{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B5EVPGMZ4JZNN3IJTAPFJDFYRW","short_pith_number":"pith:B5EVPGMZ","schema_version":"1.0","canonical_sha256":"0f49579999e272d6ed09981e548cb88dae444e6d2b9a6a280067e17529f2c72d","source":{"kind":"arxiv","id":"2606.25672","version":1},"attestation_state":"computed","paper":{"title":"Joint Residual Reweighting for Classifier Free Guidance in Flow-Matching Zero-Shot TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chunxiang Jin, Hongjin Song, Runwu Shi, Yujin Wang","submitted_at":"2026-06-24T10:34:27Z","abstract_excerpt":"Classifier-free guidance (CFG) is widely used in flow-matching-based zero-shot text-to-speech (TTS), where generation is typically controlled by two conditions: the target text and a prompt speech signal. Standard CFG strengthens these conditions jointly, while recent branch-selective guidance methods attempt to enhance text or speaker conditioning separately, often leading to a trade-off between text correctness and speaker similarity. In this paper, we revisit the CFG under independently masked text and speech-prompt conditions, and decompose the guidance field into text, speaker, and joint "},"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":"2606.25672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-24T10:34:27Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"1c2110014ebffc498f9a28373a38d97f61b3200b8272600de15e810b2984c52c","abstract_canon_sha256":"b11962d0fd3f538899bae1ae7903e682111c2c3fce4f4de2c1b7791e88a71203"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:12.421199Z","signature_b64":"P0rSGOb7yWpr7NIfAR0AoglkNYUOpMrcfws4hckDnKQh0dvcxT1uJRsZ91axPJ+/o7ObELxSHJKlOkLGCuMhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f49579999e272d6ed09981e548cb88dae444e6d2b9a6a280067e17529f2c72d","last_reissued_at":"2026-06-25T01:18:12.420801Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:12.420801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Residual Reweighting for Classifier Free Guidance in Flow-Matching Zero-Shot TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chunxiang Jin, Hongjin Song, Runwu Shi, Yujin Wang","submitted_at":"2026-06-24T10:34:27Z","abstract_excerpt":"Classifier-free guidance (CFG) is widely used in flow-matching-based zero-shot text-to-speech (TTS), where generation is typically controlled by two conditions: the target text and a prompt speech signal. Standard CFG strengthens these conditions jointly, while recent branch-selective guidance methods attempt to enhance text or speaker conditioning separately, often leading to a trade-off between text correctness and speaker similarity. In this paper, we revisit the CFG under independently masked text and speech-prompt conditions, and decompose the guidance field into text, speaker, and joint "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25672","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/2606.25672/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":"2606.25672","created_at":"2026-06-25T01:18:12.420866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25672v1","created_at":"2026-06-25T01:18:12.420866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25672","created_at":"2026-06-25T01:18:12.420866+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5EVPGMZ4JZN","created_at":"2026-06-25T01:18:12.420866+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5EVPGMZ4JZNN3IJ","created_at":"2026-06-25T01:18:12.420866+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5EVPGMZ","created_at":"2026-06-25T01:18:12.420866+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/B5EVPGMZ4JZNN3IJTAPFJDFYRW","json":"https://pith.science/pith/B5EVPGMZ4JZNN3IJTAPFJDFYRW.json","graph_json":"https://pith.science/api/pith-number/B5EVPGMZ4JZNN3IJTAPFJDFYRW/graph.json","events_json":"https://pith.science/api/pith-number/B5EVPGMZ4JZNN3IJTAPFJDFYRW/events.json","paper":"https://pith.science/paper/B5EVPGMZ"},"agent_actions":{"view_html":"https://pith.science/pith/B5EVPGMZ4JZNN3IJTAPFJDFYRW","download_json":"https://pith.science/pith/B5EVPGMZ4JZNN3IJTAPFJDFYRW.json","view_paper":"https://pith.science/paper/B5EVPGMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25672&json=true","fetch_graph":"https://pith.science/api/pith-number/B5EVPGMZ4JZNN3IJTAPFJDFYRW/graph.json","fetch_events":"https://pith.science/api/pith-number/B5EVPGMZ4JZNN3IJTAPFJDFYRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5EVPGMZ4JZNN3IJTAPFJDFYRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5EVPGMZ4JZNN3IJTAPFJDFYRW/action/storage_attestation","attest_author":"https://pith.science/pith/B5EVPGMZ4JZNN3IJTAPFJDFYRW/action/author_attestation","sign_citation":"https://pith.science/pith/B5EVPGMZ4JZNN3IJTAPFJDFYRW/action/citation_signature","submit_replication":"https://pith.science/pith/B5EVPGMZ4JZNN3IJTAPFJDFYRW/action/replication_record"}},"created_at":"2026-06-25T01:18:12.420866+00:00","updated_at":"2026-06-25T01:18:12.420866+00:00"}