{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GVV5VQ4VXXFEJEDHUR644VNWMO","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":"680df17ce50393bd8da84a85f5f0aae770c8d14a4bb5a226a0c2f75c7c8bc3bb","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-10T08:41:42Z","title_canon_sha256":"e8914e5fa2e113da7725dd916d29d3ff1e7e84ba99d0c38966159d739f59d043"},"schema_version":"1.0","source":{"id":"2501.05787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05787","created_at":"2026-07-05T09:59:28Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05787v1","created_at":"2026-07-05T09:59:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05787","created_at":"2026-07-05T09:59:28Z"},{"alias_kind":"pith_short_12","alias_value":"GVV5VQ4VXXFE","created_at":"2026-07-05T09:59:28Z"},{"alias_kind":"pith_short_16","alias_value":"GVV5VQ4VXXFEJEDH","created_at":"2026-07-05T09:59:28Z"},{"alias_kind":"pith_short_8","alias_value":"GVV5VQ4V","created_at":"2026-07-05T09:59:28Z"}],"graph_snapshots":[{"event_id":"sha256:ca70e2ac4bcd61c128d4e019ae9cb50e7d5fa6c91338dd0f2ccf2b2d66b183db","target":"graph","created_at":"2026-07-05T09:59:28Z","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/2501.05787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Codec-based text-to-speech (TTS) models have shown impressive quality with zero-shot voice cloning abilities. However, they often struggle with more expressive references or complex text inputs. We present MARS6, a robust encoder-decoder transformer for rapid, expressive TTS. MARS6 is built on recent improvements in spoken language modelling. Utilizing a hierarchical setup for its decoder, new speech tokens are processed at a rate of only 12 Hz, enabling efficient modelling of long-form text while retaining reconstruction quality. We combine several recent training and inference techniques to ","authors_text":"Akshat Prakash, Arnav Mehta, Elliott Dyson, Herman Kamper, Matthew Baas, Pieter Scholtz","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-10T08:41:42Z","title":"MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05787","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":"sha256:2ef0ee7279e61d5d0c838f86c2368650a8871a663f08df4925faa04ec9da8e51","target":"record","created_at":"2026-07-05T09:59:28Z","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":"680df17ce50393bd8da84a85f5f0aae770c8d14a4bb5a226a0c2f75c7c8bc3bb","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-10T08:41:42Z","title_canon_sha256":"e8914e5fa2e113da7725dd916d29d3ff1e7e84ba99d0c38966159d739f59d043"},"schema_version":"1.0","source":{"id":"2501.05787","kind":"arxiv","version":1}},"canonical_sha256":"356bdac395bdca449067a47dce55b663a97f3ce11c83780ffb6cb4b9aa6461a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"356bdac395bdca449067a47dce55b663a97f3ce11c83780ffb6cb4b9aa6461a9","first_computed_at":"2026-07-05T09:59:28.696484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:28.696484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TRkyK6oHC1a+KBaV05/OyM9f434fHIyOKGYqqIQuCrVUucR9teEbA/sy+bDzP8krXBvLVGo12O25Xw6/cMAaDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:28.696891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ef0ee7279e61d5d0c838f86c2368650a8871a663f08df4925faa04ec9da8e51","sha256:ca70e2ac4bcd61c128d4e019ae9cb50e7d5fa6c91338dd0f2ccf2b2d66b183db"],"state_sha256":"c0d0800c5441d133953467fbc308ec1c46d7151fc9478914fd1b0c297cabecc9"}