{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W4KZWVU3BFTG2O627PD4U5UYQB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"75d4d24a3cc1c07223df2873eca6b6b0eaa80539c4a3c317059176ba1a856daa","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-08-04T06:50:55Z","title_canon_sha256":"14c5285d978fcbe3fba461194afaa37bc1de06f4d156680358be16d63cea72d3"},"schema_version":"1.0","source":{"id":"2608.03215","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03215","created_at":"2026-08-05T00:46:17Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03215v1","created_at":"2026-08-05T00:46:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03215","created_at":"2026-08-05T00:46:17Z"},{"alias_kind":"pith_short_12","alias_value":"W4KZWVU3BFTG","created_at":"2026-08-05T00:46:17Z"},{"alias_kind":"pith_short_16","alias_value":"W4KZWVU3BFTG2O62","created_at":"2026-08-05T00:46:17Z"},{"alias_kind":"pith_short_8","alias_value":"W4KZWVU3","created_at":"2026-08-05T00:46:17Z"}],"graph_snapshots":[{"event_id":"sha256:bcd86b55c6e822fc4418da9a3b203bbebcf91703b257d979605d5455d0494d83","target":"graph","created_at":"2026-08-05T00:46:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.03215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning for flow-matching text-to-speech is complicated by deterministic ODE sampling: trajectory-level policy-gradient methods typically convert the ODE into an SDE and track per-step likelihood ratios, introducing stochastic perturbations and substantial overhead. We propose GROW, a group-relative advantage-weighted on-policy RL method that acts directly on the standard flow-matching objective. For each prompt, GROW samples a group of on-policy utterances, separately standardizes intelligibility and speaker-similarity rewards within the group, and combines them to reweight flo","authors_text":"Guanrou Yang, Haitao Li, Qian Chen, Qi Chen, Shan Yang, Tian Tan, Wenming Tu, Xie Chen, Yakun Song, Zhikang Niu, Ziyang Ma","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-08-04T06:50:55Z","title":"GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03215","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:749057dddf9561b7095f21cd9aea22f351c717ccf40702b95c240ea10ee08a0d","target":"record","created_at":"2026-08-05T00:46:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"75d4d24a3cc1c07223df2873eca6b6b0eaa80539c4a3c317059176ba1a856daa","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-08-04T06:50:55Z","title_canon_sha256":"14c5285d978fcbe3fba461194afaa37bc1de06f4d156680358be16d63cea72d3"},"schema_version":"1.0","source":{"id":"2608.03215","kind":"arxiv","version":1}},"canonical_sha256":"b7159b569b09666d3bdafbc7ca7698806e827b63735beeb568050e9429110725","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7159b569b09666d3bdafbc7ca7698806e827b63735beeb568050e9429110725","first_computed_at":"2026-08-05T00:46:17.719693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:46:17.719693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/CKh4zlLxAKYgkW4YY87Uv8oQiHAyLOBVJRQtQ59c3KUW40K7FLo15TJ8H2J+EO4s6WQFesJfdrOcYfT1tVwBA==","signature_status":"signed_v1","signed_at":"2026-08-05T00:46:17.722112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03215","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:749057dddf9561b7095f21cd9aea22f351c717ccf40702b95c240ea10ee08a0d","sha256:bcd86b55c6e822fc4418da9a3b203bbebcf91703b257d979605d5455d0494d83"],"state_sha256":"3077c032c1e1344dc4d66a04c1e4ab40d463c089730b7b26d4a89d59495ec7de"}