{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LHIRXRQQF5VULBKL6NGLAL6FGH","short_pith_number":"pith:LHIRXRQQ","canonical_record":{"source":{"id":"2010.10203","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-20T11:30:26Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"9ca6b35432d07ad8c16cb30c6e3cfe576f6d89ca8b00395d2cc7c63ad2c97a15","abstract_canon_sha256":"85c1450bc43f1d5940e65f6847b4cbf159187243393c00789f6ee11b3b99fa7f"},"schema_version":"1.0"},"canonical_sha256":"59d11bc6102f6b45854bf34cb02fc531e56847dbb2bc0e7c831932abe1c23793","source":{"kind":"arxiv","id":"2010.10203","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.10203","created_at":"2026-07-05T02:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2010.10203v2","created_at":"2026-07-05T02:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10203","created_at":"2026-07-05T02:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"LHIRXRQQF5VU","created_at":"2026-07-05T02:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"LHIRXRQQF5VULBKL","created_at":"2026-07-05T02:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"LHIRXRQQ","created_at":"2026-07-05T02:14:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LHIRXRQQF5VULBKL6NGLAL6FGH","target":"record","payload":{"canonical_record":{"source":{"id":"2010.10203","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-20T11:30:26Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"9ca6b35432d07ad8c16cb30c6e3cfe576f6d89ca8b00395d2cc7c63ad2c97a15","abstract_canon_sha256":"85c1450bc43f1d5940e65f6847b4cbf159187243393c00789f6ee11b3b99fa7f"},"schema_version":"1.0"},"canonical_sha256":"59d11bc6102f6b45854bf34cb02fc531e56847dbb2bc0e7c831932abe1c23793","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:31.736453Z","signature_b64":"yYtOF/342Wz39xuErqm3YI4CMM4k+NVA3KRoHB0sNS9UAzT9fOvonvOQLjwV4jxrjZIC+9+sgVntfjHg4Tq+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59d11bc6102f6b45854bf34cb02fc531e56847dbb2bc0e7c831932abe1c23793","last_reissued_at":"2026-07-05T02:14:31.735965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:31.735965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.10203","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":"2026-07-05T02:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Ro/T2zgbb2Jw6kohnKVNp7curXpRBl84eCN1eUuR9N7UWw82HTKvI5M1MKtxniunFKaoljFNFOyICGyiWeKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T21:00:18.264261Z"},"content_sha256":"43184e78c6584c0de9c81a1794b3aaa7fafb86f0fd0ae885c8a35e5cef8ba695","schema_version":"1.0","event_id":"sha256:43184e78c6584c0de9c81a1794b3aaa7fafb86f0fd0ae885c8a35e5cef8ba695"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LHIRXRQQF5VULBKL6NGLAL6FGH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Replacing Human Audio with Synthetic Audio for On-device Unspoken Punctuation Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Balint Miklos, Bogdan Prisacari, Daniel Valcarce, Daria Soboleva, Felix Weissenberger, Julia Proskurnia, Justin Lu, M\\'arius \\v{S}ajgal\\'ik, Ondrej Skopek, Rohit Prabhavalkar, Victor C\\u{a}rbune","submitted_at":"2020-10-20T11:30:26Z","abstract_excerpt":"We present a novel multi-modal unspoken punctuation prediction system for the English language which combines acoustic and text features. We demonstrate for the first time, that by relying exclusively on synthetic data generated using a prosody-aware text-to-speech system, we can outperform a model trained with expensive human audio recordings on the unspoken punctuation prediction problem. Our model architecture is well suited for on-device use. This is achieved by leveraging hash-based embeddings of automatic speech recognition text output in conjunction with acoustic features as input to a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10203","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/2010.10203/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":"2026-07-05T02:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dvGJ88Z907ZbU6mJWCb3XDSWmgXfodfw+Tk/pUHf67WTd8CnjUBv/kdErqJLtSmcImoplXQDvq2GSbiJ1nmOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T21:00:18.264784Z"},"content_sha256":"bab716db5c2a9b7a4b38da85555fe955eb256d4718123350270bc945c4a113c2","schema_version":"1.0","event_id":"sha256:bab716db5c2a9b7a4b38da85555fe955eb256d4718123350270bc945c4a113c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LHIRXRQQF5VULBKL6NGLAL6FGH/bundle.json","state_url":"https://pith.science/pith/LHIRXRQQF5VULBKL6NGLAL6FGH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LHIRXRQQF5VULBKL6NGLAL6FGH/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":"2026-08-20T21:00:18Z","links":{"resolver":"https://pith.science/pith/LHIRXRQQF5VULBKL6NGLAL6FGH","bundle":"https://pith.science/pith/LHIRXRQQF5VULBKL6NGLAL6FGH/bundle.json","state":"https://pith.science/pith/LHIRXRQQF5VULBKL6NGLAL6FGH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LHIRXRQQF5VULBKL6NGLAL6FGH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LHIRXRQQF5VULBKL6NGLAL6FGH","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":"85c1450bc43f1d5940e65f6847b4cbf159187243393c00789f6ee11b3b99fa7f","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-20T11:30:26Z","title_canon_sha256":"9ca6b35432d07ad8c16cb30c6e3cfe576f6d89ca8b00395d2cc7c63ad2c97a15"},"schema_version":"1.0","source":{"id":"2010.10203","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.10203","created_at":"2026-07-05T02:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2010.10203v2","created_at":"2026-07-05T02:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10203","created_at":"2026-07-05T02:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"LHIRXRQQF5VU","created_at":"2026-07-05T02:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"LHIRXRQQF5VULBKL","created_at":"2026-07-05T02:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"LHIRXRQQ","created_at":"2026-07-05T02:14:31Z"}],"graph_snapshots":[{"event_id":"sha256:bab716db5c2a9b7a4b38da85555fe955eb256d4718123350270bc945c4a113c2","target":"graph","created_at":"2026-07-05T02:14:31Z","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/2010.10203/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel multi-modal unspoken punctuation prediction system for the English language which combines acoustic and text features. We demonstrate for the first time, that by relying exclusively on synthetic data generated using a prosody-aware text-to-speech system, we can outperform a model trained with expensive human audio recordings on the unspoken punctuation prediction problem. Our model architecture is well suited for on-device use. This is achieved by leveraging hash-based embeddings of automatic speech recognition text output in conjunction with acoustic features as input to a ","authors_text":"Balint Miklos, Bogdan Prisacari, Daniel Valcarce, Daria Soboleva, Felix Weissenberger, Julia Proskurnia, Justin Lu, M\\'arius \\v{S}ajgal\\'ik, Ondrej Skopek, Rohit Prabhavalkar, Victor C\\u{a}rbune","cross_cats":["cs.CL","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-20T11:30:26Z","title":"Replacing Human Audio with Synthetic Audio for On-device Unspoken Punctuation Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10203","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":"sha256:43184e78c6584c0de9c81a1794b3aaa7fafb86f0fd0ae885c8a35e5cef8ba695","target":"record","created_at":"2026-07-05T02:14:31Z","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":"85c1450bc43f1d5940e65f6847b4cbf159187243393c00789f6ee11b3b99fa7f","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-20T11:30:26Z","title_canon_sha256":"9ca6b35432d07ad8c16cb30c6e3cfe576f6d89ca8b00395d2cc7c63ad2c97a15"},"schema_version":"1.0","source":{"id":"2010.10203","kind":"arxiv","version":2}},"canonical_sha256":"59d11bc6102f6b45854bf34cb02fc531e56847dbb2bc0e7c831932abe1c23793","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59d11bc6102f6b45854bf34cb02fc531e56847dbb2bc0e7c831932abe1c23793","first_computed_at":"2026-07-05T02:14:31.735965Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:31.735965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yYtOF/342Wz39xuErqm3YI4CMM4k+NVA3KRoHB0sNS9UAzT9fOvonvOQLjwV4jxrjZIC+9+sgVntfjHg4Tq+DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:31.736453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.10203","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43184e78c6584c0de9c81a1794b3aaa7fafb86f0fd0ae885c8a35e5cef8ba695","sha256:bab716db5c2a9b7a4b38da85555fe955eb256d4718123350270bc945c4a113c2"],"state_sha256":"f79b011b402836c58c8b923d49a023821607467f10f7e0726ce96503a6b18ae9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PWaID2QloIm+TlT1xBuPCXa2Qsuf+1Arc2SgbG0Jkbdep77AAgykpwQEDuoZdMKOUPJmKvZ6BPF8eZdiFJcDAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T21:00:18.269558Z","bundle_sha256":"59bfaf79ecb13489da73181ceb1cf6a0527c91d1505909429939bc5da7204f92"}}