{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LTTMRGW5KCBVTJVEWHM7PA5XR3","short_pith_number":"pith:LTTMRGW5","schema_version":"1.0","canonical_sha256":"5ce6c89add508359a6a4b1d9f783b78ee357609dc1095e70d10b661b0d900335","source":{"kind":"arxiv","id":"2608.00545","version":1},"attestation_state":"computed","paper":{"title":"Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Jianghao Wu, Xianhao Zhou","submitted_at":"2026-08-01T09:04:17Z","abstract_excerpt":"Natural-language descriptions have become a flexible interface for controlling generated speech. Existing evaluations largely assess whether an output matches a prompt, but prompt matching alone does not reveal whether characteristics outside the intended change remain stable. We examine this distinction through a controlled paired audit of three speech-generation systems: CosyVoice3, VoxCPM2, and Fish-Speech-S2. The evaluation contains 5,940 outputs spanning six reference speakers, ten texts, three random seeds, and eleven conditions. Using acoustic, prosodic, content, and speaker measurement"},"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":"2608.00545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-01T09:04:17Z","cross_cats_sorted":[],"title_canon_sha256":"835c1e17662b579b1d06bf57e7a1d1934b3206f6814f65afdb7e884e0d5801e8","abstract_canon_sha256":"a2c8ecbc0504c5d7de3cb9c6836a9eab12a3dd3fcc4c8bda1519e9a49cb1dc9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:37:24.786705Z","signature_b64":"v3URnLYOPB+9wxiaXZP/xdsONBAjpX5fWlqegM+ihK1un4Te6WfrBH1+y0p81L6BB6AJENPfpiOfjRanZowBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ce6c89add508359a6a4b1d9f783b78ee357609dc1095e70d10b661b0d900335","last_reissued_at":"2026-08-04T00:37:24.785265Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:37:24.785265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Jianghao Wu, Xianhao Zhou","submitted_at":"2026-08-01T09:04:17Z","abstract_excerpt":"Natural-language descriptions have become a flexible interface for controlling generated speech. Existing evaluations largely assess whether an output matches a prompt, but prompt matching alone does not reveal whether characteristics outside the intended change remain stable. We examine this distinction through a controlled paired audit of three speech-generation systems: CosyVoice3, VoxCPM2, and Fish-Speech-S2. The evaluation contains 5,940 outputs spanning six reference speakers, ten texts, three random seeds, and eleven conditions. Using acoustic, prosodic, content, and speaker measurement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00545","kind":"arxiv","version":1},"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/2608.00545/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":"2608.00545","created_at":"2026-08-04T00:37:24.786443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00545v1","created_at":"2026-08-04T00:37:24.786443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00545","created_at":"2026-08-04T00:37:24.786443+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTTMRGW5KCBV","created_at":"2026-08-04T00:37:24.786443+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTTMRGW5KCBVTJVE","created_at":"2026-08-04T00:37:24.786443+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTTMRGW5","created_at":"2026-08-04T00:37:24.786443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.00545","citing_title":"Beyond Prompt Adherence: Auditing Attribute-Level Voice Control in Speech Generation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTTMRGW5KCBVTJVEWHM7PA5XR3","json":"https://pith.science/pith/LTTMRGW5KCBVTJVEWHM7PA5XR3.json","graph_json":"https://pith.science/api/pith-number/LTTMRGW5KCBVTJVEWHM7PA5XR3/graph.json","events_json":"https://pith.science/api/pith-number/LTTMRGW5KCBVTJVEWHM7PA5XR3/events.json","paper":"https://pith.science/paper/LTTMRGW5"},"agent_actions":{"view_html":"https://pith.science/pith/LTTMRGW5KCBVTJVEWHM7PA5XR3","download_json":"https://pith.science/pith/LTTMRGW5KCBVTJVEWHM7PA5XR3.json","view_paper":"https://pith.science/paper/LTTMRGW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00545&json=true","fetch_graph":"https://pith.science/api/pith-number/LTTMRGW5KCBVTJVEWHM7PA5XR3/graph.json","fetch_events":"https://pith.science/api/pith-number/LTTMRGW5KCBVTJVEWHM7PA5XR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTTMRGW5KCBVTJVEWHM7PA5XR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTTMRGW5KCBVTJVEWHM7PA5XR3/action/storage_attestation","attest_author":"https://pith.science/pith/LTTMRGW5KCBVTJVEWHM7PA5XR3/action/author_attestation","sign_citation":"https://pith.science/pith/LTTMRGW5KCBVTJVEWHM7PA5XR3/action/citation_signature","submit_replication":"https://pith.science/pith/LTTMRGW5KCBVTJVEWHM7PA5XR3/action/replication_record"}},"created_at":"2026-08-04T00:37:24.786443+00:00","updated_at":"2026-08-04T00:37:24.786443+00:00"}