{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PLRKIF3W3K26R7EBQYVYMAEXJ3","short_pith_number":"pith:PLRKIF3W","canonical_record":{"source":{"id":"2306.01296","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-02T06:46:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"87143942be3730241e4915ac3438c94580fb609ef3e026557e6df4446e419468","abstract_canon_sha256":"bc17d217f74052f5158c92f9aff90e2fd676a0d0147019837ffa54f530861712"},"schema_version":"1.0"},"canonical_sha256":"7ae2a41776dab5e8fc81862b8600974ef6a858dfc3ec762aa96eccca2cd2e3d1","source":{"kind":"arxiv","id":"2306.01296","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PLRKIF3W3K26R7EBQYVYMAEXJ3","target":"record","payload":{"canonical_record":{"source":{"id":"2306.01296","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-02T06:46:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"87143942be3730241e4915ac3438c94580fb609ef3e026557e6df4446e419468","abstract_canon_sha256":"bc17d217f74052f5158c92f9aff90e2fd676a0d0147019837ffa54f530861712"},"schema_version":"1.0"},"canonical_sha256":"7ae2a41776dab5e8fc81862b8600974ef6a858dfc3ec762aa96eccca2cd2e3d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:29.122762Z","signature_b64":"jvYAO56NvfmXJ6rcvjRN9o0oKT4fEwEyHILQmEWirCNE1kTgtIQuC0ujIsAY0hvwc7k9yHQGIr0ySYO69yeUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ae2a41776dab5e8fc81862b8600974ef6a858dfc3ec762aa96eccca2cd2e3d1","last_reissued_at":"2026-07-05T07:06:29.122310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:29.122310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.01296","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":"2026-07-05T07:06:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YOh7VwkTJ4vB1i9kpwqPyMKcYgWVD2x6CZyy2A89esq4wcLQMfQuw0kQ9rYjhwJFJro0r65al3v2zAaZFPnBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:56:50.461341Z"},"content_sha256":"72147582a6e4182d07c8369c2db122748b8dfa74eff3db49161720f794a0f1c7","schema_version":"1.0","event_id":"sha256:72147582a6e4182d07c8369c2db122748b8dfa74eff3db49161720f794a0f1c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PLRKIF3W3K26R7EBQYVYMAEXJ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Hanbyul Kim, Lukas Lee, Seolki Baek, Seunghyun Seo","submitted_at":"2023-06-02T06:46:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01296","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/2306.01296/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":"2026-07-05T07:06:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O5s2+WQOoNiFs9rsvp8OOJUKcq5ESFyADDNL+M+rfcDdL4Txt7vO5as+hH5T4Qmhj/fJXpUvTJZ9oK0Dwz88DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:56:50.461974Z"},"content_sha256":"b6e776c9c986d5ca65a7e02f6e12158320de6969ec50d976cb5e2d82a896ee62","schema_version":"1.0","event_id":"sha256:b6e776c9c986d5ca65a7e02f6e12158320de6969ec50d976cb5e2d82a896ee62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3/bundle.json","state_url":"https://pith.science/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3/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":"2026-07-09T05:56:50Z","links":{"resolver":"https://pith.science/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3","bundle":"https://pith.science/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3/bundle.json","state":"https://pith.science/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3i38hi3gQOL16Ca0IAVJFyGKMhBua1SslbmkIIAWhDXoRltMK2c/Tjl38OfO6lKa8RGFbeuK4V8rnUXdor70BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:56:50.465831Z","bundle_sha256":"20a055e59efb36b5506002384bbb18fb9c1591c7d67c2114d44e09ea6b299f14"}}