{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BWIKTLZAB3XACTMDTRLFAU5J7Z","short_pith_number":"pith:BWIKTLZA","canonical_record":{"source":{"id":"1908.02404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-07T00:04:58Z","cross_cats_sorted":[],"title_canon_sha256":"fb1857b3893ef2deb62b5d13ed29a0f160c851eff3911ee0b0ac4578f3187859","abstract_canon_sha256":"eb68b111d33203da80c269fffe11d49a10cbb3528a6e24324622819a2ed0431a"},"schema_version":"1.0"},"canonical_sha256":"0d90a9af200eee014d839c565053a9fe65119857780b98aa0449af6fc82782bd","source":{"kind":"arxiv","id":"1908.02404","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.02404","created_at":"2026-07-04T23:52:08Z"},{"alias_kind":"arxiv_version","alias_value":"1908.02404v1","created_at":"2026-07-04T23:52:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02404","created_at":"2026-07-04T23:52:08Z"},{"alias_kind":"pith_short_12","alias_value":"BWIKTLZAB3XA","created_at":"2026-07-04T23:52:08Z"},{"alias_kind":"pith_short_16","alias_value":"BWIKTLZAB3XACTMD","created_at":"2026-07-04T23:52:08Z"},{"alias_kind":"pith_short_8","alias_value":"BWIKTLZA","created_at":"2026-07-04T23:52:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BWIKTLZAB3XACTMDTRLFAU5J7Z","target":"record","payload":{"canonical_record":{"source":{"id":"1908.02404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-07T00:04:58Z","cross_cats_sorted":[],"title_canon_sha256":"fb1857b3893ef2deb62b5d13ed29a0f160c851eff3911ee0b0ac4578f3187859","abstract_canon_sha256":"eb68b111d33203da80c269fffe11d49a10cbb3528a6e24324622819a2ed0431a"},"schema_version":"1.0"},"canonical_sha256":"0d90a9af200eee014d839c565053a9fe65119857780b98aa0449af6fc82782bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:52:08.551188Z","signature_b64":"dAuk8YDuCFffo1o1WvLebhaqX/2EjT3jkxmrHhBwBJUTYz4CT83BE8/7J9bSgW0Nqw9gX+9vqRnjKhzKov5FCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d90a9af200eee014d839c565053a9fe65119857780b98aa0449af6fc82782bd","last_reissued_at":"2026-07-04T23:52:08.550845Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:52:08.550845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.02404","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":"2026-07-04T23:52:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hrP4uNf2D5Tw/O3v1nyQZ+aXHTFxNMhbcaEzrRDtgcWRSTvqvNGxBTkqiFdCs7Kll6jJ0kKmbQHNs42Cn5zTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:22:41.204926Z"},"content_sha256":"2b5420c8bba482fc079a532102f387d8e2f2a8d3e0b0fc0f958f62fec9638052","schema_version":"1.0","event_id":"sha256:2b5420c8bba482fc079a532102f387d8e2f2a8d3e0b0fc0f958f62fec9638052"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BWIKTLZAB3XACTMDTRLFAU5J7Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast and Accurate Capitalization and Punctuation for Automatic Speech Recognition Using Transformer and Chunk Merging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binh Nguyen, Hien Nguyen, Luong Chi Mai, Pham Ngoc Phuong, Quoc Truong Do, The-Loc Nguyen, Vu Bao Hung Nguyen","submitted_at":"2019-08-07T00:04:58Z","abstract_excerpt":"In recent years, studies on automatic speech recognition (ASR) have shown outstanding results that reach human parity on short speech segments. However, there are still difficulties in standardizing the output of ASR such as capitalization and punctuation restoration for long-speech transcription. The problems obstruct readers to understand the ASR output semantically and also cause difficulties for natural language processing models such as NER, POS and semantic parsing. In this paper, we propose a method to restore the punctuation and capitalization for long-speech ASR transcription. The met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02404","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/1908.02404/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":"2026-07-04T23:52:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iLU6JZ0JF0oF/ubcHjA2xEJ5c89xd4aEoAApEymcGZkR1FBWh+0ZYPT5giEzffraVOWnm/DCWDbbyIw68e5gAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:22:41.205510Z"},"content_sha256":"36e0660c81468180959dde798a565263a3254975b2477697fe8ea83675fbd476","schema_version":"1.0","event_id":"sha256:36e0660c81468180959dde798a565263a3254975b2477697fe8ea83675fbd476"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BWIKTLZAB3XACTMDTRLFAU5J7Z/bundle.json","state_url":"https://pith.science/pith/BWIKTLZAB3XACTMDTRLFAU5J7Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BWIKTLZAB3XACTMDTRLFAU5J7Z/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":"2026-08-14T21:22:41Z","links":{"resolver":"https://pith.science/pith/BWIKTLZAB3XACTMDTRLFAU5J7Z","bundle":"https://pith.science/pith/BWIKTLZAB3XACTMDTRLFAU5J7Z/bundle.json","state":"https://pith.science/pith/BWIKTLZAB3XACTMDTRLFAU5J7Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BWIKTLZAB3XACTMDTRLFAU5J7Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BWIKTLZAB3XACTMDTRLFAU5J7Z","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":"eb68b111d33203da80c269fffe11d49a10cbb3528a6e24324622819a2ed0431a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-07T00:04:58Z","title_canon_sha256":"fb1857b3893ef2deb62b5d13ed29a0f160c851eff3911ee0b0ac4578f3187859"},"schema_version":"1.0","source":{"id":"1908.02404","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.02404","created_at":"2026-07-04T23:52:08Z"},{"alias_kind":"arxiv_version","alias_value":"1908.02404v1","created_at":"2026-07-04T23:52:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02404","created_at":"2026-07-04T23:52:08Z"},{"alias_kind":"pith_short_12","alias_value":"BWIKTLZAB3XA","created_at":"2026-07-04T23:52:08Z"},{"alias_kind":"pith_short_16","alias_value":"BWIKTLZAB3XACTMD","created_at":"2026-07-04T23:52:08Z"},{"alias_kind":"pith_short_8","alias_value":"BWIKTLZA","created_at":"2026-07-04T23:52:08Z"}],"graph_snapshots":[{"event_id":"sha256:36e0660c81468180959dde798a565263a3254975b2477697fe8ea83675fbd476","target":"graph","created_at":"2026-07-04T23:52:08Z","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/1908.02404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, studies on automatic speech recognition (ASR) have shown outstanding results that reach human parity on short speech segments. However, there are still difficulties in standardizing the output of ASR such as capitalization and punctuation restoration for long-speech transcription. The problems obstruct readers to understand the ASR output semantically and also cause difficulties for natural language processing models such as NER, POS and semantic parsing. In this paper, we propose a method to restore the punctuation and capitalization for long-speech ASR transcription. The met","authors_text":"Binh Nguyen, Hien Nguyen, Luong Chi Mai, Pham Ngoc Phuong, Quoc Truong Do, The-Loc Nguyen, Vu Bao Hung Nguyen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-07T00:04:58Z","title":"Fast and Accurate Capitalization and Punctuation for Automatic Speech Recognition Using Transformer and Chunk Merging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02404","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":"sha256:2b5420c8bba482fc079a532102f387d8e2f2a8d3e0b0fc0f958f62fec9638052","target":"record","created_at":"2026-07-04T23:52:08Z","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":"eb68b111d33203da80c269fffe11d49a10cbb3528a6e24324622819a2ed0431a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-07T00:04:58Z","title_canon_sha256":"fb1857b3893ef2deb62b5d13ed29a0f160c851eff3911ee0b0ac4578f3187859"},"schema_version":"1.0","source":{"id":"1908.02404","kind":"arxiv","version":1}},"canonical_sha256":"0d90a9af200eee014d839c565053a9fe65119857780b98aa0449af6fc82782bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d90a9af200eee014d839c565053a9fe65119857780b98aa0449af6fc82782bd","first_computed_at":"2026-07-04T23:52:08.550845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:52:08.550845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dAuk8YDuCFffo1o1WvLebhaqX/2EjT3jkxmrHhBwBJUTYz4CT83BE8/7J9bSgW0Nqw9gX+9vqRnjKhzKov5FCg==","signature_status":"signed_v1","signed_at":"2026-07-04T23:52:08.551188Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.02404","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b5420c8bba482fc079a532102f387d8e2f2a8d3e0b0fc0f958f62fec9638052","sha256:36e0660c81468180959dde798a565263a3254975b2477697fe8ea83675fbd476"],"state_sha256":"6f6589fc68d702c423d2a6b5fd6243b0bef0ccd231de0206fd16f0c4060e9bca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sjOcXoH6h+STdqKJF1qFh3xxZrbdZJESi7b6FvnEoJIVdntKEc6yf9nGZuckTSFOEDttrrKIsWxuq1cJJlkpCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T21:22:41.210349Z","bundle_sha256":"8dbabac6d80377d75ea24cdc7bb35a4e425b763740a3f16b4397c7e9e89b931a"}}