{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WFMSW6QCKTOJHT2LBAMU2JONGU","short_pith_number":"pith:WFMSW6QC","canonical_record":{"source":{"id":"2407.04368","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-05T09:13:24Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b93a980ea20c9e4221b9683a4910159d2b9272affb34cb12676595df06ce50e0","abstract_canon_sha256":"9d46518e88cac31c981068d592a52b859c0799794650ed48566cd74147de1091"},"schema_version":"1.0"},"canonical_sha256":"b1592b7a0254dc93cf4b08194d25cd351e19e2859c0e6f6b979428b576bd7b60","source":{"kind":"arxiv","id":"2407.04368","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04368","created_at":"2026-07-05T09:50:03Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04368v2","created_at":"2026-07-05T09:50:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04368","created_at":"2026-07-05T09:50:03Z"},{"alias_kind":"pith_short_12","alias_value":"WFMSW6QCKTOJ","created_at":"2026-07-05T09:50:03Z"},{"alias_kind":"pith_short_16","alias_value":"WFMSW6QCKTOJHT2L","created_at":"2026-07-05T09:50:03Z"},{"alias_kind":"pith_short_8","alias_value":"WFMSW6QC","created_at":"2026-07-05T09:50:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WFMSW6QCKTOJHT2LBAMU2JONGU","target":"record","payload":{"canonical_record":{"source":{"id":"2407.04368","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-05T09:13:24Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b93a980ea20c9e4221b9683a4910159d2b9272affb34cb12676595df06ce50e0","abstract_canon_sha256":"9d46518e88cac31c981068d592a52b859c0799794650ed48566cd74147de1091"},"schema_version":"1.0"},"canonical_sha256":"b1592b7a0254dc93cf4b08194d25cd351e19e2859c0e6f6b979428b576bd7b60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:03.680614Z","signature_b64":"VOJ7lLWKq5c609KHvLaGDV/z17knQY8ck1N968gMbh//Arps54v1Zy5HoIEvy15Xervf8Pv8iSIrlMB5QjSzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1592b7a0254dc93cf4b08194d25cd351e19e2859c0e6f6b979428b576bd7b60","last_reissued_at":"2026-07-05T09:50:03.680039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:03.680039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.04368","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":"2026-07-05T09:50:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R/01tPbZypkHTqE2SRHZzSdBwqMJuxxyG/MmvFErUOQiZXC4ynDdHIVKplKCOv9L5bofuCZx6gLXjsYLOLIQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:11:21.213441Z"},"content_sha256":"e49010fd4422fa974a4be7bba1f18010d2ad84d342279643380547a9d1a01163","schema_version":"1.0","event_id":"sha256:e49010fd4422fa974a4be7bba1f18010d2ad84d342279643380547a9d1a01163"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WFMSW6QCKTOJHT2LBAMU2JONGU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Romanization Encoding For Multilingual ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Fei Jia, Hainan Xu, Junjie Lai, Wen Ding, Yu Xi","submitted_at":"2024-07-05T09:13:24Z","abstract_excerpt":"We introduce romanization encoding for script-heavy languages to optimize multilingual and code-switching Automatic Speech Recognition (ASR) systems. By adopting romanization encoding alongside a balanced concatenated tokenizer within a FastConformer-RNNT framework equipped with a Roman2Char module, we significantly reduce vocabulary and output dimensions, enabling larger training batches and reduced memory consumption. Our method decouples acoustic modeling and language modeling, enhancing the flexibility and adaptability of the system. In our study, applying this method to Mandarin-English A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04368","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/2407.04368/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":"2026-07-05T09:50:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l3imiCYVhE+UQcqjBfBhZlvohzzRUluCCZeWPz/BG2o73ifczl/ztEkRiZ5K7Z+moQuZuw5IHYr7kph5QCJUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:11:21.213956Z"},"content_sha256":"5322f20a23f65df278726f20dcb36f17c642bb44729512aec1eab3fe21b3b7ad","schema_version":"1.0","event_id":"sha256:5322f20a23f65df278726f20dcb36f17c642bb44729512aec1eab3fe21b3b7ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WFMSW6QCKTOJHT2LBAMU2JONGU/bundle.json","state_url":"https://pith.science/pith/WFMSW6QCKTOJHT2LBAMU2JONGU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WFMSW6QCKTOJHT2LBAMU2JONGU/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":"2026-08-06T00:11:21Z","links":{"resolver":"https://pith.science/pith/WFMSW6QCKTOJHT2LBAMU2JONGU","bundle":"https://pith.science/pith/WFMSW6QCKTOJHT2LBAMU2JONGU/bundle.json","state":"https://pith.science/pith/WFMSW6QCKTOJHT2LBAMU2JONGU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WFMSW6QCKTOJHT2LBAMU2JONGU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WFMSW6QCKTOJHT2LBAMU2JONGU","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":"9d46518e88cac31c981068d592a52b859c0799794650ed48566cd74147de1091","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-05T09:13:24Z","title_canon_sha256":"b93a980ea20c9e4221b9683a4910159d2b9272affb34cb12676595df06ce50e0"},"schema_version":"1.0","source":{"id":"2407.04368","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04368","created_at":"2026-07-05T09:50:03Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04368v2","created_at":"2026-07-05T09:50:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04368","created_at":"2026-07-05T09:50:03Z"},{"alias_kind":"pith_short_12","alias_value":"WFMSW6QCKTOJ","created_at":"2026-07-05T09:50:03Z"},{"alias_kind":"pith_short_16","alias_value":"WFMSW6QCKTOJHT2L","created_at":"2026-07-05T09:50:03Z"},{"alias_kind":"pith_short_8","alias_value":"WFMSW6QC","created_at":"2026-07-05T09:50:03Z"}],"graph_snapshots":[{"event_id":"sha256:5322f20a23f65df278726f20dcb36f17c642bb44729512aec1eab3fe21b3b7ad","target":"graph","created_at":"2026-07-05T09:50:03Z","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/2407.04368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce romanization encoding for script-heavy languages to optimize multilingual and code-switching Automatic Speech Recognition (ASR) systems. By adopting romanization encoding alongside a balanced concatenated tokenizer within a FastConformer-RNNT framework equipped with a Roman2Char module, we significantly reduce vocabulary and output dimensions, enabling larger training batches and reduced memory consumption. Our method decouples acoustic modeling and language modeling, enhancing the flexibility and adaptability of the system. In our study, applying this method to Mandarin-English A","authors_text":"Boris Ginsburg, Fei Jia, Hainan Xu, Junjie Lai, Wen Ding, Yu Xi","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-05T09:13:24Z","title":"Romanization Encoding For Multilingual ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04368","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:e49010fd4422fa974a4be7bba1f18010d2ad84d342279643380547a9d1a01163","target":"record","created_at":"2026-07-05T09:50:03Z","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":"9d46518e88cac31c981068d592a52b859c0799794650ed48566cd74147de1091","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-05T09:13:24Z","title_canon_sha256":"b93a980ea20c9e4221b9683a4910159d2b9272affb34cb12676595df06ce50e0"},"schema_version":"1.0","source":{"id":"2407.04368","kind":"arxiv","version":2}},"canonical_sha256":"b1592b7a0254dc93cf4b08194d25cd351e19e2859c0e6f6b979428b576bd7b60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1592b7a0254dc93cf4b08194d25cd351e19e2859c0e6f6b979428b576bd7b60","first_computed_at":"2026-07-05T09:50:03.680039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:03.680039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VOJ7lLWKq5c609KHvLaGDV/z17knQY8ck1N968gMbh//Arps54v1Zy5HoIEvy15Xervf8Pv8iSIrlMB5QjSzCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:03.680614Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04368","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e49010fd4422fa974a4be7bba1f18010d2ad84d342279643380547a9d1a01163","sha256:5322f20a23f65df278726f20dcb36f17c642bb44729512aec1eab3fe21b3b7ad"],"state_sha256":"8188adf7eb31049d354f3542fa4c1268af6740f760e9c97e1692c3c66dd33159"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"59ZENr6CGbvF12xBwczyPEP2psCGZUnIXMPMQsZvDqbkzH7ubzVBrEzabG+uqbzpIaAeFQWUe2AM2K7njtDcAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:11:21.217394Z","bundle_sha256":"c7ad0567cb0204a96fa467e10bfaf9e5ce72aad5fbf5b4c3663ac21e134198e1"}}