{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QHJ7NOQBMFAVIKD32L6YTQPBSX","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":"87238b22ed9b80c944cc79536d4d23e76ac35c1effd243db50d5cc78f1ef9719","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-11T17:16:52Z","title_canon_sha256":"2e3ae2f532009640a571ce8cf6f5eab78c787d2ca0db1b069aa5e31b5a4ee04c"},"schema_version":"1.0","source":{"id":"2509.09631","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09631","created_at":"2026-06-19T16:12:04Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09631v5","created_at":"2026-06-19T16:12:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09631","created_at":"2026-06-19T16:12:04Z"},{"alias_kind":"pith_short_12","alias_value":"QHJ7NOQBMFAV","created_at":"2026-06-19T16:12:04Z"},{"alias_kind":"pith_short_16","alias_value":"QHJ7NOQBMFAVIKD3","created_at":"2026-06-19T16:12:04Z"},{"alias_kind":"pith_short_8","alias_value":"QHJ7NOQB","created_at":"2026-06-19T16:12:04Z"}],"graph_snapshots":[{"event_id":"sha256:33203cfc30e395c88e0b0259b1d8119ca95c1a934fb9e5a398c4dd8e334b2510","target":"graph","created_at":"2026-06-19T16:12:04Z","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/2509.09631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot text-to-speech (TTS) has made significant progress in replicating unseen voices, yet balancing generation quality and inference efficiency remains challenging. Autoregressive models suffer from high latency, while diffusion-based approaches are constrained by training-time configurations. Moreover, most flow-based methods operate in continuous space, which introduces optimization challenges because continuous token spaces are inherently more complex than discrete ones. To address these limitations, we propose DiFlow-TTS, a novel zero-shot TTS framework based on discrete flow matching","authors_text":"Hieu-Nghia Huynh-Nguyen, Ngoc-Son Nguyen, Thanh V. T. Tran, Truong-Son Hy, Van Nguyen","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-11T17:16:52Z","title":"DiFlow-TTS: Compact and Low-Latency Zero-Shot Text-to-Speech with Discrete Flow Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09631","kind":"arxiv","version":5},"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:fe00915de4907d81b29e4e0d7146a35e8821cb23a5265b668661699815e5d8b5","target":"record","created_at":"2026-06-19T16:12:04Z","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":"87238b22ed9b80c944cc79536d4d23e76ac35c1effd243db50d5cc78f1ef9719","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-11T17:16:52Z","title_canon_sha256":"2e3ae2f532009640a571ce8cf6f5eab78c787d2ca0db1b069aa5e31b5a4ee04c"},"schema_version":"1.0","source":{"id":"2509.09631","kind":"arxiv","version":5}},"canonical_sha256":"81d3f6ba01614154287bd2fd89c1e195f78ee1164cd1a55c9fbe0e63700ecb56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81d3f6ba01614154287bd2fd89c1e195f78ee1164cd1a55c9fbe0e63700ecb56","first_computed_at":"2026-06-19T16:12:04.245501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:04.245501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dSsEqtRPrQXfy0SQExSZtG/WWehuBkkYg0vIqrzVVSutzqzlpPNwis/rel3agg/8RG71hKB49CKl1Tl75NlsCA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:04.245961Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09631","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe00915de4907d81b29e4e0d7146a35e8821cb23a5265b668661699815e5d8b5","sha256:33203cfc30e395c88e0b0259b1d8119ca95c1a934fb9e5a398c4dd8e334b2510"],"state_sha256":"844036ac2b33e445cfb2f05a6d93885a4f05c1d7af942ba2d7198e757a9db106"}