{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HQBOT7R5U7BVCZTNGBNCHQPFSI","short_pith_number":"pith:HQBOT7R5","canonical_record":{"source":{"id":"2108.09889","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-23T01:55:03Z","cross_cats_sorted":[],"title_canon_sha256":"f3fed492eb3cd185174490b14359163179c1627504db8c584c213600e989fcbe","abstract_canon_sha256":"02c36bd83aacfbfbdd63c092780184766bc7766a921f7f83eb592d235def54ee"},"schema_version":"1.0"},"canonical_sha256":"3c02e9fe3da7c351666d305a23c1e59204c1c948c66acf7f12fcaaacd13b4522","source":{"kind":"arxiv","id":"2108.09889","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.09889","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"arxiv_version","alias_value":"2108.09889v1","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.09889","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"pith_short_12","alias_value":"HQBOT7R5U7BV","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"pith_short_16","alias_value":"HQBOT7R5U7BVCZTN","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"pith_short_8","alias_value":"HQBOT7R5","created_at":"2026-07-05T03:07:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HQBOT7R5U7BVCZTNGBNCHQPFSI","target":"record","payload":{"canonical_record":{"source":{"id":"2108.09889","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-23T01:55:03Z","cross_cats_sorted":[],"title_canon_sha256":"f3fed492eb3cd185174490b14359163179c1627504db8c584c213600e989fcbe","abstract_canon_sha256":"02c36bd83aacfbfbdd63c092780184766bc7766a921f7f83eb592d235def54ee"},"schema_version":"1.0"},"canonical_sha256":"3c02e9fe3da7c351666d305a23c1e59204c1c948c66acf7f12fcaaacd13b4522","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:59.574118Z","signature_b64":"7B0hp8cES7ayB/GlUCCDBajdGavQWhGEB+MwQQBT/Pg4Gw3q8XuNWtkojDdbIpA+qN9xZ9y2zynhaY3R1AZ6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c02e9fe3da7c351666d305a23c1e59204c1c948c66acf7f12fcaaacd13b4522","last_reissued_at":"2026-07-05T03:07:59.573760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:59.573760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.09889","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":"2026-07-05T03:07:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P+3meNufRiJFFTNH6UqBWjwyXUAIE5lCqgQrFb945sZPAptw0PZy/hWe3VDj2LVJvwGRa34WnnkO6EWbJ+sSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:58:58.828347Z"},"content_sha256":"7a4fbd909dcd4fc5ad36f89fb1386c09851ebfe16701d82a397caa7cf018fcb8","schema_version":"1.0","event_id":"sha256:7a4fbd909dcd4fc5ad36f89fb1386c09851ebfe16701d82a397caa7cf018fcb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HQBOT7R5U7BVCZTNGBNCHQPFSI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Unified Transformer-based Framework for Duplex Text Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Evelina Bakhturina, Heng Ji, Tuan Manh Lai, Yang Zhang","submitted_at":"2021-08-23T01:55:03Z","abstract_excerpt":"Text normalization (TN) and inverse text normalization (ITN) are essential preprocessing and postprocessing steps for text-to-speech synthesis and automatic speech recognition, respectively. Many methods have been proposed for either TN or ITN, ranging from weighted finite-state transducers to neural networks. Despite their impressive performance, these methods aim to tackle only one of the two tasks but not both. As a result, in a complete spoken dialog system, two separate models for TN and ITN need to be built. This heterogeneity increases the technical complexity of the system, which in tu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.09889","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/2108.09889/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":"2026-07-05T03:07:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"50Q6cCMJQ7ZwuU+/nliNxrGzhZWasVrrpGZxCltJNDJtff8tyAK5AQfF9ncztOr4/Nho9vNzqz5AN2TddiDPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:58:58.829029Z"},"content_sha256":"3a4d4e8689bc2fcec39b010a6a2a9728417e3ef774646a65d6e591734a3d551b","schema_version":"1.0","event_id":"sha256:3a4d4e8689bc2fcec39b010a6a2a9728417e3ef774646a65d6e591734a3d551b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HQBOT7R5U7BVCZTNGBNCHQPFSI/bundle.json","state_url":"https://pith.science/pith/HQBOT7R5U7BVCZTNGBNCHQPFSI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HQBOT7R5U7BVCZTNGBNCHQPFSI/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":"2026-08-05T22:58:58Z","links":{"resolver":"https://pith.science/pith/HQBOT7R5U7BVCZTNGBNCHQPFSI","bundle":"https://pith.science/pith/HQBOT7R5U7BVCZTNGBNCHQPFSI/bundle.json","state":"https://pith.science/pith/HQBOT7R5U7BVCZTNGBNCHQPFSI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HQBOT7R5U7BVCZTNGBNCHQPFSI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HQBOT7R5U7BVCZTNGBNCHQPFSI","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":"02c36bd83aacfbfbdd63c092780184766bc7766a921f7f83eb592d235def54ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-23T01:55:03Z","title_canon_sha256":"f3fed492eb3cd185174490b14359163179c1627504db8c584c213600e989fcbe"},"schema_version":"1.0","source":{"id":"2108.09889","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.09889","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"arxiv_version","alias_value":"2108.09889v1","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.09889","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"pith_short_12","alias_value":"HQBOT7R5U7BV","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"pith_short_16","alias_value":"HQBOT7R5U7BVCZTN","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"pith_short_8","alias_value":"HQBOT7R5","created_at":"2026-07-05T03:07:59Z"}],"graph_snapshots":[{"event_id":"sha256:3a4d4e8689bc2fcec39b010a6a2a9728417e3ef774646a65d6e591734a3d551b","target":"graph","created_at":"2026-07-05T03:07:59Z","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/2108.09889/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text normalization (TN) and inverse text normalization (ITN) are essential preprocessing and postprocessing steps for text-to-speech synthesis and automatic speech recognition, respectively. Many methods have been proposed for either TN or ITN, ranging from weighted finite-state transducers to neural networks. Despite their impressive performance, these methods aim to tackle only one of the two tasks but not both. As a result, in a complete spoken dialog system, two separate models for TN and ITN need to be built. This heterogeneity increases the technical complexity of the system, which in tu","authors_text":"Boris Ginsburg, Evelina Bakhturina, Heng Ji, Tuan Manh Lai, Yang Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-23T01:55:03Z","title":"A Unified Transformer-based Framework for Duplex Text Normalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.09889","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":"sha256:7a4fbd909dcd4fc5ad36f89fb1386c09851ebfe16701d82a397caa7cf018fcb8","target":"record","created_at":"2026-07-05T03:07:59Z","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":"02c36bd83aacfbfbdd63c092780184766bc7766a921f7f83eb592d235def54ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-23T01:55:03Z","title_canon_sha256":"f3fed492eb3cd185174490b14359163179c1627504db8c584c213600e989fcbe"},"schema_version":"1.0","source":{"id":"2108.09889","kind":"arxiv","version":1}},"canonical_sha256":"3c02e9fe3da7c351666d305a23c1e59204c1c948c66acf7f12fcaaacd13b4522","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c02e9fe3da7c351666d305a23c1e59204c1c948c66acf7f12fcaaacd13b4522","first_computed_at":"2026-07-05T03:07:59.573760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:07:59.573760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7B0hp8cES7ayB/GlUCCDBajdGavQWhGEB+MwQQBT/Pg4Gw3q8XuNWtkojDdbIpA+qN9xZ9y2zynhaY3R1AZ6Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:07:59.574118Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.09889","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a4fbd909dcd4fc5ad36f89fb1386c09851ebfe16701d82a397caa7cf018fcb8","sha256:3a4d4e8689bc2fcec39b010a6a2a9728417e3ef774646a65d6e591734a3d551b"],"state_sha256":"7c4939744a37c5bf0335ef5deaa7b6db14aeacecf7a912a2d6cbc16e02ecf2ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+seLihlPme4eEq2NZ14VHN5h9c5dKbjRw++eeKolLHQsmtZ3YMLKu/BFOmolviK602cNU5m5g0Vr3DY4+P+YAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:58:58.833000Z","bundle_sha256":"babe36ff5d23c71dfd4cdb6d45ec93510b47f86f958be3959d4e0beadc1dcf3d"}}