{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ACCAWI4DN2C7WQSDK4US6C77ZE","short_pith_number":"pith:ACCAWI4D","canonical_record":{"source":{"id":"2204.03067","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T20:03:38Z","cross_cats_sorted":[],"title_canon_sha256":"667aebff3f15c235da521c21021541782709c4425807913136da21b8a8d060f4","abstract_canon_sha256":"7ea254108eba179741f466f51c8094b072849c979e9d7364c03c4457d29a6e53"},"schema_version":"1.0"},"canonical_sha256":"00840b23836e85fb424357292f0bffc92c80e7ddcc8c52c49e2ec6cbbd156eb4","source":{"kind":"arxiv","id":"2204.03067","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03067","created_at":"2026-07-05T04:37:05Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03067v2","created_at":"2026-07-05T04:37:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03067","created_at":"2026-07-05T04:37:05Z"},{"alias_kind":"pith_short_12","alias_value":"ACCAWI4DN2C7","created_at":"2026-07-05T04:37:05Z"},{"alias_kind":"pith_short_16","alias_value":"ACCAWI4DN2C7WQSD","created_at":"2026-07-05T04:37:05Z"},{"alias_kind":"pith_short_8","alias_value":"ACCAWI4D","created_at":"2026-07-05T04:37:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ACCAWI4DN2C7WQSDK4US6C77ZE","target":"record","payload":{"canonical_record":{"source":{"id":"2204.03067","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T20:03:38Z","cross_cats_sorted":[],"title_canon_sha256":"667aebff3f15c235da521c21021541782709c4425807913136da21b8a8d060f4","abstract_canon_sha256":"7ea254108eba179741f466f51c8094b072849c979e9d7364c03c4457d29a6e53"},"schema_version":"1.0"},"canonical_sha256":"00840b23836e85fb424357292f0bffc92c80e7ddcc8c52c49e2ec6cbbd156eb4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:37:05.420400Z","signature_b64":"+yi7d6XEaMHASPJiE+LW0O2Ko1gZMbjGoxalgFHGBvRWdb5+NLv/izcX8a9L4dSwaJC5FYR45aq1oOg0jvR2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00840b23836e85fb424357292f0bffc92c80e7ddcc8c52c49e2ec6cbbd156eb4","last_reissued_at":"2026-07-05T04:37:05.419908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:37:05.419908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.03067","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:37:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KjaK4gBucjNkiUtsPngIvHVY2STZHghn5XyKICOwG/lyiA2Wj2B9gzLmiUhNX9IBBEEgff3xWvHE+mGivHl3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:05:46.458299Z"},"content_sha256":"b0cd83c4c852f1352920ad6d4e82efff944d2ffd9fa5d6d774cd70de294aca8e","schema_version":"1.0","event_id":"sha256:b0cd83c4c852f1352920ad6d4e82efff944d2ffd9fa5d6d774cd70de294aca8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ACCAWI4DN2C7WQSDK4US6C77ZE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ByT5 model for massively multilingual grapheme-to-phoneme conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cong Zhang, David Jurgens, Jian Zhu","submitted_at":"2022-04-06T20:03:38Z","abstract_excerpt":"In this study, we tackle massively multilingual grapheme-to-phoneme conversion through implementing G2P models based on ByT5. We have curated a G2P dataset from various sources that covers around 100 languages and trained large-scale multilingual G2P models based on ByT5. We found that ByT5 operating on byte-level inputs significantly outperformed the token-based mT5 model in terms of multilingual G2P. Pairwise comparison with monolingual models in these languages suggests that multilingual ByT5 models generally lower the phone error rate by jointly learning from a variety of languages. The pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03067","kind":"arxiv","version":2},"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/2204.03067/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":"2026-07-05T04:37:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SM7iQxFGy0aDtAHCSKCmdCfCoEcpp/lrKY4XP+fScjj5bGXsewcCH/tDNNw+eO7ALqktl9Vz4+0evEdj1oODAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:05:46.458817Z"},"content_sha256":"d3d8101c5bd1b5aa17dc7fac67eedaaab5d0b2d755ebe37b76c95f7dfe49f38a","schema_version":"1.0","event_id":"sha256:d3d8101c5bd1b5aa17dc7fac67eedaaab5d0b2d755ebe37b76c95f7dfe49f38a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACCAWI4DN2C7WQSDK4US6C77ZE/bundle.json","state_url":"https://pith.science/pith/ACCAWI4DN2C7WQSDK4US6C77ZE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACCAWI4DN2C7WQSDK4US6C77ZE/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":"2026-08-08T20:05:46Z","links":{"resolver":"https://pith.science/pith/ACCAWI4DN2C7WQSDK4US6C77ZE","bundle":"https://pith.science/pith/ACCAWI4DN2C7WQSDK4US6C77ZE/bundle.json","state":"https://pith.science/pith/ACCAWI4DN2C7WQSDK4US6C77ZE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACCAWI4DN2C7WQSDK4US6C77ZE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ACCAWI4DN2C7WQSDK4US6C77ZE","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":"7ea254108eba179741f466f51c8094b072849c979e9d7364c03c4457d29a6e53","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T20:03:38Z","title_canon_sha256":"667aebff3f15c235da521c21021541782709c4425807913136da21b8a8d060f4"},"schema_version":"1.0","source":{"id":"2204.03067","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03067","created_at":"2026-07-05T04:37:05Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03067v2","created_at":"2026-07-05T04:37:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03067","created_at":"2026-07-05T04:37:05Z"},{"alias_kind":"pith_short_12","alias_value":"ACCAWI4DN2C7","created_at":"2026-07-05T04:37:05Z"},{"alias_kind":"pith_short_16","alias_value":"ACCAWI4DN2C7WQSD","created_at":"2026-07-05T04:37:05Z"},{"alias_kind":"pith_short_8","alias_value":"ACCAWI4D","created_at":"2026-07-05T04:37:05Z"}],"graph_snapshots":[{"event_id":"sha256:d3d8101c5bd1b5aa17dc7fac67eedaaab5d0b2d755ebe37b76c95f7dfe49f38a","target":"graph","created_at":"2026-07-05T04:37:05Z","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/2204.03067/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we tackle massively multilingual grapheme-to-phoneme conversion through implementing G2P models based on ByT5. We have curated a G2P dataset from various sources that covers around 100 languages and trained large-scale multilingual G2P models based on ByT5. We found that ByT5 operating on byte-level inputs significantly outperformed the token-based mT5 model in terms of multilingual G2P. Pairwise comparison with monolingual models in these languages suggests that multilingual ByT5 models generally lower the phone error rate by jointly learning from a variety of languages. The pr","authors_text":"Cong Zhang, David Jurgens, Jian Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T20:03:38Z","title":"ByT5 model for massively multilingual grapheme-to-phoneme conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03067","kind":"arxiv","version":2},"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:b0cd83c4c852f1352920ad6d4e82efff944d2ffd9fa5d6d774cd70de294aca8e","target":"record","created_at":"2026-07-05T04:37:05Z","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":"7ea254108eba179741f466f51c8094b072849c979e9d7364c03c4457d29a6e53","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T20:03:38Z","title_canon_sha256":"667aebff3f15c235da521c21021541782709c4425807913136da21b8a8d060f4"},"schema_version":"1.0","source":{"id":"2204.03067","kind":"arxiv","version":2}},"canonical_sha256":"00840b23836e85fb424357292f0bffc92c80e7ddcc8c52c49e2ec6cbbd156eb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00840b23836e85fb424357292f0bffc92c80e7ddcc8c52c49e2ec6cbbd156eb4","first_computed_at":"2026-07-05T04:37:05.419908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:37:05.419908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+yi7d6XEaMHASPJiE+LW0O2Ko1gZMbjGoxalgFHGBvRWdb5+NLv/izcX8a9L4dSwaJC5FYR45aq1oOg0jvR2DA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:37:05.420400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.03067","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0cd83c4c852f1352920ad6d4e82efff944d2ffd9fa5d6d774cd70de294aca8e","sha256:d3d8101c5bd1b5aa17dc7fac67eedaaab5d0b2d755ebe37b76c95f7dfe49f38a"],"state_sha256":"39908ba8c00ecc7fb82965843d5ed1570c9ed0fe69ad1dbf43aa72291e7d6b0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IRl3OWvytPiE4SON1iJEwuYw3NfG3FgNNfhs09ODx9bJqPV0y+N4XXzEpVHFAMIeayuaSm6fOOnsu2E/6EotAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:05:46.463709Z","bundle_sha256":"d0138da84ce3e2e539b9c494975d84da8b1b260aa1a1f91dc3369508649eaeb5"}}