{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LNDSXX4T6HKDXC7KTXCGWKUBUQ","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":"762ec7064a8c1880ced3b120dde264c39a36ae8ea2a287bc7f37b0edff95a561","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-16T16:34:35Z","title_canon_sha256":"141ffc09789893e1087a3cacf6af79da531fc35f4a3f024ba75800df1a8a0e3d"},"schema_version":"1.0","source":{"id":"2606.18134","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18134","created_at":"2026-06-19T16:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18134v1","created_at":"2026-06-19T16:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18134","created_at":"2026-06-19T16:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"LNDSXX4T6HKD","created_at":"2026-06-19T16:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"LNDSXX4T6HKDXC7K","created_at":"2026-06-19T16:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"LNDSXX4T","created_at":"2026-06-19T16:10:49Z"}],"graph_snapshots":[{"event_id":"sha256:6afadc667eaad0076db45945133e8bc35548284a1c7ce8d3f46e7c3d62ee1df8","target":"graph","created_at":"2026-06-19T16:10:49Z","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/2606.18134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose diarization-conditioned spoken language models (SLMs), a strategy for extending SLMs to far-field multi-talker audio. Rather than adapting the decoder via Serialized Output Training, which risks catastrophic forgetting, we condition the acoustic encoder on diarization masks to extract target-speaker representations, keeping the decoder frozen. We instantiate this as Dixtral, integrating a Diarization Conditioned Whisper (DiCoW) encoder into the Voxtral SLM. On AMI, NOTSOFAR-1, LibriSpeechMix, and Mixer6, Dixtral outperforms Gemini 3.0 Flash, VibeVoice, and Voxtral Mini Transcribe V2","authors_text":"Alexander Polok, Jan \\v{C}ernock\\'y, Luk\\'a\\v{s} Burget, Samuele Cornell, Sathvik Udupa, Shinji Watanabe","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-16T16:34:35Z","title":"Grounding Spoken LLMs in Multi-Speaker Audio via Diarization Conditioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18134","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":"sha256:877b0158226db068ef8852649d8773f309a7e1968d7714fb54ef979778616e6c","target":"record","created_at":"2026-06-19T16:10:49Z","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":"762ec7064a8c1880ced3b120dde264c39a36ae8ea2a287bc7f37b0edff95a561","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-16T16:34:35Z","title_canon_sha256":"141ffc09789893e1087a3cacf6af79da531fc35f4a3f024ba75800df1a8a0e3d"},"schema_version":"1.0","source":{"id":"2606.18134","kind":"arxiv","version":1}},"canonical_sha256":"5b472bdf93f1d43b8bea9dc46b2a81a43467173aa714be9ad3f63e86e426d36e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b472bdf93f1d43b8bea9dc46b2a81a43467173aa714be9ad3f63e86e426d36e","first_computed_at":"2026-06-19T16:10:49.271506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:49.271506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Je6Frgyr9Yhx5sf5a+ZpqEpynxhIRiOKskU9ahQhmlJ+9misvm9tlH7ZDRDuOqVEirDZXGO5nV3kikUmiLBpAw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:49.271864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18134","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:877b0158226db068ef8852649d8773f309a7e1968d7714fb54ef979778616e6c","sha256:6afadc667eaad0076db45945133e8bc35548284a1c7ce8d3f46e7c3d62ee1df8"],"state_sha256":"913438bb172e9ac8445a209768df362818d287c73e7d94823386057301e18ed9"}