{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:45DQHKRNB45O6QJIZQNNPRGJTS","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":"c36b78c3dd984daa3962db5db7b986237ec869cb737b93711d01ccd71a743257","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T07:34:20Z","title_canon_sha256":"f833c3c50ff0c46b818ce99c269f7e2b1285a8e4d526e25bb181af2cfd92b5ba"},"schema_version":"1.0","source":{"id":"2211.08726","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.08726","created_at":"2026-07-05T06:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2211.08726v2","created_at":"2026-07-05T06:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08726","created_at":"2026-07-05T06:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"45DQHKRNB45O","created_at":"2026-07-05T06:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"45DQHKRNB45O6QJI","created_at":"2026-07-05T06:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"45DQHKRN","created_at":"2026-07-05T06:09:06Z"}],"graph_snapshots":[{"event_id":"sha256:2c2fb0f0f89fe2f0750b1128797caa51fbba6262c64ab86b61e33eeed5f1d7aa","target":"graph","created_at":"2026-07-05T06:09:06Z","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/2211.08726/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Disfluency detection has mainly been solved in a pipeline approach, as post-processing of speech recognition. In this study, we propose Transformer-based encoder-decoder models that jointly solve speech recognition and disfluency detection, which work in a streaming manner. Compared to pipeline approaches, the joint models can leverage acoustic information that makes disfluency detection robust to recognition errors and provide non-verbal clues. Moreover, joint modeling results in low-latency and lightweight inference. We investigate two joint model variants for streaming disfluency detection:","authors_text":"Emiru Tsunoo, Hayato Futami, Kentaro Shibata, Shinji Watanabe, Siddhant Arora, Takao Okuda, Yosuke Kashiwagi","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T07:34:20Z","title":"Streaming Joint Speech Recognition and Disfluency Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08726","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":"sha256:6cd6320d0de077a8c74f0ac663fff2554ff6dee84cc0a804877ca59846001383","target":"record","created_at":"2026-07-05T06:09:06Z","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":"c36b78c3dd984daa3962db5db7b986237ec869cb737b93711d01ccd71a743257","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T07:34:20Z","title_canon_sha256":"f833c3c50ff0c46b818ce99c269f7e2b1285a8e4d526e25bb181af2cfd92b5ba"},"schema_version":"1.0","source":{"id":"2211.08726","kind":"arxiv","version":2}},"canonical_sha256":"e74703aa2d0f3aef4128cc1ad7c4c99c97f6da12f22ad43598cccc3abecb8408","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e74703aa2d0f3aef4128cc1ad7c4c99c97f6da12f22ad43598cccc3abecb8408","first_computed_at":"2026-07-05T06:09:06.798284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:06.798284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oT3nk6VIs2Nt6oMNpDpi9YLyh0Yrh7HItfI16AJkDcK9mSsMQxhPIC+nemmsom/V0eejvrFNnOCMfaDX86TRAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:06.798773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.08726","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cd6320d0de077a8c74f0ac663fff2554ff6dee84cc0a804877ca59846001383","sha256:2c2fb0f0f89fe2f0750b1128797caa51fbba6262c64ab86b61e33eeed5f1d7aa"],"state_sha256":"8b6a4390b6313d32cbaf9c1d1b47cf8d983e92073a89427ffead7387fe8ce176"}