{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XXQLLWCDRCYOHW5R2YKDCH6DBY","short_pith_number":"pith:XXQLLWCD","canonical_record":{"source":{"id":"2604.01897","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-02T11:00:37Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d9dfe7b18982be050dbf78437210d4f73832d58223bae197c038a76d15a1d2ea","abstract_canon_sha256":"64515f1a7a4fc675adf98610a77c8cbea12800c3d8b7eb31cd3b12b751f4fcc1"},"schema_version":"1.0"},"canonical_sha256":"bde0b5d84388b0e3dbb1d614311fc30e3f1419e29d200ddb3d438d4d22cc7339","source":{"kind":"arxiv","id":"2604.01897","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.01897","created_at":"2026-07-01T01:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"2604.01897v5","created_at":"2026-07-01T01:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.01897","created_at":"2026-07-01T01:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"XXQLLWCDRCYO","created_at":"2026-07-01T01:17:49Z"},{"alias_kind":"pith_short_16","alias_value":"XXQLLWCDRCYOHW5R","created_at":"2026-07-01T01:17:49Z"},{"alias_kind":"pith_short_8","alias_value":"XXQLLWCD","created_at":"2026-07-01T01:17:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XXQLLWCDRCYOHW5R2YKDCH6DBY","target":"record","payload":{"canonical_record":{"source":{"id":"2604.01897","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-02T11:00:37Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d9dfe7b18982be050dbf78437210d4f73832d58223bae197c038a76d15a1d2ea","abstract_canon_sha256":"64515f1a7a4fc675adf98610a77c8cbea12800c3d8b7eb31cd3b12b751f4fcc1"},"schema_version":"1.0"},"canonical_sha256":"bde0b5d84388b0e3dbb1d614311fc30e3f1419e29d200ddb3d438d4d22cc7339","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:49.917227Z","signature_b64":"xBctOjNfEqIq/u4ZnbA0SroExhnX8M9K9krwiSMwbiBkPeANcQuIxSbOA4l9jbGut4yx3TeFr+Y8xwRPkSjGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bde0b5d84388b0e3dbb1d614311fc30e3f1419e29d200ddb3d438d4d22cc7339","last_reissued_at":"2026-07-01T01:17:49.916740Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:49.916740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.01897","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-01T01:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CcTEf/XNHp1AT446af2gVbeXjATViLuE++7lzapHoPq6kaqCtatJJ38MVMT2iYjRZGnktFLlZLTCEYChZFSzCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T13:32:58.555159Z"},"content_sha256":"624e26f118e012bf13454c56dce7aa6f44be3e838c90ed3a2514b415de2493cf","schema_version":"1.0","event_id":"sha256:624e26f118e012bf13454c56dce7aa6f44be3e838c90ed3a2514b415de2493cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XXQLLWCDRCYOHW5R2YKDCH6DBY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FastTurn: Unifying Acoustic and Streaming Semantic Cues for Low-Latency and Robust Turn Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"FastTurn detects conversation turns faster by fusing partial semantic cues from streaming speech recognition with acoustic features.","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bo Wu, Chengyou Wang, Chunjiang He, Hongfei Xue, Jimeng Zheng, Jingbin Hu, Lei Xie, Ruofei Chen, Shuiyuan Wang, Yuyu Ji, Zhou Zhu","submitted_at":"2026-04-02T11:00:37Z","abstract_excerpt":"Recent advances in AudioLLMs have enabled spoken dialogue systems to move beyond turn-based interaction toward real-time full-duplex communication, where the agent must decide when to speak, yield, or interrupt while the user is still talking. Existing full-duplex approaches either rely on voice activity cues, which lack semantic understanding, or on ASR-based modules, which introduce latency and degrade under overlapping speech and noise. Moreover, available datasets rarely capture realistic interaction dynamics, limiting evaluation and deployment. To mitigate the problem, we propose \\textbf{"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"FastTurn achieves higher decision accuracy with lower interruption latency than representative baselines and remains robust under challenging acoustic conditions, demonstrating its effectiveness for practical full-duplex dialogue systems.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That fusing partial CTC outputs with acoustic features yields reliable early semantic cues without introducing errors from incomplete observations, and that the new real-dialogue test set sufficiently represents deployment conditions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FastTurn unifies acoustic features and streaming CTC decoding for low-latency, robust turn detection in full-duplex dialogue systems and releases a realistic human-dialogue test set.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"FastTurn detects conversation turns faster by fusing partial semantic cues from streaming speech recognition with acoustic features.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9de29b177ff932eba2ddd51774b894193bdf687e4acfd103e9c9e1a42c16b733"},"source":{"id":"2604.01897","kind":"arxiv","version":5},"verdict":{"id":"b5001cf0-088a-4752-83d3-21ee490e2370","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T20:52:02.722754Z","strongest_claim":"FastTurn achieves higher decision accuracy with lower interruption latency than representative baselines and remains robust under challenging acoustic conditions, demonstrating its effectiveness for practical full-duplex dialogue systems.","one_line_summary":"FastTurn unifies acoustic features and streaming CTC decoding for low-latency, robust turn detection in full-duplex dialogue systems and releases a realistic human-dialogue test set.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That fusing partial CTC outputs with acoustic features yields reliable early semantic cues without introducing errors from incomplete observations, and that the new real-dialogue test set sufficiently represents deployment conditions.","pith_extraction_headline":"FastTurn detects conversation turns faster by fusing partial semantic cues from streaming speech recognition with acoustic features."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.01897/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":"b5001cf0-088a-4752-83d3-21ee490e2370"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-01T01:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tzkK1BU+bJNdEAdtACrhVgUukunCBQVabO0A6dtrHN6qGUSwoC7MNC/LjhZQl8HZy5qgdK5+zuYEBUUroZuMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T13:32:58.555522Z"},"content_sha256":"96777737f2c0bfe5bb5892efd8d9259319e1ea00ba39f58e5daee4c375903e7d","schema_version":"1.0","event_id":"sha256:96777737f2c0bfe5bb5892efd8d9259319e1ea00ba39f58e5daee4c375903e7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XXQLLWCDRCYOHW5R2YKDCH6DBY/bundle.json","state_url":"https://pith.science/pith/XXQLLWCDRCYOHW5R2YKDCH6DBY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XXQLLWCDRCYOHW5R2YKDCH6DBY/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":"2026-08-01T13:32:58Z","links":{"resolver":"https://pith.science/pith/XXQLLWCDRCYOHW5R2YKDCH6DBY","bundle":"https://pith.science/pith/XXQLLWCDRCYOHW5R2YKDCH6DBY/bundle.json","state":"https://pith.science/pith/XXQLLWCDRCYOHW5R2YKDCH6DBY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XXQLLWCDRCYOHW5R2YKDCH6DBY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XXQLLWCDRCYOHW5R2YKDCH6DBY","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":"64515f1a7a4fc675adf98610a77c8cbea12800c3d8b7eb31cd3b12b751f4fcc1","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-02T11:00:37Z","title_canon_sha256":"d9dfe7b18982be050dbf78437210d4f73832d58223bae197c038a76d15a1d2ea"},"schema_version":"1.0","source":{"id":"2604.01897","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.01897","created_at":"2026-07-01T01:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"2604.01897v5","created_at":"2026-07-01T01:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.01897","created_at":"2026-07-01T01:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"XXQLLWCDRCYO","created_at":"2026-07-01T01:17:49Z"},{"alias_kind":"pith_short_16","alias_value":"XXQLLWCDRCYOHW5R","created_at":"2026-07-01T01:17:49Z"},{"alias_kind":"pith_short_8","alias_value":"XXQLLWCD","created_at":"2026-07-01T01:17:49Z"}],"graph_snapshots":[{"event_id":"sha256:96777737f2c0bfe5bb5892efd8d9259319e1ea00ba39f58e5daee4c375903e7d","target":"graph","created_at":"2026-07-01T01:17:49Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"FastTurn achieves higher decision accuracy with lower interruption latency than representative baselines and remains robust under challenging acoustic conditions, demonstrating its effectiveness for practical full-duplex dialogue systems."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That fusing partial CTC outputs with acoustic features yields reliable early semantic cues without introducing errors from incomplete observations, and that the new real-dialogue test set sufficiently represents deployment conditions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"FastTurn unifies acoustic features and streaming CTC decoding for low-latency, robust turn detection in full-duplex dialogue systems and releases a realistic human-dialogue test set."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"FastTurn detects conversation turns faster by fusing partial semantic cues from streaming speech recognition with acoustic features."}],"snapshot_sha256":"9de29b177ff932eba2ddd51774b894193bdf687e4acfd103e9c9e1a42c16b733"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.01897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in AudioLLMs have enabled spoken dialogue systems to move beyond turn-based interaction toward real-time full-duplex communication, where the agent must decide when to speak, yield, or interrupt while the user is still talking. Existing full-duplex approaches either rely on voice activity cues, which lack semantic understanding, or on ASR-based modules, which introduce latency and degrade under overlapping speech and noise. Moreover, available datasets rarely capture realistic interaction dynamics, limiting evaluation and deployment. To mitigate the problem, we propose \\textbf{","authors_text":"Bo Wu, Chengyou Wang, Chunjiang He, Hongfei Xue, Jimeng Zheng, Jingbin Hu, Lei Xie, Ruofei Chen, Shuiyuan Wang, Yuyu Ji, Zhou Zhu","cross_cats":["eess.AS"],"headline":"FastTurn detects conversation turns faster by fusing partial semantic cues from streaming speech recognition with acoustic features.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-02T11:00:37Z","title":"FastTurn: Unifying Acoustic and Streaming Semantic Cues for Low-Latency and Robust Turn Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.01897","kind":"arxiv","version":5},"verdict":{"created_at":"2026-05-13T20:52:02.722754Z","id":"b5001cf0-088a-4752-83d3-21ee490e2370","model_set":{"reader":"grok-4.3"},"one_line_summary":"FastTurn unifies acoustic features and streaming CTC decoding for low-latency, robust turn detection in full-duplex dialogue systems and releases a realistic human-dialogue test set.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"FastTurn detects conversation turns faster by fusing partial semantic cues from streaming speech recognition with acoustic features.","strongest_claim":"FastTurn achieves higher decision accuracy with lower interruption latency than representative baselines and remains robust under challenging acoustic conditions, demonstrating its effectiveness for practical full-duplex dialogue systems.","weakest_assumption":"That fusing partial CTC outputs with acoustic features yields reliable early semantic cues without introducing errors from incomplete observations, and that the new real-dialogue test set sufficiently represents deployment conditions."}},"verdict_id":"b5001cf0-088a-4752-83d3-21ee490e2370"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:624e26f118e012bf13454c56dce7aa6f44be3e838c90ed3a2514b415de2493cf","target":"record","created_at":"2026-07-01T01:17:49Z","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":"64515f1a7a4fc675adf98610a77c8cbea12800c3d8b7eb31cd3b12b751f4fcc1","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-02T11:00:37Z","title_canon_sha256":"d9dfe7b18982be050dbf78437210d4f73832d58223bae197c038a76d15a1d2ea"},"schema_version":"1.0","source":{"id":"2604.01897","kind":"arxiv","version":5}},"canonical_sha256":"bde0b5d84388b0e3dbb1d614311fc30e3f1419e29d200ddb3d438d4d22cc7339","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bde0b5d84388b0e3dbb1d614311fc30e3f1419e29d200ddb3d438d4d22cc7339","first_computed_at":"2026-07-01T01:17:49.916740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:49.916740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xBctOjNfEqIq/u4ZnbA0SroExhnX8M9K9krwiSMwbiBkPeANcQuIxSbOA4l9jbGut4yx3TeFr+Y8xwRPkSjGCQ==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:49.917227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.01897","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:624e26f118e012bf13454c56dce7aa6f44be3e838c90ed3a2514b415de2493cf","sha256:96777737f2c0bfe5bb5892efd8d9259319e1ea00ba39f58e5daee4c375903e7d"],"state_sha256":"54e7234f0a1a16f09f8a33aeb1f6dc48ae6e81d8daf15dda3c849b79b1f356bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZiS2s3WRJIehpkSlYQx2Jic20qS4lNg/YBW29DJldFf5xbELNqY6My3yP37FIgqn+3Vn8gZ71NyIQO4vpIJkAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T13:32:58.560517Z","bundle_sha256":"78b98c064d3d12227e7e221271b33ee3bdb86128e3fbdb0ad7c50f979e93abd4"}}