{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5TYWZ3S7VYUBO7MDI6EE7IGJ2E","short_pith_number":"pith:5TYWZ3S7","schema_version":"1.0","canonical_sha256":"ecf16cee5fae28177d8347884fa0c9d127dbb9d504a9caa900a9e3b06b0973f5","source":{"kind":"arxiv","id":"2602.00560","version":2},"attestation_state":"computed","paper":{"title":"Edit Content, Preserve Acoustics: Imperceptible Text-Based Speech Editing via Self-Consistency Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiangyan Yi, Jianhua Tao, Le Xu, Tao Wang, Yong Ren, Zhengqi Wen","submitted_at":"2026-01-31T06:56:50Z","abstract_excerpt":"Imperceptible text-based speech editing modifies spoken content through transcript manipulation while preserving acoustic continuity. Prior acoustic-space approaches suffer from content-style entanglement, causing unstable generation and boundary artifacts. We introduce a framework guided by the principle of \"Edit Content, Preserve Acoustics\". Editing is conducted in a stable semantic space, while acoustic realization is handled by a Flow Matching decoder. To ensure perceptual consistency, we propose Self-Consistency Rewards Group Relative Policy Optimization, which leverages a pre-trained Tex"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.00560","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-01-31T06:56:50Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"c59141a72fc9f29452e3d642695a8d2b82a6140029e09a45b1090de4fc4dc3bf","abstract_canon_sha256":"19969456d6dcaa8564a97a89d65f409cff88753e81b452102fb3dc1aa638cbcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:28.204698Z","signature_b64":"GgLAseAolIec2JSajVpQBb3+fajo0Tq5dSlNO/60PijHh94p8eLpUOqAq8zyI2VsUeZ4QQ4OGKuuSDjhITrvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecf16cee5fae28177d8347884fa0c9d127dbb9d504a9caa900a9e3b06b0973f5","last_reissued_at":"2026-06-11T01:09:28.203707Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:28.203707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Edit Content, Preserve Acoustics: Imperceptible Text-Based Speech Editing via Self-Consistency Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiangyan Yi, Jianhua Tao, Le Xu, Tao Wang, Yong Ren, Zhengqi Wen","submitted_at":"2026-01-31T06:56:50Z","abstract_excerpt":"Imperceptible text-based speech editing modifies spoken content through transcript manipulation while preserving acoustic continuity. Prior acoustic-space approaches suffer from content-style entanglement, causing unstable generation and boundary artifacts. We introduce a framework guided by the principle of \"Edit Content, Preserve Acoustics\". Editing is conducted in a stable semantic space, while acoustic realization is handled by a Flow Matching decoder. To ensure perceptual consistency, we propose Self-Consistency Rewards Group Relative Policy Optimization, which leverages a pre-trained Tex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.00560","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.00560/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.00560","created_at":"2026-06-11T01:09:28.203838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.00560v2","created_at":"2026-06-11T01:09:28.203838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.00560","created_at":"2026-06-11T01:09:28.203838+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TYWZ3S7VYUB","created_at":"2026-06-11T01:09:28.203838+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TYWZ3S7VYUBO7MD","created_at":"2026-06-11T01:09:28.203838+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TYWZ3S7","created_at":"2026-06-11T01:09:28.203838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.25930","citing_title":"CosyEdit2: Speech-Editing-Oriented Reinforcement Learning Unlocks Better Zero-Shot TTS","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5TYWZ3S7VYUBO7MDI6EE7IGJ2E","json":"https://pith.science/pith/5TYWZ3S7VYUBO7MDI6EE7IGJ2E.json","graph_json":"https://pith.science/api/pith-number/5TYWZ3S7VYUBO7MDI6EE7IGJ2E/graph.json","events_json":"https://pith.science/api/pith-number/5TYWZ3S7VYUBO7MDI6EE7IGJ2E/events.json","paper":"https://pith.science/paper/5TYWZ3S7"},"agent_actions":{"view_html":"https://pith.science/pith/5TYWZ3S7VYUBO7MDI6EE7IGJ2E","download_json":"https://pith.science/pith/5TYWZ3S7VYUBO7MDI6EE7IGJ2E.json","view_paper":"https://pith.science/paper/5TYWZ3S7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.00560&json=true","fetch_graph":"https://pith.science/api/pith-number/5TYWZ3S7VYUBO7MDI6EE7IGJ2E/graph.json","fetch_events":"https://pith.science/api/pith-number/5TYWZ3S7VYUBO7MDI6EE7IGJ2E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TYWZ3S7VYUBO7MDI6EE7IGJ2E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TYWZ3S7VYUBO7MDI6EE7IGJ2E/action/storage_attestation","attest_author":"https://pith.science/pith/5TYWZ3S7VYUBO7MDI6EE7IGJ2E/action/author_attestation","sign_citation":"https://pith.science/pith/5TYWZ3S7VYUBO7MDI6EE7IGJ2E/action/citation_signature","submit_replication":"https://pith.science/pith/5TYWZ3S7VYUBO7MDI6EE7IGJ2E/action/replication_record"}},"created_at":"2026-06-11T01:09:28.203838+00:00","updated_at":"2026-06-11T01:09:28.203838+00:00"}