{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5P2DDVRUBSOQWWTDTE2Z5OHAEY","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":"3a30f5bf152b719177f38ed6a247fb0de5a25c958258b1c712777ecab8e3bc45","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-25T15:12:56Z","title_canon_sha256":"fcfdf26a09795c6657403c3c31aab9cab8c9431be2de532af7c8ef9d669472a0"},"schema_version":"1.0","source":{"id":"2605.25930","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25930","created_at":"2026-05-26T02:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25930v1","created_at":"2026-05-26T02:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25930","created_at":"2026-05-26T02:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"5P2DDVRUBSOQ","created_at":"2026-05-26T02:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"5P2DDVRUBSOQWWTD","created_at":"2026-05-26T02:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"5P2DDVRU","created_at":"2026-05-26T02:05:18Z"}],"graph_snapshots":[{"event_id":"sha256:e658874bc3f8e77e76a394ca6ea9fbd2f883e974a0aefd11b02af2e142e78e0f","target":"graph","created_at":"2026-05-26T02:05:18Z","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/2605.25930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech editing and zero-shot Text-to-Speech (TTS) share a similar generative foundation conditioned on speech prompts, yet speech editing demands far stricter local acoustic consistency with surrounding unedited content. While prior work has shown that Supervised Fine-Tuning (SFT) enables TTS models to acquire functional editing capability, this approach remains fundamentally bottlenecked by imperfect paired editing data and coarse-grained optimization signals. To address these limitations, we propose CosyEdit2, a speech editing model built on a two-stage post-training framework that progresse","authors_text":"Hui Wang, Jiaming Zhou, Junyang Chen, Yongchang Gan, Yong Qin, Yuhang Jia","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-25T15:12:56Z","title":"CosyEdit2: Speech-Editing-Oriented Reinforcement Learning Unlocks Better Zero-Shot TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25930","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":"sha256:3f1ea8ff312eee520d7ecdf618fe3e987f17cb635add2485fe8ea997645e2ddb","target":"record","created_at":"2026-05-26T02:05:18Z","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":"3a30f5bf152b719177f38ed6a247fb0de5a25c958258b1c712777ecab8e3bc45","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-25T15:12:56Z","title_canon_sha256":"fcfdf26a09795c6657403c3c31aab9cab8c9431be2de532af7c8ef9d669472a0"},"schema_version":"1.0","source":{"id":"2605.25930","kind":"arxiv","version":1}},"canonical_sha256":"ebf431d6340c9d0b5a6399359eb8e0263b4e1a5511ea268607647cff1c601da4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebf431d6340c9d0b5a6399359eb8e0263b4e1a5511ea268607647cff1c601da4","first_computed_at":"2026-05-26T02:05:18.879331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:18.879331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7+PoD6IMnmEJqWDZLAxFGs4CZ9r+/Ur+VacQK/IvYWeqr96SwuH5EAQBcZ15lL52Zh0An5hkEg97u01LrYKuAw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:18.880071Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25930","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f1ea8ff312eee520d7ecdf618fe3e987f17cb635add2485fe8ea997645e2ddb","sha256:e658874bc3f8e77e76a394ca6ea9fbd2f883e974a0aefd11b02af2e142e78e0f"],"state_sha256":"7a326a7bbcbb51d1697c536d06630834c4b79d1de9d15abddcea99f569ad2cb5"}