{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:RESWJ7IKTP7T6CBAOJUKZV7WBE","short_pith_number":"pith:RESWJ7IK","canonical_record":{"source":{"id":"1708.01464","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-04T11:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"4bd090c817566b68c5a9d3aa386b95b85a70d12a71b8f178f74f5bc506791297","abstract_canon_sha256":"02f89227e0431e102439c90d99d6276475a90d035ab28e4556e4d36b60e65428"},"schema_version":"1.0"},"canonical_sha256":"892564fd0a9bff3f08207268acd7f60904b47367033295ec22889cfaf4b8fcab","source":{"kind":"arxiv","id":"1708.01464","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.01464","created_at":"2026-05-18T00:33:43Z"},{"alias_kind":"arxiv_version","alias_value":"1708.01464v1","created_at":"2026-05-18T00:33:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01464","created_at":"2026-05-18T00:33:43Z"},{"alias_kind":"pith_short_12","alias_value":"RESWJ7IKTP7T","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RESWJ7IKTP7T6CBA","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RESWJ7IK","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:RESWJ7IKTP7T6CBAOJUKZV7WBE","target":"record","payload":{"canonical_record":{"source":{"id":"1708.01464","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-04T11:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"4bd090c817566b68c5a9d3aa386b95b85a70d12a71b8f178f74f5bc506791297","abstract_canon_sha256":"02f89227e0431e102439c90d99d6276475a90d035ab28e4556e4d36b60e65428"},"schema_version":"1.0"},"canonical_sha256":"892564fd0a9bff3f08207268acd7f60904b47367033295ec22889cfaf4b8fcab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:43.297073Z","signature_b64":"5A2mJ360RoP2H+FWdfyTPJjenLCxB97dG2RsLCC01Iyx68gPI43WVxs9Os6nNnJoeKVvyFIq95pO+61Had5cCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"892564fd0a9bff3f08207268acd7f60904b47367033295ec22889cfaf4b8fcab","last_reissued_at":"2026-05-18T00:33:43.296380Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:43.296380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.01464","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":"2026-05-18T00:33:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1OWfRzrIB1d8UpIHrXSvL4SqVZemvZbZXRB7RBW3aHw66EZo6mAFLu++qNGZb62mNKzFf1MKyAOZMtHVuIL/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T22:36:34.057868Z"},"content_sha256":"9cb13af4e3efacc88f49957eea2c22ee96a49bfc7aaf454576a7aa14ebbcc8fc","schema_version":"1.0","event_id":"sha256:9cb13af4e3efacc88f49957eea2c22ee96a49bfc7aaf454576a7aa14ebbcc8fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:RESWJ7IKTP7T6CBAOJUKZV7WBE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Massively Multilingual Neural Grapheme-to-Phoneme Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ben Peters, Jon Dehdari, Josef van Genabith","submitted_at":"2017-08-04T11:57:02Z","abstract_excerpt":"Grapheme-to-phoneme conversion (g2p) is necessary for text-to-speech and automatic speech recognition systems. Most g2p systems are monolingual: they require language-specific data or handcrafting of rules. Such systems are difficult to extend to low resource languages, for which data and handcrafted rules are not available. As an alternative, we present a neural sequence-to-sequence approach to g2p which is trained on spelling--pronunciation pairs in hundreds of languages. The system shares a single encoder and decoder across all languages, allowing it to utilize the intrinsic similarities be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01464","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":""},"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":"2026-05-18T00:33:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lcKiTHhu7GRbUpUy1KQDGW2T9r+XaIT3Zbb/x2R72hjoM9mj9G3w6vFwXjsFIPjSiEMFTM/0bh41aPkBUgKJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T22:36:34.058576Z"},"content_sha256":"e6987c1c14f1ab394ea4959ec59aa1f175c8bc072d047abae12c892bab4de890","schema_version":"1.0","event_id":"sha256:e6987c1c14f1ab394ea4959ec59aa1f175c8bc072d047abae12c892bab4de890"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE/bundle.json","state_url":"https://pith.science/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE/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":"2026-05-24T22:36:34Z","links":{"resolver":"https://pith.science/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE","bundle":"https://pith.science/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE/bundle.json","state":"https://pith.science/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RESWJ7IKTP7T6CBAOJUKZV7WBE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:RESWJ7IKTP7T6CBAOJUKZV7WBE","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":"02f89227e0431e102439c90d99d6276475a90d035ab28e4556e4d36b60e65428","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-04T11:57:02Z","title_canon_sha256":"4bd090c817566b68c5a9d3aa386b95b85a70d12a71b8f178f74f5bc506791297"},"schema_version":"1.0","source":{"id":"1708.01464","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.01464","created_at":"2026-05-18T00:33:43Z"},{"alias_kind":"arxiv_version","alias_value":"1708.01464v1","created_at":"2026-05-18T00:33:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01464","created_at":"2026-05-18T00:33:43Z"},{"alias_kind":"pith_short_12","alias_value":"RESWJ7IKTP7T","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RESWJ7IKTP7T6CBA","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RESWJ7IK","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:e6987c1c14f1ab394ea4959ec59aa1f175c8bc072d047abae12c892bab4de890","target":"graph","created_at":"2026-05-18T00:33:43Z","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"},"paper":{"abstract_excerpt":"Grapheme-to-phoneme conversion (g2p) is necessary for text-to-speech and automatic speech recognition systems. Most g2p systems are monolingual: they require language-specific data or handcrafting of rules. Such systems are difficult to extend to low resource languages, for which data and handcrafted rules are not available. As an alternative, we present a neural sequence-to-sequence approach to g2p which is trained on spelling--pronunciation pairs in hundreds of languages. The system shares a single encoder and decoder across all languages, allowing it to utilize the intrinsic similarities be","authors_text":"Ben Peters, Jon Dehdari, Josef van Genabith","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-04T11:57:02Z","title":"Massively Multilingual Neural Grapheme-to-Phoneme Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01464","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":"sha256:9cb13af4e3efacc88f49957eea2c22ee96a49bfc7aaf454576a7aa14ebbcc8fc","target":"record","created_at":"2026-05-18T00:33:43Z","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":"02f89227e0431e102439c90d99d6276475a90d035ab28e4556e4d36b60e65428","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-04T11:57:02Z","title_canon_sha256":"4bd090c817566b68c5a9d3aa386b95b85a70d12a71b8f178f74f5bc506791297"},"schema_version":"1.0","source":{"id":"1708.01464","kind":"arxiv","version":1}},"canonical_sha256":"892564fd0a9bff3f08207268acd7f60904b47367033295ec22889cfaf4b8fcab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"892564fd0a9bff3f08207268acd7f60904b47367033295ec22889cfaf4b8fcab","first_computed_at":"2026-05-18T00:33:43.296380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:33:43.296380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5A2mJ360RoP2H+FWdfyTPJjenLCxB97dG2RsLCC01Iyx68gPI43WVxs9Os6nNnJoeKVvyFIq95pO+61Had5cCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:33:43.297073Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.01464","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cb13af4e3efacc88f49957eea2c22ee96a49bfc7aaf454576a7aa14ebbcc8fc","sha256:e6987c1c14f1ab394ea4959ec59aa1f175c8bc072d047abae12c892bab4de890"],"state_sha256":"5b100355d4af7ff1776909711ea00d7fa5f96213cb34d5e279f11b6a2bf6fb2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vfuQF4tOYyj/LLf7r0a0R0U8IbpbLzZNAtmPeCfhHlb00GlgAho/2Ivkzp3H/vsh1n/TKchhuj60RnGekyzdBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T22:36:34.061832Z","bundle_sha256":"5deda344eb0d1cf9dc4cbbe8bf0707804d4ddac606e60f2e418c41d9a0496a7a"}}