{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YO4JVHB4Y77B66CK3H5AD4A7KJ","short_pith_number":"pith:YO4JVHB4","canonical_record":{"source":{"id":"2104.04091","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-08T21:36:21Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"dc49c52c9ed5cfdb2b6a262f05d7138e30659e05a67cb6f45cbbd5a5462a4b9c","abstract_canon_sha256":"4fb9b31c8072a898cede4a8cf07c5aee06936903d364f5c18e1821640d65055c"},"schema_version":"1.0"},"canonical_sha256":"c3b89a9c3cc7fe1f784ad9fa01f01f5250a2a09eaee6ad768a051bd341a1deee","source":{"kind":"arxiv","id":"2104.04091","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.04091","created_at":"2026-07-05T02:30:34Z"},{"alias_kind":"arxiv_version","alias_value":"2104.04091v1","created_at":"2026-07-05T02:30:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04091","created_at":"2026-07-05T02:30:34Z"},{"alias_kind":"pith_short_12","alias_value":"YO4JVHB4Y77B","created_at":"2026-07-05T02:30:34Z"},{"alias_kind":"pith_short_16","alias_value":"YO4JVHB4Y77B66CK","created_at":"2026-07-05T02:30:34Z"},{"alias_kind":"pith_short_8","alias_value":"YO4JVHB4","created_at":"2026-07-05T02:30:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YO4JVHB4Y77B66CK3H5AD4A7KJ","target":"record","payload":{"canonical_record":{"source":{"id":"2104.04091","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-08T21:36:21Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"dc49c52c9ed5cfdb2b6a262f05d7138e30659e05a67cb6f45cbbd5a5462a4b9c","abstract_canon_sha256":"4fb9b31c8072a898cede4a8cf07c5aee06936903d364f5c18e1821640d65055c"},"schema_version":"1.0"},"canonical_sha256":"c3b89a9c3cc7fe1f784ad9fa01f01f5250a2a09eaee6ad768a051bd341a1deee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:34.846261Z","signature_b64":"8236kEPnjqUOmQgI/5SnchJsOY1AaHQK1+jP6XJXiUpN7OLc6m3knmRaxNSXgm0+ZZjZxSmgYSIwQulJusx2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3b89a9c3cc7fe1f784ad9fa01f01f5250a2a09eaee6ad768a051bd341a1deee","last_reissued_at":"2026-07-05T02:30:34.845817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:34.845817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.04091","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":"2026-07-05T02:30:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o41kb/eeiK91ay5oHpEflQsm5j7eZOmDG0W2txUIpZHpN/0XMjHkCvvNhTiOBXeHyrSMZmWHmmg26WBU4aBCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T11:44:55.322441Z"},"content_sha256":"97e6f0e7f67a4f7636a95be6a7872affc4791d6790caa5d73414ef2af7e6afe0","schema_version":"1.0","event_id":"sha256:97e6f0e7f67a4f7636a95be6a7872affc4791d6790caa5d73414ef2af7e6afe0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YO4JVHB4Y77B66CK3H5AD4A7KJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grapheme-to-Phoneme Transformer Model for Transfer Learning Dialects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"cs.CL","authors_text":"Eric Engelhart, Gaurav Bharaj, Mahsa Elyasi","submitted_at":"2021-04-08T21:36:21Z","abstract_excerpt":"Grapheme-to-Phoneme (G2P) models convert words to their phonetic pronunciations. Classic G2P methods include rule-based systems and pronunciation dictionaries, while modern G2P systems incorporate learning, such as, LSTM and Transformer-based attention models. Usually, dictionary-based methods require significant manual effort to build, and have limited adaptivity on unseen words. And transformer-based models require significant training data, and do not generalize well, especially for dialects with limited data.\n  We propose a novel use of transformer-based attention model that can adapt to u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04091","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/2104.04091/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":"2026-07-05T02:30:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NZqufL6ysPGAk+1deLZVHzxwVlDEZA4F9OJDlsbBjKN1P04NjTJDl4/zmzib0OLOd6jhr2gCTQkTleZm0hyyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T11:44:55.322774Z"},"content_sha256":"0c0893a70496c7a54c1d85e90ba181b77dfe60d83ff420057e38217c8b8dc563","schema_version":"1.0","event_id":"sha256:0c0893a70496c7a54c1d85e90ba181b77dfe60d83ff420057e38217c8b8dc563"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ/bundle.json","state_url":"https://pith.science/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ/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":"2026-08-23T11:44:55Z","links":{"resolver":"https://pith.science/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ","bundle":"https://pith.science/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ/bundle.json","state":"https://pith.science/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YO4JVHB4Y77B66CK3H5AD4A7KJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YO4JVHB4Y77B66CK3H5AD4A7KJ","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":"4fb9b31c8072a898cede4a8cf07c5aee06936903d364f5c18e1821640d65055c","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-08T21:36:21Z","title_canon_sha256":"dc49c52c9ed5cfdb2b6a262f05d7138e30659e05a67cb6f45cbbd5a5462a4b9c"},"schema_version":"1.0","source":{"id":"2104.04091","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.04091","created_at":"2026-07-05T02:30:34Z"},{"alias_kind":"arxiv_version","alias_value":"2104.04091v1","created_at":"2026-07-05T02:30:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04091","created_at":"2026-07-05T02:30:34Z"},{"alias_kind":"pith_short_12","alias_value":"YO4JVHB4Y77B","created_at":"2026-07-05T02:30:34Z"},{"alias_kind":"pith_short_16","alias_value":"YO4JVHB4Y77B66CK","created_at":"2026-07-05T02:30:34Z"},{"alias_kind":"pith_short_8","alias_value":"YO4JVHB4","created_at":"2026-07-05T02:30:34Z"}],"graph_snapshots":[{"event_id":"sha256:0c0893a70496c7a54c1d85e90ba181b77dfe60d83ff420057e38217c8b8dc563","target":"graph","created_at":"2026-07-05T02:30:34Z","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/2104.04091/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grapheme-to-Phoneme (G2P) models convert words to their phonetic pronunciations. Classic G2P methods include rule-based systems and pronunciation dictionaries, while modern G2P systems incorporate learning, such as, LSTM and Transformer-based attention models. Usually, dictionary-based methods require significant manual effort to build, and have limited adaptivity on unseen words. And transformer-based models require significant training data, and do not generalize well, especially for dialects with limited data.\n  We propose a novel use of transformer-based attention model that can adapt to u","authors_text":"Eric Engelhart, Gaurav Bharaj, Mahsa Elyasi","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-08T21:36:21Z","title":"Grapheme-to-Phoneme Transformer Model for Transfer Learning Dialects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04091","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":"sha256:97e6f0e7f67a4f7636a95be6a7872affc4791d6790caa5d73414ef2af7e6afe0","target":"record","created_at":"2026-07-05T02:30:34Z","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":"4fb9b31c8072a898cede4a8cf07c5aee06936903d364f5c18e1821640d65055c","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-08T21:36:21Z","title_canon_sha256":"dc49c52c9ed5cfdb2b6a262f05d7138e30659e05a67cb6f45cbbd5a5462a4b9c"},"schema_version":"1.0","source":{"id":"2104.04091","kind":"arxiv","version":1}},"canonical_sha256":"c3b89a9c3cc7fe1f784ad9fa01f01f5250a2a09eaee6ad768a051bd341a1deee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3b89a9c3cc7fe1f784ad9fa01f01f5250a2a09eaee6ad768a051bd341a1deee","first_computed_at":"2026-07-05T02:30:34.845817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:30:34.845817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8236kEPnjqUOmQgI/5SnchJsOY1AaHQK1+jP6XJXiUpN7OLc6m3knmRaxNSXgm0+ZZjZxSmgYSIwQulJusx2CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:30:34.846261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.04091","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97e6f0e7f67a4f7636a95be6a7872affc4791d6790caa5d73414ef2af7e6afe0","sha256:0c0893a70496c7a54c1d85e90ba181b77dfe60d83ff420057e38217c8b8dc563"],"state_sha256":"da4a43b2faf056e21d6ab8b811609258cb161681c481be4cd76cc948e86bd26b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9HZKnNBtAhbO0F8Kd2a3N/q0i5DJM+4DSxFuzg234XcazAvYnKYgDH+MxsgrcqMoLr/OIXejL0Ynl8j+nYZnCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T11:44:55.325989Z","bundle_sha256":"2b9144fe67964da1e255fb151fe7c771af6d938bcb98f8247e67cd50ea728491"}}