{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YTD2WVRWMBLNN2WHVZ65TKK6MW","short_pith_number":"pith:YTD2WVRW","schema_version":"1.0","canonical_sha256":"c4c7ab56366056d6eac7ae7dd9a95e6583135c5c787737e9740c64cbd673db1d","source":{"kind":"arxiv","id":"2506.00832","version":1},"attestation_state":"computed","paper":{"title":"Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Artyom Stitsyuk, Gunu Jho, Inchul Hwang, Jaesik Choi, Kyowoon Lee","submitted_at":"2025-06-01T04:33:37Z","abstract_excerpt":"Recent advances in Text-to-Speech (TTS) have significantly improved speech naturalness, increasing the demand for precise prosody control and mispronunciation correction. Existing approaches for prosody manipulation often depend on specialized modules or additional training, limiting their capacity for post-hoc adjustments. Similarly, traditional mispronunciation correction relies on grapheme-to-phoneme dictionaries, making it less practical in low-resource settings. We introduce Counterfactual Activation Editing, a model-agnostic method that manipulates internal representations in a pre-train"},"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":"2506.00832","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-01T04:33:37Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"abff8de36c4187a58a123804db6c51e09604903bfd8f849ac58622a83c290356","abstract_canon_sha256":"130900cdadf10b2dad4ae124d7f548de3e29acdd4fc7f283228d005c28d9473b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:41.280041Z","signature_b64":"n0JhxI6EKoKHEG9sVkCwJ984C+oNFbsvOgN8/FH2S0ZWdoWlXfTHrU2F5qNzgnD1k9gWQO0bVUXMmX1/fAgcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4c7ab56366056d6eac7ae7dd9a95e6583135c5c787737e9740c64cbd673db1d","last_reissued_at":"2026-07-05T11:13:41.279483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:41.279483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Artyom Stitsyuk, Gunu Jho, Inchul Hwang, Jaesik Choi, Kyowoon Lee","submitted_at":"2025-06-01T04:33:37Z","abstract_excerpt":"Recent advances in Text-to-Speech (TTS) have significantly improved speech naturalness, increasing the demand for precise prosody control and mispronunciation correction. Existing approaches for prosody manipulation often depend on specialized modules or additional training, limiting their capacity for post-hoc adjustments. Similarly, traditional mispronunciation correction relies on grapheme-to-phoneme dictionaries, making it less practical in low-resource settings. We introduce Counterfactual Activation Editing, a model-agnostic method that manipulates internal representations in a pre-train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00832","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/2506.00832/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":"2506.00832","created_at":"2026-07-05T11:13:41.279563+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00832v1","created_at":"2026-07-05T11:13:41.279563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00832","created_at":"2026-07-05T11:13:41.279563+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTD2WVRWMBLN","created_at":"2026-07-05T11:13:41.279563+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTD2WVRWMBLNN2WH","created_at":"2026-07-05T11:13:41.279563+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTD2WVRW","created_at":"2026-07-05T11:13:41.279563+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00832","citing_title":"Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YTD2WVRWMBLNN2WHVZ65TKK6MW","json":"https://pith.science/pith/YTD2WVRWMBLNN2WHVZ65TKK6MW.json","graph_json":"https://pith.science/api/pith-number/YTD2WVRWMBLNN2WHVZ65TKK6MW/graph.json","events_json":"https://pith.science/api/pith-number/YTD2WVRWMBLNN2WHVZ65TKK6MW/events.json","paper":"https://pith.science/paper/YTD2WVRW"},"agent_actions":{"view_html":"https://pith.science/pith/YTD2WVRWMBLNN2WHVZ65TKK6MW","download_json":"https://pith.science/pith/YTD2WVRWMBLNN2WHVZ65TKK6MW.json","view_paper":"https://pith.science/paper/YTD2WVRW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00832&json=true","fetch_graph":"https://pith.science/api/pith-number/YTD2WVRWMBLNN2WHVZ65TKK6MW/graph.json","fetch_events":"https://pith.science/api/pith-number/YTD2WVRWMBLNN2WHVZ65TKK6MW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTD2WVRWMBLNN2WHVZ65TKK6MW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTD2WVRWMBLNN2WHVZ65TKK6MW/action/storage_attestation","attest_author":"https://pith.science/pith/YTD2WVRWMBLNN2WHVZ65TKK6MW/action/author_attestation","sign_citation":"https://pith.science/pith/YTD2WVRWMBLNN2WHVZ65TKK6MW/action/citation_signature","submit_replication":"https://pith.science/pith/YTD2WVRWMBLNN2WHVZ65TKK6MW/action/replication_record"}},"created_at":"2026-07-05T11:13:41.279563+00:00","updated_at":"2026-07-05T11:13:41.279563+00:00"}