, Shahar Armon, Yoav HaCohen","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-17T17:51:50Z","title":"Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19325","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:de367fcaf6f46a9af3489e784e74b5bffacad901174a1e72b24c399708ae6277","target":"record","created_at":"2026-06-19T16:12:11Z","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":"31d3dc7dbc359f46be0fe013d485f3f30858053b6620764a6e7416c8a55999b5","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-17T17:51:50Z","title_canon_sha256":"54bd80f75577bfb2e9e91d208c69c1367ef0c8fe755cce000b8c06b510edec85"},"schema_version":"1.0","source":{"id":"2606.19325","kind":"arxiv","version":1}},"canonical_sha256":"cd833761414bf1e1d0e666ab8d943302fe4c4558425cf695ba2b05846ce33abc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd833761414bf1e1d0e666ab8d943302fe4c4558425cf695ba2b05846ce33abc","first_computed_at":"2026-06-19T16:12:11.183857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:11.183857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6pe09ptVCRIR5M5r6wr6d79ydcHxK9wIs316S13AqR+ImKyJ8mXUDVPEG5NXaGoqbOZy+9QMGn52J6/T49TABw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:11.184193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19325","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de367fcaf6f46a9af3489e784e74b5bffacad901174a1e72b24c399708ae6277","sha256:342c4f082029d9d90d770a3f0a0c83f1ee88cdb79b4da68759c2decf93a34248"],"state_sha256":"d5649a6738c1f9c06a2213d4b2c7cc6d08897f3e99fed5cfe692454330e261ee"}