{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L7QAYMBMCRNKFDMX5IWMSV57BD","short_pith_number":"pith:L7QAYMBM","schema_version":"1.0","canonical_sha256":"5fe00c302c145aa28d97ea2cc957bf08c9daf636f631c070860ee792853d6f87","source":{"kind":"arxiv","id":"2602.03420","version":2},"attestation_state":"computed","paper":{"title":"CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"Gongping Huang, Hong Jia, James Bailey, Shihong Tan, Siyi Liu, Siyi Wang, Ting Dang","submitted_at":"2026-02-03T11:45:00Z","abstract_excerpt":"Emotional expression in human speech is nuanced and compositional, often involving multiple, sometimes conflicting, affective cues that may diverge from linguistic content. In contrast, most expressive text-to-speech systems enforce a single utterance-level emotion, collapsing affective diversity and suppressing mixed or text-emotion-misaligned expression. While activation steering via latent direction vectors offers a promising solution, it remains unclear whether emotion representations are linearly steerable in TTS, where steering should be applied within hybrid TTS architectures, and how s"},"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":"2602.03420","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-02-03T11:45:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c846b90fb6b14431f1ccea1ee228b7951e1521b16c85fe9bf96813b395f3ec99","abstract_canon_sha256":"7e8258c3b93e29c0a2b9a4b80b68acdaa46313629a6e34dd4f713728d1d4ef37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:34.788878Z","signature_b64":"LRWxBN4Fz6dsYLz58nH7ERwfUBY0aF9mdpa4pPRtn09ooMBV9yf9OHkLsr3cj9QjI5hyOUBvrjZQ1vBo2MJCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fe00c302c145aa28d97ea2cc957bf08c9daf636f631c070860ee792853d6f87","last_reissued_at":"2026-06-19T16:10:34.788392Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:34.788392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"Gongping Huang, Hong Jia, James Bailey, Shihong Tan, Siyi Liu, Siyi Wang, Ting Dang","submitted_at":"2026-02-03T11:45:00Z","abstract_excerpt":"Emotional expression in human speech is nuanced and compositional, often involving multiple, sometimes conflicting, affective cues that may diverge from linguistic content. In contrast, most expressive text-to-speech systems enforce a single utterance-level emotion, collapsing affective diversity and suppressing mixed or text-emotion-misaligned expression. While activation steering via latent direction vectors offers a promising solution, it remains unclear whether emotion representations are linearly steerable in TTS, where steering should be applied within hybrid TTS architectures, and how s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03420","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/2602.03420/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":"2602.03420","created_at":"2026-06-19T16:10:34.788452+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.03420v2","created_at":"2026-06-19T16:10:34.788452+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03420","created_at":"2026-06-19T16:10:34.788452+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7QAYMBMCRNK","created_at":"2026-06-19T16:10:34.788452+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7QAYMBMCRNKFDMX","created_at":"2026-06-19T16:10:34.788452+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7QAYMBM","created_at":"2026-06-19T16:10:34.788452+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7QAYMBMCRNKFDMX5IWMSV57BD","json":"https://pith.science/pith/L7QAYMBMCRNKFDMX5IWMSV57BD.json","graph_json":"https://pith.science/api/pith-number/L7QAYMBMCRNKFDMX5IWMSV57BD/graph.json","events_json":"https://pith.science/api/pith-number/L7QAYMBMCRNKFDMX5IWMSV57BD/events.json","paper":"https://pith.science/paper/L7QAYMBM"},"agent_actions":{"view_html":"https://pith.science/pith/L7QAYMBMCRNKFDMX5IWMSV57BD","download_json":"https://pith.science/pith/L7QAYMBMCRNKFDMX5IWMSV57BD.json","view_paper":"https://pith.science/paper/L7QAYMBM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.03420&json=true","fetch_graph":"https://pith.science/api/pith-number/L7QAYMBMCRNKFDMX5IWMSV57BD/graph.json","fetch_events":"https://pith.science/api/pith-number/L7QAYMBMCRNKFDMX5IWMSV57BD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7QAYMBMCRNKFDMX5IWMSV57BD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7QAYMBMCRNKFDMX5IWMSV57BD/action/storage_attestation","attest_author":"https://pith.science/pith/L7QAYMBMCRNKFDMX5IWMSV57BD/action/author_attestation","sign_citation":"https://pith.science/pith/L7QAYMBMCRNKFDMX5IWMSV57BD/action/citation_signature","submit_replication":"https://pith.science/pith/L7QAYMBMCRNKFDMX5IWMSV57BD/action/replication_record"}},"created_at":"2026-06-19T16:10:34.788452+00:00","updated_at":"2026-06-19T16:10:34.788452+00:00"}