{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PLRKIF3W3K26R7EBQYVYMAEXJ3","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":"bc17d217f74052f5158c92f9aff90e2fd676a0d0147019837ffa54f530861712","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-02T06:46:14Z","title_canon_sha256":"87143942be3730241e4915ac3438c94580fb609ef3e026557e6df4446e419468"},"schema_version":"1.0","source":{"id":"2306.01296","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.01296","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"arxiv_version","alias_value":"2306.01296v1","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01296","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"pith_short_12","alias_value":"PLRKIF3W3K26","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"pith_short_16","alias_value":"PLRKIF3W3K26R7EB","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"pith_short_8","alias_value":"PLRKIF3W","created_at":"2026-07-05T07:06:29Z"}],"graph_snapshots":[{"event_id":"sha256:b6e776c9c986d5ca65a7e02f6e12158320de6969ec50d976cb5e2d82a896ee62","target":"graph","created_at":"2026-07-05T07:06:29Z","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/2306.01296/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Punctuated text prediction is crucial for automatic speech recognition as it enhances readability and impacts downstream natural language processing tasks. In streaming scenarios, the ability to predict punctuation in real-time is particularly desirable but presents a difficult technical challenge. In this work, we propose a method for predicting punctuated text from input speech using a chunk-based Transformer encoder trained with Connectionist Temporal Classification (CTC) loss. The acoustic model trained with long sequences by concatenating the input and target sequences can learn punctuati","authors_text":"Hanbyul Kim, Lukas Lee, Seolki Baek, Seunghyun Seo","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-02T06:46:14Z","title":"Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01296","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":"sha256:72147582a6e4182d07c8369c2db122748b8dfa74eff3db49161720f794a0f1c7","target":"record","created_at":"2026-07-05T07:06:29Z","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":"bc17d217f74052f5158c92f9aff90e2fd676a0d0147019837ffa54f530861712","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-02T06:46:14Z","title_canon_sha256":"87143942be3730241e4915ac3438c94580fb609ef3e026557e6df4446e419468"},"schema_version":"1.0","source":{"id":"2306.01296","kind":"arxiv","version":1}},"canonical_sha256":"7ae2a41776dab5e8fc81862b8600974ef6a858dfc3ec762aa96eccca2cd2e3d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ae2a41776dab5e8fc81862b8600974ef6a858dfc3ec762aa96eccca2cd2e3d1","first_computed_at":"2026-07-05T07:06:29.122310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:29.122310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jvYAO56NvfmXJ6rcvjRN9o0oKT4fEwEyHILQmEWirCNE1kTgtIQuC0ujIsAY0hvwc7k9yHQGIr0ySYO69yeUDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:29.122762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.01296","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72147582a6e4182d07c8369c2db122748b8dfa74eff3db49161720f794a0f1c7","sha256:b6e776c9c986d5ca65a7e02f6e12158320de6969ec50d976cb5e2d82a896ee62"],"state_sha256":"00604e09ac6ffbbc17cd03d98550bb0d2f62fcea7a1b0b2c78c6a03c18c88f8f"}