{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7DSP72LMYYID2OKUVJO23M3WJ5","short_pith_number":"pith:7DSP72LM","canonical_record":{"source":{"id":"2501.05948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T13:21:33Z","cross_cats_sorted":[],"title_canon_sha256":"8d8406e8be87e4a3e97d5bfcea3134022fccdb0a65a8bd58f4c3ce49f4ff5b26","abstract_canon_sha256":"5e3880eb5bf18f17608ca363501c16793f426bc6532916c8c8dc6a7d8544e9df"},"schema_version":"1.0"},"canonical_sha256":"f8e4ffe96cc6103d3954aa5dadb3764f496305957fc5f537b359abc948e34f17","source":{"kind":"arxiv","id":"2501.05948","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05948","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05948v1","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05948","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"pith_short_12","alias_value":"7DSP72LMYYID","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"pith_short_16","alias_value":"7DSP72LMYYID2OKU","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"pith_short_8","alias_value":"7DSP72LM","created_at":"2026-07-05T09:59:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7DSP72LMYYID2OKUVJO23M3WJ5","target":"record","payload":{"canonical_record":{"source":{"id":"2501.05948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T13:21:33Z","cross_cats_sorted":[],"title_canon_sha256":"8d8406e8be87e4a3e97d5bfcea3134022fccdb0a65a8bd58f4c3ce49f4ff5b26","abstract_canon_sha256":"5e3880eb5bf18f17608ca363501c16793f426bc6532916c8c8dc6a7d8544e9df"},"schema_version":"1.0"},"canonical_sha256":"f8e4ffe96cc6103d3954aa5dadb3764f496305957fc5f537b359abc948e34f17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:30.733803Z","signature_b64":"+AmsEfPHNmclIz02k30wDLl5e0tcQOnGv05jX7FjM83YeRS8XaIydW8WCMufdmHgFxKerxCKXPbgH2RvzSAWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8e4ffe96cc6103d3954aa5dadb3764f496305957fc5f537b359abc948e34f17","last_reissued_at":"2026-07-05T09:59:30.733365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:30.733365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.05948","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":"2026-07-05T09:59:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gjwDpnMnw8TWpyz9LG8CijsN8tBO5qIHnVjBI51KF94z1y/LCrOvN8oPNwNQlOw50xu5lgc40aw8qPOmF5l2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T07:47:00.711665Z"},"content_sha256":"a36dce2eb053d8fd8d7717beb06f2d4f1888e34ded0d7c8413b713e11c6c8ecb","schema_version":"1.0","event_id":"sha256:a36dce2eb053d8fd8d7717beb06f2d4f1888e34ded0d7c8413b713e11c6c8ecb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7DSP72LMYYID2OKUVJO23M3WJ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Universal-2-TF: Robust All-Neural Text Formatting for ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrea Vanzo, Takuya Yoshioka, Taufiquzzaman Peyash, Yash Khare","submitted_at":"2025-01-10T13:21:33Z","abstract_excerpt":"This paper introduces an all-neural text formatting (TF) model designed for commercial automatic speech recognition (ASR) systems, encompassing punctuation restoration (PR), truecasing, and inverse text normalization (ITN). Unlike traditional rule-based or hybrid approaches, this method leverages a two-stage neural architecture comprising a multi-objective token classifier and a sequence-to-sequence (seq2seq) model. This design minimizes computational costs and reduces hallucinations while ensuring flexibility and robustness across diverse linguistic entities and text domains. Developed as par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05948","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/2501.05948/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":"2026-07-05T09:59:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zjmSa+8yyPyDb1GBmRBqpJ7NFmNdkWn7n3Vjlai9O8iUudoXzCft8b0CK1YA/RxIaw9unvyGPjTB+YHlZSxaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T07:47:00.712144Z"},"content_sha256":"2e9814af872a8de06a41a827f780dd21a62466b357cc5e6f7f65d39602493533","schema_version":"1.0","event_id":"sha256:2e9814af872a8de06a41a827f780dd21a62466b357cc5e6f7f65d39602493533"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7DSP72LMYYID2OKUVJO23M3WJ5/bundle.json","state_url":"https://pith.science/pith/7DSP72LMYYID2OKUVJO23M3WJ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7DSP72LMYYID2OKUVJO23M3WJ5/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":"2026-08-15T07:47:00Z","links":{"resolver":"https://pith.science/pith/7DSP72LMYYID2OKUVJO23M3WJ5","bundle":"https://pith.science/pith/7DSP72LMYYID2OKUVJO23M3WJ5/bundle.json","state":"https://pith.science/pith/7DSP72LMYYID2OKUVJO23M3WJ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7DSP72LMYYID2OKUVJO23M3WJ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7DSP72LMYYID2OKUVJO23M3WJ5","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":"5e3880eb5bf18f17608ca363501c16793f426bc6532916c8c8dc6a7d8544e9df","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T13:21:33Z","title_canon_sha256":"8d8406e8be87e4a3e97d5bfcea3134022fccdb0a65a8bd58f4c3ce49f4ff5b26"},"schema_version":"1.0","source":{"id":"2501.05948","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05948","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05948v1","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05948","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"pith_short_12","alias_value":"7DSP72LMYYID","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"pith_short_16","alias_value":"7DSP72LMYYID2OKU","created_at":"2026-07-05T09:59:30Z"},{"alias_kind":"pith_short_8","alias_value":"7DSP72LM","created_at":"2026-07-05T09:59:30Z"}],"graph_snapshots":[{"event_id":"sha256:2e9814af872a8de06a41a827f780dd21a62466b357cc5e6f7f65d39602493533","target":"graph","created_at":"2026-07-05T09:59:30Z","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/2501.05948/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces an all-neural text formatting (TF) model designed for commercial automatic speech recognition (ASR) systems, encompassing punctuation restoration (PR), truecasing, and inverse text normalization (ITN). Unlike traditional rule-based or hybrid approaches, this method leverages a two-stage neural architecture comprising a multi-objective token classifier and a sequence-to-sequence (seq2seq) model. This design minimizes computational costs and reduces hallucinations while ensuring flexibility and robustness across diverse linguistic entities and text domains. Developed as par","authors_text":"Andrea Vanzo, Takuya Yoshioka, Taufiquzzaman Peyash, Yash Khare","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T13:21:33Z","title":"Universal-2-TF: Robust All-Neural Text Formatting for ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05948","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:a36dce2eb053d8fd8d7717beb06f2d4f1888e34ded0d7c8413b713e11c6c8ecb","target":"record","created_at":"2026-07-05T09:59:30Z","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":"5e3880eb5bf18f17608ca363501c16793f426bc6532916c8c8dc6a7d8544e9df","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T13:21:33Z","title_canon_sha256":"8d8406e8be87e4a3e97d5bfcea3134022fccdb0a65a8bd58f4c3ce49f4ff5b26"},"schema_version":"1.0","source":{"id":"2501.05948","kind":"arxiv","version":1}},"canonical_sha256":"f8e4ffe96cc6103d3954aa5dadb3764f496305957fc5f537b359abc948e34f17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8e4ffe96cc6103d3954aa5dadb3764f496305957fc5f537b359abc948e34f17","first_computed_at":"2026-07-05T09:59:30.733365Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:30.733365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+AmsEfPHNmclIz02k30wDLl5e0tcQOnGv05jX7FjM83YeRS8XaIydW8WCMufdmHgFxKerxCKXPbgH2RvzSAWDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:30.733803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05948","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a36dce2eb053d8fd8d7717beb06f2d4f1888e34ded0d7c8413b713e11c6c8ecb","sha256:2e9814af872a8de06a41a827f780dd21a62466b357cc5e6f7f65d39602493533"],"state_sha256":"22e16179fb0bf85974570351f046d2fd5b34ede5e9488aeb752db2458a71d540"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LAB2dzw6HXKvVNNCckhjdSx2D0vuA68zWslEKd4XT7T6+LgScw8qrRxQ+QYHEx7/vEttQ+Rkm4FD80a3HBxxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T07:47:00.716636Z","bundle_sha256":"4f986ad7f516e899fee4f4e19a6555f00ba5531b2fc2ef1ececa7c34907ab934"}}