{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:36QIVER2WUTIJBVJJDYKCKVHDG","short_pith_number":"pith:36QIVER2","canonical_record":{"source":{"id":"2607.02633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T14:40:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c6ba479dd4b728559c5b5fb5786ad43abee20b3b812f74e362e6f67f4778803b","abstract_canon_sha256":"582f0ec090fb71f41d69c3fdc720a012cb4262952b4926fd22574008f5ec25b3"},"schema_version":"1.0"},"canonical_sha256":"dfa08a923ab5268486a948f0a12aa719a6fbce5f661ed049d007f003e6f698ff","source":{"kind":"arxiv","id":"2607.02633","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:36QIVER2WUTIJBVJJDYKCKVHDG","target":"record","payload":{"canonical_record":{"source":{"id":"2607.02633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T14:40:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c6ba479dd4b728559c5b5fb5786ad43abee20b3b812f74e362e6f67f4778803b","abstract_canon_sha256":"582f0ec090fb71f41d69c3fdc720a012cb4262952b4926fd22574008f5ec25b3"},"schema_version":"1.0"},"canonical_sha256":"dfa08a923ab5268486a948f0a12aa719a6fbce5f661ed049d007f003e6f698ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T00:16:04.529846Z","signature_b64":"4g1RGgtDxWqjhDMA1IxdjPhJiIeKAa/9RpX73U8LF9hpTR07FkU814OsKlQkSLBSXxMqrAdKtgEv6JXX5A8oDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfa08a923ab5268486a948f0a12aa719a6fbce5f661ed049d007f003e6f698ff","last_reissued_at":"2026-07-07T00:16:04.529249Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T00:16:04.529249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.02633","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T00:16:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Y8JJ+83GfQSXnDfH+DrlG4ICrM/sYMJqT4DkoCMkVthzgmmeWJxWDvmu+J/Gby5opSIWIP0Ino4taWxRlqvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T05:41:44.253293Z"},"content_sha256":"9745c2e3558cade6931bdf6085ebf0496aabc131dce65a3533d9b0ad2c02597f","schema_version":"1.0","event_id":"sha256:9745c2e3558cade6931bdf6085ebf0496aabc131dce65a3533d9b0ad2c02597f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:36QIVER2WUTIJBVJJDYKCKVHDG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Antonis Asonitis, Aref Farhadipour, Francesco Verdini, Juan Pablo Zuluaga Gomez, Marzieh Razavi, Pierre-Edouard Honnet, Vijeta Avijeet","submitted_at":"2026-07-02T14:40:21Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02633","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/2607.02633/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T00:16:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X5aedj17ED9tGFbRq+1Zf0vKi0ZTEWCUmxcK36EINpVsJcS0o0VyznOQnWxwQg8MCR9OtxsH2h4RCTTZ6eUKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T05:41:44.253671Z"},"content_sha256":"06ab772d57f2020242ec926b72e9ebc245bfdf0dc950cf179b76b9e0d6ba83d3","schema_version":"1.0","event_id":"sha256:06ab772d57f2020242ec926b72e9ebc245bfdf0dc950cf179b76b9e0d6ba83d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/36QIVER2WUTIJBVJJDYKCKVHDG/bundle.json","state_url":"https://pith.science/pith/36QIVER2WUTIJBVJJDYKCKVHDG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/36QIVER2WUTIJBVJJDYKCKVHDG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-22T05:41:44Z","links":{"resolver":"https://pith.science/pith/36QIVER2WUTIJBVJJDYKCKVHDG","bundle":"https://pith.science/pith/36QIVER2WUTIJBVJJDYKCKVHDG/bundle.json","state":"https://pith.science/pith/36QIVER2WUTIJBVJJDYKCKVHDG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/36QIVER2WUTIJBVJJDYKCKVHDG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i2n/ypBQuC79f1twbdTCj0obAQSiQpiFEOBjXAV+OjZa7poOYKf9HNUn4FU/FcBn9w1ljuL6Yip5HnsPwSCYAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T05:41:44.256401Z","bundle_sha256":"6a732ebedf3fd84d702609ce39e93afb5f4b9ad01be2e08c26caf5d566938a9e"}}