{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:36QIVER2WUTIJBVJJDYKCKVHDG","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":"582f0ec090fb71f41d69c3fdc720a012cb4262952b4926fd22574008f5ec25b3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T14:40:21Z","title_canon_sha256":"c6ba479dd4b728559c5b5fb5786ad43abee20b3b812f74e362e6f67f4778803b"},"schema_version":"1.0","source":{"id":"2607.02633","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02633","created_at":"2026-07-07T00:16:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02633v1","created_at":"2026-07-07T00:16:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02633","created_at":"2026-07-07T00:16:04Z"},{"alias_kind":"pith_short_12","alias_value":"36QIVER2WUTI","created_at":"2026-07-07T00:16:04Z"},{"alias_kind":"pith_short_16","alias_value":"36QIVER2WUTIJBVJ","created_at":"2026-07-07T00:16:04Z"},{"alias_kind":"pith_short_8","alias_value":"36QIVER2","created_at":"2026-07-07T00:16:04Z"}],"graph_snapshots":[{"event_id":"sha256:06ab772d57f2020242ec926b72e9ebc245bfdf0dc950cf179b76b9e0d6ba83d3","target":"graph","created_at":"2026-07-07T00:16:04Z","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/2607.02633/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present GRAFT, a per-word pronunciation conditioning mechanism for text-to-speech neural codec language modeling. Existing systems reach high intelligibility and naturalness but inherit the ambiguity of text and mispronounce rare proper nouns, loanwords and technical terms. Even phoneme-conditioned models offer no direct acoustic handle for per-word pronunciation. GRAFT controls the pronunciation of a chosen word from a short spoken sample of it, encoded with the model's own speech tokenizer and bound to the word's position in the prompt. Voice conversion during training-data construction d","authors_text":"Antonis Asonitis, Aref Farhadipour, Francesco Verdini, Juan Pablo Zuluaga Gomez, Marzieh Razavi, Pierre-Edouard Honnet, Vijeta Avijeet","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T14:40:21Z","title":"GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02633","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":"sha256:9745c2e3558cade6931bdf6085ebf0496aabc131dce65a3533d9b0ad2c02597f","target":"record","created_at":"2026-07-07T00:16:04Z","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":"582f0ec090fb71f41d69c3fdc720a012cb4262952b4926fd22574008f5ec25b3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T14:40:21Z","title_canon_sha256":"c6ba479dd4b728559c5b5fb5786ad43abee20b3b812f74e362e6f67f4778803b"},"schema_version":"1.0","source":{"id":"2607.02633","kind":"arxiv","version":1}},"canonical_sha256":"dfa08a923ab5268486a948f0a12aa719a6fbce5f661ed049d007f003e6f698ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfa08a923ab5268486a948f0a12aa719a6fbce5f661ed049d007f003e6f698ff","first_computed_at":"2026-07-07T00:16:04.529249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T00:16:04.529249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4g1RGgtDxWqjhDMA1IxdjPhJiIeKAa/9RpX73U8LF9hpTR07FkU814OsKlQkSLBSXxMqrAdKtgEv6JXX5A8oDw==","signature_status":"signed_v1","signed_at":"2026-07-07T00:16:04.529846Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02633","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9745c2e3558cade6931bdf6085ebf0496aabc131dce65a3533d9b0ad2c02597f","sha256:06ab772d57f2020242ec926b72e9ebc245bfdf0dc950cf179b76b9e0d6ba83d3"],"state_sha256":"d9c6b5cb40c0d08bd270f7b30aee6d526aa8350811d5feaf27267ec99f0d2a67"}