{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DPMSSXY7C2WC5JNJPTN2VBXJNC","short_pith_number":"pith:DPMSSXY7","canonical_record":{"source":{"id":"1807.00543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-02T09:06:27Z","cross_cats_sorted":[],"title_canon_sha256":"3ab41dca2a4aa9d02a5208be430997ab79671e5fa796853d213334477aa99674","abstract_canon_sha256":"71ad59d4489c1177c106421cfd2144a3fa291f8aa1cda37116605c5e42e8c56c"},"schema_version":"1.0"},"canonical_sha256":"1bd9295f1f16ac2ea5a97cdbaa86e968a3d086f7953aa9851efc00745b5f5c36","source":{"kind":"arxiv","id":"1807.00543","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.00543","created_at":"2026-05-18T00:11:52Z"},{"alias_kind":"arxiv_version","alias_value":"1807.00543v1","created_at":"2026-05-18T00:11:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00543","created_at":"2026-05-18T00:11:52Z"},{"alias_kind":"pith_short_12","alias_value":"DPMSSXY7C2WC","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DPMSSXY7C2WC5JNJ","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DPMSSXY7","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DPMSSXY7C2WC5JNJPTN2VBXJNC","target":"record","payload":{"canonical_record":{"source":{"id":"1807.00543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-02T09:06:27Z","cross_cats_sorted":[],"title_canon_sha256":"3ab41dca2a4aa9d02a5208be430997ab79671e5fa796853d213334477aa99674","abstract_canon_sha256":"71ad59d4489c1177c106421cfd2144a3fa291f8aa1cda37116605c5e42e8c56c"},"schema_version":"1.0"},"canonical_sha256":"1bd9295f1f16ac2ea5a97cdbaa86e968a3d086f7953aa9851efc00745b5f5c36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:52.237701Z","signature_b64":"1jHTQnuZ/FspwFSBFf+vD7f8eYi1g5P7IRtSmEmWCNSFqYphWhJfkFIHGlnkvRnmim9JLZ0HN+IKxA3U/RomCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bd9295f1f16ac2ea5a97cdbaa86e968a3d086f7953aa9851efc00745b5f5c36","last_reissued_at":"2026-05-18T00:11:52.236961Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:52.236961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.00543","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":"2026-05-18T00:11:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/EgvfdIyYjolTJQKCQY1i5XSkaI/ItL1H8vWuScjHaJ1OU5GTZAGQqI4p0Ol/TCWBJ9t+WilbUqry3hLzR8aCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:00:59.133828Z"},"content_sha256":"ca29eaf322a7aac3ca8ecb159a9f42681e82533427b07bc24799640912513131","schema_version":"1.0","event_id":"sha256:ca29eaf322a7aac3ca8ecb159a9f42681e82533427b07bc24799640912513131"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DPMSSXY7C2WC5JNJPTN2VBXJNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Punctuation Prediction Model for Conversational Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adrian Szymczak, Jan Mizgajski, Najim Dehak, Piotr Szyma\\'nski, Piotr \\.Zelasko, Yishay Carmiel","submitted_at":"2018-07-02T09:06:27Z","abstract_excerpt":"An ASR system usually does not predict any punctuation or capitalization. Lack of punctuation causes problems in result presentation and confuses both the human reader andoff-the-shelf natural language processing algorithms. To overcome these limitations, we train two variants of Deep Neural Network (DNN) sequence labelling models - a Bidirectional Long Short-Term Memory (BLSTM) and a Convolutional Neural Network (CNN), to predict the punctuation. The models are trained on the Fisher corpus which includes punctuation annotation. In our experiments, we combine time-aligned and punctuated Fisher"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00543","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":""},"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":"2026-05-18T00:11:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cPoXBG7MPqG6MFkEe3Jujqw3OR/SimxX3hlONrtbNyJJ2KYEADCeI4jAiTkk+So8cK2i5m1rPyq+0K5wz9YdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:00:59.134205Z"},"content_sha256":"34bdc52162bb8ab97218280f7d3a3d94f7a53e9268222cedad6784d0d1f391c0","schema_version":"1.0","event_id":"sha256:34bdc52162bb8ab97218280f7d3a3d94f7a53e9268222cedad6784d0d1f391c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC/bundle.json","state_url":"https://pith.science/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC/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":"2026-05-30T05:00:59Z","links":{"resolver":"https://pith.science/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC","bundle":"https://pith.science/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC/bundle.json","state":"https://pith.science/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DPMSSXY7C2WC5JNJPTN2VBXJNC","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":"71ad59d4489c1177c106421cfd2144a3fa291f8aa1cda37116605c5e42e8c56c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-02T09:06:27Z","title_canon_sha256":"3ab41dca2a4aa9d02a5208be430997ab79671e5fa796853d213334477aa99674"},"schema_version":"1.0","source":{"id":"1807.00543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.00543","created_at":"2026-05-18T00:11:52Z"},{"alias_kind":"arxiv_version","alias_value":"1807.00543v1","created_at":"2026-05-18T00:11:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00543","created_at":"2026-05-18T00:11:52Z"},{"alias_kind":"pith_short_12","alias_value":"DPMSSXY7C2WC","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DPMSSXY7C2WC5JNJ","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DPMSSXY7","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:34bdc52162bb8ab97218280f7d3a3d94f7a53e9268222cedad6784d0d1f391c0","target":"graph","created_at":"2026-05-18T00:11:52Z","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"},"paper":{"abstract_excerpt":"An ASR system usually does not predict any punctuation or capitalization. Lack of punctuation causes problems in result presentation and confuses both the human reader andoff-the-shelf natural language processing algorithms. To overcome these limitations, we train two variants of Deep Neural Network (DNN) sequence labelling models - a Bidirectional Long Short-Term Memory (BLSTM) and a Convolutional Neural Network (CNN), to predict the punctuation. The models are trained on the Fisher corpus which includes punctuation annotation. In our experiments, we combine time-aligned and punctuated Fisher","authors_text":"Adrian Szymczak, Jan Mizgajski, Najim Dehak, Piotr Szyma\\'nski, Piotr \\.Zelasko, Yishay Carmiel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-02T09:06:27Z","title":"Punctuation Prediction Model for Conversational Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00543","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:ca29eaf322a7aac3ca8ecb159a9f42681e82533427b07bc24799640912513131","target":"record","created_at":"2026-05-18T00:11:52Z","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":"71ad59d4489c1177c106421cfd2144a3fa291f8aa1cda37116605c5e42e8c56c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-02T09:06:27Z","title_canon_sha256":"3ab41dca2a4aa9d02a5208be430997ab79671e5fa796853d213334477aa99674"},"schema_version":"1.0","source":{"id":"1807.00543","kind":"arxiv","version":1}},"canonical_sha256":"1bd9295f1f16ac2ea5a97cdbaa86e968a3d086f7953aa9851efc00745b5f5c36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bd9295f1f16ac2ea5a97cdbaa86e968a3d086f7953aa9851efc00745b5f5c36","first_computed_at":"2026-05-18T00:11:52.236961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:52.236961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1jHTQnuZ/FspwFSBFf+vD7f8eYi1g5P7IRtSmEmWCNSFqYphWhJfkFIHGlnkvRnmim9JLZ0HN+IKxA3U/RomCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:52.237701Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.00543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca29eaf322a7aac3ca8ecb159a9f42681e82533427b07bc24799640912513131","sha256:34bdc52162bb8ab97218280f7d3a3d94f7a53e9268222cedad6784d0d1f391c0"],"state_sha256":"f00721c3e97678ac777b352c85d48ef1eacefe954480139742a06c7893661096"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J53NKQSGG22ONnUkvn6FsRnP9fPxqVlNGS11pnPs7PsEme8xSQ0rDrgXLWmsPSEfrnK7aisXR+S8KIyGUG3ZCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T05:00:59.136414Z","bundle_sha256":"f4a0d2f9bb16145495ac079780b9235cdf1ccdebf9310aed98de0b89e67bb5dc"}}