{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:U7OBJS3L3UX7L5V7MFNSQU57IT","short_pith_number":"pith:U7OBJS3L","canonical_record":{"source":{"id":"2303.03926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-07T14:31:55Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"03a443cdf0ef40686cf9bb192b3485e9d64260c7a9a961e7632601d23e1f3afc","abstract_canon_sha256":"6c1905f7b6cc16cd2c17c9a2d7f23666570ee3d30283a0452dcb01d0e0b5f390"},"schema_version":"1.0"},"canonical_sha256":"a7dc14cb6bdd2ff5f6bf615b2853bf44f2a7ca8a1985d0400643c3022ec8c1cb","source":{"kind":"arxiv","id":"2303.03926","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.03926","created_at":"2026-07-05T05:49:01Z"},{"alias_kind":"arxiv_version","alias_value":"2303.03926v1","created_at":"2026-07-05T05:49:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03926","created_at":"2026-07-05T05:49:01Z"},{"alias_kind":"pith_short_12","alias_value":"U7OBJS3L3UX7","created_at":"2026-07-05T05:49:01Z"},{"alias_kind":"pith_short_16","alias_value":"U7OBJS3L3UX7L5V7","created_at":"2026-07-05T05:49:01Z"},{"alias_kind":"pith_short_8","alias_value":"U7OBJS3L","created_at":"2026-07-05T05:49:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:U7OBJS3L3UX7L5V7MFNSQU57IT","target":"record","payload":{"canonical_record":{"source":{"id":"2303.03926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-07T14:31:55Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"03a443cdf0ef40686cf9bb192b3485e9d64260c7a9a961e7632601d23e1f3afc","abstract_canon_sha256":"6c1905f7b6cc16cd2c17c9a2d7f23666570ee3d30283a0452dcb01d0e0b5f390"},"schema_version":"1.0"},"canonical_sha256":"a7dc14cb6bdd2ff5f6bf615b2853bf44f2a7ca8a1985d0400643c3022ec8c1cb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:01.078479Z","signature_b64":"DuuJjgZNAWAN+V5MBH5HRHBeHkf7z17LtY5lcVjKDPXNO99RP6Btbfoc9U171HALrlpsDrPLMVfj4LwQ9VGqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7dc14cb6bdd2ff5f6bf615b2853bf44f2a7ca8a1985d0400643c3022ec8c1cb","last_reissued_at":"2026-07-05T05:49:01.078011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:01.078011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.03926","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":"2026-07-05T05:49:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/MY4zEBVt+qZwnVnHXfGemCdFgmGChKeNwfU8CAjIGUuahRfnC9ZgLW9WSY9k7nqQozUVvJyUVtQoKvAC7zEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T06:16:09.556922Z"},"content_sha256":"f283694de7f809bcad8ab0dcd19d65b50e2205a09a3744ca58bac4e590de3cf0","schema_version":"1.0","event_id":"sha256:f283694de7f809bcad8ab0dcd19d65b50e2205a09a3744ca58bac4e590de3cf0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:U7OBJS3L3UX7L5V7MFNSQU57IT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chengyi Wang, Furu Wei, Huaming Wang, Jinyu Li, Lei He, Long Zhou, Sanyuan Chen, Sheng Zhao, Shujie Liu, Yanqing Liu, Yu Wu, Zhuo Chen, Ziqiang Zhang","submitted_at":"2023-03-07T14:31:55Z","abstract_excerpt":"We propose a cross-lingual neural codec language model, VALL-E X, for cross-lingual speech synthesis. Specifically, we extend VALL-E and train a multi-lingual conditional codec language model to predict the acoustic token sequences of the target language speech by using both the source language speech and the target language text as prompts. VALL-E X inherits strong in-context learning capabilities and can be applied for zero-shot cross-lingual text-to-speech synthesis and zero-shot speech-to-speech translation tasks. Experimental results show that it can generate high-quality speech in the ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03926","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/2303.03926/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":"2026-07-05T05:49:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"557F6CBBdYqgC8E36pzADsgvuVkFpBpZU70wRb5ws+n5TxqO8QvLs4rSH6Ou82GGXS0mtg0RFn9+OVwOqW2NBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T06:16:09.557310Z"},"content_sha256":"3944acf0bc6443e02854c1fc235412af45821b87f6db56b51811e1d281084a91","schema_version":"1.0","event_id":"sha256:3944acf0bc6443e02854c1fc235412af45821b87f6db56b51811e1d281084a91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U7OBJS3L3UX7L5V7MFNSQU57IT/bundle.json","state_url":"https://pith.science/pith/U7OBJS3L3UX7L5V7MFNSQU57IT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U7OBJS3L3UX7L5V7MFNSQU57IT/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":"2026-07-28T06:16:09Z","links":{"resolver":"https://pith.science/pith/U7OBJS3L3UX7L5V7MFNSQU57IT","bundle":"https://pith.science/pith/U7OBJS3L3UX7L5V7MFNSQU57IT/bundle.json","state":"https://pith.science/pith/U7OBJS3L3UX7L5V7MFNSQU57IT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U7OBJS3L3UX7L5V7MFNSQU57IT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:U7OBJS3L3UX7L5V7MFNSQU57IT","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":"6c1905f7b6cc16cd2c17c9a2d7f23666570ee3d30283a0452dcb01d0e0b5f390","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-07T14:31:55Z","title_canon_sha256":"03a443cdf0ef40686cf9bb192b3485e9d64260c7a9a961e7632601d23e1f3afc"},"schema_version":"1.0","source":{"id":"2303.03926","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.03926","created_at":"2026-07-05T05:49:01Z"},{"alias_kind":"arxiv_version","alias_value":"2303.03926v1","created_at":"2026-07-05T05:49:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03926","created_at":"2026-07-05T05:49:01Z"},{"alias_kind":"pith_short_12","alias_value":"U7OBJS3L3UX7","created_at":"2026-07-05T05:49:01Z"},{"alias_kind":"pith_short_16","alias_value":"U7OBJS3L3UX7L5V7","created_at":"2026-07-05T05:49:01Z"},{"alias_kind":"pith_short_8","alias_value":"U7OBJS3L","created_at":"2026-07-05T05:49:01Z"}],"graph_snapshots":[{"event_id":"sha256:3944acf0bc6443e02854c1fc235412af45821b87f6db56b51811e1d281084a91","target":"graph","created_at":"2026-07-05T05:49:01Z","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/2303.03926/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a cross-lingual neural codec language model, VALL-E X, for cross-lingual speech synthesis. Specifically, we extend VALL-E and train a multi-lingual conditional codec language model to predict the acoustic token sequences of the target language speech by using both the source language speech and the target language text as prompts. VALL-E X inherits strong in-context learning capabilities and can be applied for zero-shot cross-lingual text-to-speech synthesis and zero-shot speech-to-speech translation tasks. Experimental results show that it can generate high-quality speech in the ta","authors_text":"Chengyi Wang, Furu Wei, Huaming Wang, Jinyu Li, Lei He, Long Zhou, Sanyuan Chen, Sheng Zhao, Shujie Liu, Yanqing Liu, Yu Wu, Zhuo Chen, Ziqiang Zhang","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-07T14:31:55Z","title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03926","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:f283694de7f809bcad8ab0dcd19d65b50e2205a09a3744ca58bac4e590de3cf0","target":"record","created_at":"2026-07-05T05:49:01Z","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":"6c1905f7b6cc16cd2c17c9a2d7f23666570ee3d30283a0452dcb01d0e0b5f390","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-07T14:31:55Z","title_canon_sha256":"03a443cdf0ef40686cf9bb192b3485e9d64260c7a9a961e7632601d23e1f3afc"},"schema_version":"1.0","source":{"id":"2303.03926","kind":"arxiv","version":1}},"canonical_sha256":"a7dc14cb6bdd2ff5f6bf615b2853bf44f2a7ca8a1985d0400643c3022ec8c1cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7dc14cb6bdd2ff5f6bf615b2853bf44f2a7ca8a1985d0400643c3022ec8c1cb","first_computed_at":"2026-07-05T05:49:01.078011Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:01.078011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DuuJjgZNAWAN+V5MBH5HRHBeHkf7z17LtY5lcVjKDPXNO99RP6Btbfoc9U171HALrlpsDrPLMVfj4LwQ9VGqAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:01.078479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.03926","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f283694de7f809bcad8ab0dcd19d65b50e2205a09a3744ca58bac4e590de3cf0","sha256:3944acf0bc6443e02854c1fc235412af45821b87f6db56b51811e1d281084a91"],"state_sha256":"ae341c91844a5645ac04494b18097e444e6853140c76ce3d6ff901e1dc4cd757"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ceRXkpoI+BglU+lkc6QxV2OLMB5qPHuqlXYgaPiexx+qJXZOQi0lXddmIdSS1BMdNYquO+EBxMTKKDzUbUWRBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-28T06:16:09.559544Z","bundle_sha256":"0579c1a0941589f740636d73a871aad908799a8f824ff75ca5f2657edd910aff"}}