{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:OJCSFRRBCLWO3F67J5DMHZ27C2","short_pith_number":"pith:OJCSFRRB","canonical_record":{"source":{"id":"2012.15404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-12-31T02:34:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a2126950c649c640ddc0314970e182701168f3b5ffebf0b3cd3b0b1cde1be7b5","abstract_canon_sha256":"b3f1f66e8e79e0afbf09c5164173ce90b492287012183bf29131e8c4a8b0bdfc"},"schema_version":"1.0"},"canonical_sha256":"724522c62112eced97df4f46c3e75f1690c108aee5051de981614c141ced1b60","source":{"kind":"arxiv","id":"2012.15404","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15404","created_at":"2026-07-05T02:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15404v1","created_at":"2026-07-05T02:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15404","created_at":"2026-07-05T02:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"OJCSFRRBCLWO","created_at":"2026-07-05T02:03:18Z"},{"alias_kind":"pith_short_16","alias_value":"OJCSFRRBCLWO3F67","created_at":"2026-07-05T02:03:18Z"},{"alias_kind":"pith_short_8","alias_value":"OJCSFRRB","created_at":"2026-07-05T02:03:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:OJCSFRRBCLWO3F67J5DMHZ27C2","target":"record","payload":{"canonical_record":{"source":{"id":"2012.15404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-12-31T02:34:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a2126950c649c640ddc0314970e182701168f3b5ffebf0b3cd3b0b1cde1be7b5","abstract_canon_sha256":"b3f1f66e8e79e0afbf09c5164173ce90b492287012183bf29131e8c4a8b0bdfc"},"schema_version":"1.0"},"canonical_sha256":"724522c62112eced97df4f46c3e75f1690c108aee5051de981614c141ced1b60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:03:18.128201Z","signature_b64":"hf+cU/eeFtYIaZuykSAxUy2nayurQYwskn7N6G6UicdWmfSrmqXixf/fxMEnSyQiP4iETS4+Iq4vgFbE6qypAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"724522c62112eced97df4f46c3e75f1690c108aee5051de981614c141ced1b60","last_reissued_at":"2026-07-05T02:03:18.127801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:03:18.127801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.15404","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":"2026-07-05T02:03:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vtbPAeUa752SMO+rFzMvmL3wOXtkoD83GFwurPT9WipKBsmTBw6wyT4CDFwZ3kKBR8fH73qPyEqacnpuWzVOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:10:52.824247Z"},"content_sha256":"7dd0867f235d9b1af6dfffd99a98520b8204cb850c6a87dd57b800ed86ef2334","schema_version":"1.0","event_id":"sha256:7dd0867f235d9b1af6dfffd99a98520b8204cb850c6a87dd57b800ed86ef2334"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:OJCSFRRBCLWO3F67J5DMHZ27C2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Mandarin TTS Front-end Based on Distilled BERT Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Liqun Deng, Yang Zhang, Yasheng Wang","submitted_at":"2020-12-31T02:34:57Z","abstract_excerpt":"The front-end module in a typical Mandarin text-to-speech system (TTS) is composed of a long pipeline of text processing components, which requires extensive efforts to build and is prone to large accumulative model size and cascade errors. In this paper, a pre-trained language model (PLM) based model is proposed to simultaneously tackle the two most important tasks in TTS front-end, i.e., prosodic structure prediction (PSP) and grapheme-to-phoneme (G2P) conversion. We use a pre-trained Chinese BERT[1] as the text encoder and employ multi-task learning technique to adapt it to the two TTS fron"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15404","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/2012.15404/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":"2026-07-05T02:03:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H9p/5uH2KR3SpZ80N5o2vz81Vo7Z/3pFNER84NFNtjocSfylxo7kkqHvBY7zsoAnpBURDpe94yTM6YC3BGSkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:10:52.824760Z"},"content_sha256":"a1af03bee8850067372182bcd296cca9248675b57c7e85acf3fe5a3c681b831b","schema_version":"1.0","event_id":"sha256:a1af03bee8850067372182bcd296cca9248675b57c7e85acf3fe5a3c681b831b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OJCSFRRBCLWO3F67J5DMHZ27C2/bundle.json","state_url":"https://pith.science/pith/OJCSFRRBCLWO3F67J5DMHZ27C2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OJCSFRRBCLWO3F67J5DMHZ27C2/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":"2026-08-08T03:10:52Z","links":{"resolver":"https://pith.science/pith/OJCSFRRBCLWO3F67J5DMHZ27C2","bundle":"https://pith.science/pith/OJCSFRRBCLWO3F67J5DMHZ27C2/bundle.json","state":"https://pith.science/pith/OJCSFRRBCLWO3F67J5DMHZ27C2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OJCSFRRBCLWO3F67J5DMHZ27C2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OJCSFRRBCLWO3F67J5DMHZ27C2","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":"b3f1f66e8e79e0afbf09c5164173ce90b492287012183bf29131e8c4a8b0bdfc","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-12-31T02:34:57Z","title_canon_sha256":"a2126950c649c640ddc0314970e182701168f3b5ffebf0b3cd3b0b1cde1be7b5"},"schema_version":"1.0","source":{"id":"2012.15404","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15404","created_at":"2026-07-05T02:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15404v1","created_at":"2026-07-05T02:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15404","created_at":"2026-07-05T02:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"OJCSFRRBCLWO","created_at":"2026-07-05T02:03:18Z"},{"alias_kind":"pith_short_16","alias_value":"OJCSFRRBCLWO3F67","created_at":"2026-07-05T02:03:18Z"},{"alias_kind":"pith_short_8","alias_value":"OJCSFRRB","created_at":"2026-07-05T02:03:18Z"}],"graph_snapshots":[{"event_id":"sha256:a1af03bee8850067372182bcd296cca9248675b57c7e85acf3fe5a3c681b831b","target":"graph","created_at":"2026-07-05T02:03:18Z","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/2012.15404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The front-end module in a typical Mandarin text-to-speech system (TTS) is composed of a long pipeline of text processing components, which requires extensive efforts to build and is prone to large accumulative model size and cascade errors. In this paper, a pre-trained language model (PLM) based model is proposed to simultaneously tackle the two most important tasks in TTS front-end, i.e., prosodic structure prediction (PSP) and grapheme-to-phoneme (G2P) conversion. We use a pre-trained Chinese BERT[1] as the text encoder and employ multi-task learning technique to adapt it to the two TTS fron","authors_text":"Liqun Deng, Yang Zhang, Yasheng Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-12-31T02:34:57Z","title":"Unified Mandarin TTS Front-end Based on Distilled BERT Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15404","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":"sha256:7dd0867f235d9b1af6dfffd99a98520b8204cb850c6a87dd57b800ed86ef2334","target":"record","created_at":"2026-07-05T02:03:18Z","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":"b3f1f66e8e79e0afbf09c5164173ce90b492287012183bf29131e8c4a8b0bdfc","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-12-31T02:34:57Z","title_canon_sha256":"a2126950c649c640ddc0314970e182701168f3b5ffebf0b3cd3b0b1cde1be7b5"},"schema_version":"1.0","source":{"id":"2012.15404","kind":"arxiv","version":1}},"canonical_sha256":"724522c62112eced97df4f46c3e75f1690c108aee5051de981614c141ced1b60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"724522c62112eced97df4f46c3e75f1690c108aee5051de981614c141ced1b60","first_computed_at":"2026-07-05T02:03:18.127801Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:03:18.127801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hf+cU/eeFtYIaZuykSAxUy2nayurQYwskn7N6G6UicdWmfSrmqXixf/fxMEnSyQiP4iETS4+Iq4vgFbE6qypAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:03:18.128201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.15404","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dd0867f235d9b1af6dfffd99a98520b8204cb850c6a87dd57b800ed86ef2334","sha256:a1af03bee8850067372182bcd296cca9248675b57c7e85acf3fe5a3c681b831b"],"state_sha256":"4de3269a75c5c8d103fc7386ad648f78af484160996f28a85d1c293703ca5dff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZRVdQvAS57MmVjropZVAwjKIPHKvErokTg7vhVojWm5rFDilvEx0hYv+cfawwg8m1uiAeV6zJ7XBghjpY9QZDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:10:52.828499Z","bundle_sha256":"ac3fcce7d7ec0125e4d108c76177e38f07459ef547790a8f8c882876a7a67307"}}