{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DNYLA6JJPHW6FRUQRW7MXM5ES7","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":"2d83df4d717fdfa9c39a4f7ab7258492707815aa5265aea69800e20e5102263e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T21:43:37Z","title_canon_sha256":"7bd0fc62455a8928cf201e7e8bd11092653f095c79ed9c799726d1f4b97a4281"},"schema_version":"1.0","source":{"id":"2506.00722","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00722","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00722v1","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00722","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_12","alias_value":"DNYLA6JJPHW6","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_16","alias_value":"DNYLA6JJPHW6FRUQ","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_8","alias_value":"DNYLA6JJ","created_at":"2026-07-05T11:13:39Z"}],"graph_snapshots":[{"event_id":"sha256:d6080b5f534e98fa0636bb484938b280ee5bd4b1c5218167404e5599db2b7afc","target":"graph","created_at":"2026-07-05T11:13:39Z","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/2506.00722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unlike traditional cascaded pipelines, end-to-end (E2E) spoken dialogue systems preserve full differentiability and capture non-phonemic information, making them well-suited for modeling spoken interactions. However, existing E2E approaches often require large-scale training data and generates responses lacking semantic coherence. We propose a simple yet effective strategy leveraging a chain-of-thought (CoT) formulation, ensuring that training on conversational data remains closely aligned with the multimodal language model (LM)'s pre-training on speech recognition~(ASR), text-to-speech synthe","authors_text":"Emiru Tsunoo, Hayato Futami, Jee-weon Jung, Jiatong Shi, Jinchuan Tian, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T21:43:37Z","title":"Chain-of-Thought Training for Open E2E Spoken Dialogue Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00722","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:f4a71ec5e1c3e2e3353c38dd898da6345e7fa1238e5079b1e52f7aa3c72796c6","target":"record","created_at":"2026-07-05T11:13:39Z","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":"2d83df4d717fdfa9c39a4f7ab7258492707815aa5265aea69800e20e5102263e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T21:43:37Z","title_canon_sha256":"7bd0fc62455a8928cf201e7e8bd11092653f095c79ed9c799726d1f4b97a4281"},"schema_version":"1.0","source":{"id":"2506.00722","kind":"arxiv","version":1}},"canonical_sha256":"1b70b0792979ede2c6908dbecbb3a497dea5ba7ba8f1a3ea0e4aaa2661380bf0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b70b0792979ede2c6908dbecbb3a497dea5ba7ba8f1a3ea0e4aaa2661380bf0","first_computed_at":"2026-07-05T11:13:39.301239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:39.301239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TeTDMr+OBbjLh9NmMyEQ7C4KLJkewHssMp8k7kEzgrvAUbpOjQMc8S5gl0GqhWb0o1onJfREE+Jq+HBk5VgLCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:39.301737Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00722","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4a71ec5e1c3e2e3353c38dd898da6345e7fa1238e5079b1e52f7aa3c72796c6","sha256:d6080b5f534e98fa0636bb484938b280ee5bd4b1c5218167404e5599db2b7afc"],"state_sha256":"4118c22ec043735cc18d3525d1ecfbdcaafcc46ff5f386f51a182fe86ca95b01"}