{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JGJPUEFPRZTUNDMOLUEKMETUXY","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":"6aff3ff8947861bd80010022b2be4b73961049b711bbf7dd93414bf1112e7a97","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T02:40:46Z","title_canon_sha256":"4e67c0ea444919389a13716c505b7fdf32934efbd95d781f352395ff91558822"},"schema_version":"1.0","source":{"id":"2506.01268","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01268","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01268v1","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01268","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"pith_short_12","alias_value":"JGJPUEFPRZTU","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"pith_short_16","alias_value":"JGJPUEFPRZTUNDMO","created_at":"2026-07-05T11:14:10Z"},{"alias_kind":"pith_short_8","alias_value":"JGJPUEFP","created_at":"2026-07-05T11:14:10Z"}],"graph_snapshots":[{"event_id":"sha256:896c30257fc53b660600b7a87cb5f24e940cac16271e2652d7fbb423c956e12d","target":"graph","created_at":"2026-07-05T11:14:10Z","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/2506.01268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"CleanS2S is a framework for human-like speech-to-speech interaction that advances conversational AI through single-file implementation and proactive dialogue capabilities. Our system integrates automatic speech recognition, large language models, and text-to-speech synthesis into a unified pipeline with real-time interruption handling, achieving low transition latency through full-duplex websocket connections and non-blocking I/O. Beyond conventional chatbot paradigms, we pioneer a proactive interaction mechanism, which combines memory systems with Subjective Action Judgement module, enabling ","authors_text":"Haolin Wang, Shuai Hu, Yazhe Niu, Yudong Lu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T02:40:46Z","title":"CleanS2S: Single-file Framework for Proactive Speech-to-Speech Interaction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01268","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":"sha256:077ecbe20e4bad70779eae201d22b9b228ded0a2a1b657dcfd5cb88f56d1ce84","target":"record","created_at":"2026-07-05T11:14:10Z","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":"6aff3ff8947861bd80010022b2be4b73961049b711bbf7dd93414bf1112e7a97","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T02:40:46Z","title_canon_sha256":"4e67c0ea444919389a13716c505b7fdf32934efbd95d781f352395ff91558822"},"schema_version":"1.0","source":{"id":"2506.01268","kind":"arxiv","version":1}},"canonical_sha256":"4992fa10af8e67468d8e5d08a61274be2bf3ad6d2b448b1e49876b00db32c32f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4992fa10af8e67468d8e5d08a61274be2bf3ad6d2b448b1e49876b00db32c32f","first_computed_at":"2026-07-05T11:14:10.979463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:10.979463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cF2+150S+jBUYzeb4v5ee3Hj49/gBWdGggA4pYVL9WOXXAA+Aq5w7mPZom6b1jtAbnoa92HXhpsFalp18TAvAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:10.979931Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01268","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:077ecbe20e4bad70779eae201d22b9b228ded0a2a1b657dcfd5cb88f56d1ce84","sha256:896c30257fc53b660600b7a87cb5f24e940cac16271e2652d7fbb423c956e12d"],"state_sha256":"dfcc153150bdf8c0bec3955aba3680b1d7f08d8c7a11fc72b1e1690005fba4a3"}