{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JY2HNHE6DB6TQOR3VFRHEEAYRQ","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":"876ba734eb7c62470bb98113ab3690dc820f052504ee5c2c68d71753ed541492","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-27T03:16:22Z","title_canon_sha256":"c2e8d2ed1fcfd771ad46a9d5a7c5633a4a58a42c05547595ca972eddb485c5d3"},"schema_version":"1.0","source":{"id":"2406.18862","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18862","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18862v1","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18862","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"pith_short_12","alias_value":"JY2HNHE6DB6T","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"pith_short_16","alias_value":"JY2HNHE6DB6TQOR3","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"pith_short_8","alias_value":"JY2HNHE6","created_at":"2026-07-05T08:37:26Z"}],"graph_snapshots":[{"event_id":"sha256:f7abb341df4417825f72b92641e4558c8c8ba89381aa87328b093d0aa29f7ccf","target":"graph","created_at":"2026-07-05T08:37:26Z","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/2406.18862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unified speech-text models like SpeechGPT, VioLA, and AudioPaLM have shown impressive performance across various speech-related tasks, especially in Automatic Speech Recognition (ASR). These models typically adopt a unified method to model discrete speech and text tokens, followed by training a decoder-only transformer. However, they are all designed for non-streaming ASR tasks, where the entire speech utterance is needed during decoding. Hence, we introduce a decoder-only model exclusively designed for streaming recognition, incorporating a dedicated boundary token to facilitate streaming rec","authors_text":"Changhao Shan, Lei Xie, Peikun Chen, Qing Yang, Sining Sun","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-27T03:16:22Z","title":"Streaming Decoder-Only Automatic Speech Recognition with Discrete Speech Units: A Pilot Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18862","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":"sha256:6c1a81d2730b2c08f13f39fc21553e370ba4ae70bfd935f09bba701527f8fc14","target":"record","created_at":"2026-07-05T08:37:26Z","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":"876ba734eb7c62470bb98113ab3690dc820f052504ee5c2c68d71753ed541492","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-27T03:16:22Z","title_canon_sha256":"c2e8d2ed1fcfd771ad46a9d5a7c5633a4a58a42c05547595ca972eddb485c5d3"},"schema_version":"1.0","source":{"id":"2406.18862","kind":"arxiv","version":1}},"canonical_sha256":"4e34769c9e187d383a3ba9627210188c006aab5567816faf5d01dd93f8bd5956","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e34769c9e187d383a3ba9627210188c006aab5567816faf5d01dd93f8bd5956","first_computed_at":"2026-07-05T08:37:26.800134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:26.800134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hX2G7Xsq6bN/A4yeKNn6mSO+KmleziS6MDeQ8O7OSapyItxlaK9jGrvhcEK7jI/yBiIrbAkO/vHHX7OWSddRBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:26.800506Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.18862","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c1a81d2730b2c08f13f39fc21553e370ba4ae70bfd935f09bba701527f8fc14","sha256:f7abb341df4417825f72b92641e4558c8c8ba89381aa87328b093d0aa29f7ccf"],"state_sha256":"0536b96a41280d0fd25c2a370995f9a44c604303598362016d79f87eb9b27844"}