{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L4XVFA5UDWAP5G4JVG4S677BW6","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":"c3290f23804a91109934df6a55f6fb8a164e0343b194faf3e43a1eda1347f86b","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-08T10:54:23Z","title_canon_sha256":"d76865f605ca589bf74f590d0952ddc9ae0524486155948fbd9ea70936ce40e6"},"schema_version":"1.0","source":{"id":"2506.07081","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07081","created_at":"2026-07-05T11:24:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07081v2","created_at":"2026-07-05T11:24:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07081","created_at":"2026-07-05T11:24:22Z"},{"alias_kind":"pith_short_12","alias_value":"L4XVFA5UDWAP","created_at":"2026-07-05T11:24:22Z"},{"alias_kind":"pith_short_16","alias_value":"L4XVFA5UDWAP5G4J","created_at":"2026-07-05T11:24:22Z"},{"alias_kind":"pith_short_8","alias_value":"L4XVFA5U","created_at":"2026-07-05T11:24:22Z"}],"graph_snapshots":[{"event_id":"sha256:424f16ce0349dd90a448f5acc5768228ac45920346add9ed79ee227708a9f823","target":"graph","created_at":"2026-07-05T11:24:22Z","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/2506.07081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate, low-latency endpointing is crucial for effective spoken dialogue systems. While traditional endpointers often rely on spectrum-based audio features, this work proposes real-time speech endpointing for multi-turn dialogues using streaming, low-bitrate Neural Audio Codec (NAC) features, building upon recent advancements in neural audio codecs. To further reduce cutoff errors, we introduce a novel label delay training scheme. At a fixed median latency of 160 ms, our combined NAC and label delay approach achieves significant relative cutoff error reductions: 42.7% for a single-stream end","authors_text":"Jan Cernocky, Petr Schwarz, Sathvik Udupa, Shinji Watanabe","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-08T10:54:23Z","title":"Streaming Endpointer for Spoken Dialogue using Neural Audio Codecs and Label-Delayed Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07081","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":"sha256:9d75c73f311b69a4e2434480bd4c37a7633301c460d25d1d046b929b45d83d66","target":"record","created_at":"2026-07-05T11:24:22Z","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":"c3290f23804a91109934df6a55f6fb8a164e0343b194faf3e43a1eda1347f86b","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-08T10:54:23Z","title_canon_sha256":"d76865f605ca589bf74f590d0952ddc9ae0524486155948fbd9ea70936ce40e6"},"schema_version":"1.0","source":{"id":"2506.07081","kind":"arxiv","version":2}},"canonical_sha256":"5f2f5283b41d80fe9b89a9b92f7fe1b7afa91348b11f48403306c7bc0b6f5533","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f2f5283b41d80fe9b89a9b92f7fe1b7afa91348b11f48403306c7bc0b6f5533","first_computed_at":"2026-07-05T11:24:22.342640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:22.342640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0W3ObtLK1Qx/iT4Y8g8ZfW2cD0tfprTSPBQ6JLsg+DRxAqKIxGzaGAZfhTnMwRbCjSdkfB2+HUtd69a29nxEAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:22.343203Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07081","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d75c73f311b69a4e2434480bd4c37a7633301c460d25d1d046b929b45d83d66","sha256:424f16ce0349dd90a448f5acc5768228ac45920346add9ed79ee227708a9f823"],"state_sha256":"56f51928612c5ede4cb2b69541e59a94e0b0da1aa5ee4f24f4f7f818f9a22395"}