{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3VDZDIHWCRHMW542YAPNJWDDU4","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":"216e07ebcc5c05947f1be26909cd763a15d1d406103ce218a3314acd92e10cad","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T18:09:37Z","title_canon_sha256":"e8eed618ae8badce98b6e89abdcdbab93878ac5b3a1a47b611501b2b6ede75b1"},"schema_version":"1.0","source":{"id":"2606.10029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10029","created_at":"2026-06-10T00:08:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10029v1","created_at":"2026-06-10T00:08:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10029","created_at":"2026-06-10T00:08:45Z"},{"alias_kind":"pith_short_12","alias_value":"3VDZDIHWCRHM","created_at":"2026-06-10T00:08:45Z"},{"alias_kind":"pith_short_16","alias_value":"3VDZDIHWCRHMW542","created_at":"2026-06-10T00:08:45Z"},{"alias_kind":"pith_short_8","alias_value":"3VDZDIHW","created_at":"2026-06-10T00:08:45Z"}],"graph_snapshots":[{"event_id":"sha256:798f3f0ea63ba000614a2c88216a925ec8b3b34f481e15e9b4865a6fcae6abe0","target":"graph","created_at":"2026-06-10T00:08:45Z","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/2606.10029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models increasingly serve as the backbone of text-to-speech (TTS) systems, yet we understand little about the representations they build when text and generated speech tokens share a single residual stream. We train BatchTopK sparse autoencoders on the LM backbone of CosyVoice3 and introduce a modality-aware auto-interp pipeline that labels each feature from where it fires-text-prefix context, 1-second speech clips, or both. The recovered features are interpretable, spanning phonemes, laughter, accent prompts and speaker gender. Steering through the SAE latent space shows these featur","authors_text":"Daniil Gavrilov, Georgii Aparin, Nikita Balagansky, Nikita Koriagin","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T18:09:37Z","title":"Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10029","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:d994d6dbf075e433f29ef342ad0edac69de6d36a6a256618a566871d2a83bf2a","target":"record","created_at":"2026-06-10T00:08:45Z","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":"216e07ebcc5c05947f1be26909cd763a15d1d406103ce218a3314acd92e10cad","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T18:09:37Z","title_canon_sha256":"e8eed618ae8badce98b6e89abdcdbab93878ac5b3a1a47b611501b2b6ede75b1"},"schema_version":"1.0","source":{"id":"2606.10029","kind":"arxiv","version":1}},"canonical_sha256":"dd4791a0f6144ecb779ac01ed4d863a73948847bdf4f43df55f34b121d6ae818","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd4791a0f6144ecb779ac01ed4d863a73948847bdf4f43df55f34b121d6ae818","first_computed_at":"2026-06-10T00:08:45.384192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T00:08:45.384192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j+SfXrz3KeWq4dxv2B9KzUdbpbfe2TAwh99w3xdRoPgcUqYh8z0jQlldhy7en6GPDU9yLjjOY4lsCmEv29DuBA==","signature_status":"signed_v1","signed_at":"2026-06-10T00:08:45.385069Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d994d6dbf075e433f29ef342ad0edac69de6d36a6a256618a566871d2a83bf2a","sha256:798f3f0ea63ba000614a2c88216a925ec8b3b34f481e15e9b4865a6fcae6abe0"],"state_sha256":"2aa43f1f04ed04e7acddcdc5aca09971e7c5641f5a5de7a68603bd44f4851019"}