{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZWBTOYKBJPY6DUHGM2VY3FBTAL","short_pith_number":"pith:ZWBTOYKB","schema_version":"1.0","canonical_sha256":"cd833761414bf1e1d0e666ab8d943302fe4c4558425cf695ba2b05846ce33abc","source":{"kind":"arxiv","id":"2606.19325","version":1},"attestation_state":"computed","paper":{"title":"Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.SD","authors_text":"Benjamin Brazowski, Daniel Segal, Eitan Richardson, Michael Finkelson, Nani Goldring, Nir Zabari, Or Patashnik, Poriya Panet, Shahar Armon, Yoav HaCohen","submitted_at":"2026-06-17T17:51:50Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.19325","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-17T17:51:50Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"54bd80f75577bfb2e9e91d208c69c1367ef0c8fe755cce000b8c06b510edec85","abstract_canon_sha256":"31d3dc7dbc359f46be0fe013d485f3f30858053b6620764a6e7416c8a55999b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:11.184193Z","signature_b64":"6pe09ptVCRIR5M5r6wr6d79ydcHxK9wIs316S13AqR+ImKyJ8mXUDVPEG5NXaGoqbOZy+9QMGn52J6/T49TABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd833761414bf1e1d0e666ab8d943302fe4c4558425cf695ba2b05846ce33abc","last_reissued_at":"2026-06-19T16:12:11.183857Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:11.183857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.SD","authors_text":"Benjamin Brazowski, Daniel Segal, Eitan Richardson, Michael Finkelson, Nani Goldring, Nir Zabari, Or Patashnik, Poriya Panet, Shahar Armon, Yoav HaCohen","submitted_at":"2026-06-17T17:51:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19325","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.19325/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.19325","created_at":"2026-06-19T16:12:11.183917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19325v1","created_at":"2026-06-19T16:12:11.183917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19325","created_at":"2026-06-19T16:12:11.183917+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWBTOYKBJPY6","created_at":"2026-06-19T16:12:11.183917+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWBTOYKBJPY6DUHG","created_at":"2026-06-19T16:12:11.183917+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWBTOYKB","created_at":"2026-06-19T16:12:11.183917+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWBTOYKBJPY6DUHGM2VY3FBTAL","json":"https://pith.science/pith/ZWBTOYKBJPY6DUHGM2VY3FBTAL.json","graph_json":"https://pith.science/api/pith-number/ZWBTOYKBJPY6DUHGM2VY3FBTAL/graph.json","events_json":"https://pith.science/api/pith-number/ZWBTOYKBJPY6DUHGM2VY3FBTAL/events.json","paper":"https://pith.science/paper/ZWBTOYKB"},"agent_actions":{"view_html":"https://pith.science/pith/ZWBTOYKBJPY6DUHGM2VY3FBTAL","download_json":"https://pith.science/pith/ZWBTOYKBJPY6DUHGM2VY3FBTAL.json","view_paper":"https://pith.science/paper/ZWBTOYKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19325&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWBTOYKBJPY6DUHGM2VY3FBTAL/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWBTOYKBJPY6DUHGM2VY3FBTAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWBTOYKBJPY6DUHGM2VY3FBTAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWBTOYKBJPY6DUHGM2VY3FBTAL/action/storage_attestation","attest_author":"https://pith.science/pith/ZWBTOYKBJPY6DUHGM2VY3FBTAL/action/author_attestation","sign_citation":"https://pith.science/pith/ZWBTOYKBJPY6DUHGM2VY3FBTAL/action/citation_signature","submit_replication":"https://pith.science/pith/ZWBTOYKBJPY6DUHGM2VY3FBTAL/action/replication_record"}},"created_at":"2026-06-19T16:12:11.183917+00:00","updated_at":"2026-06-19T16:12:11.183917+00:00"}