{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZJYIJ3HRMJST5JZPMG2AVSUHXS","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":"67a2a88b42d3d61a71df1130a913fd259e3364050750b0c41cd280e59a694396","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-21T07:22:28Z","title_canon_sha256":"92baeea7bb64cfef676b459a2d94dfa881d1a7d7f147e86a6ccbf9c3a265df3d"},"schema_version":"1.0","source":{"id":"2605.22083","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22083","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22083v1","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22083","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"ZJYIJ3HRMJST","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"ZJYIJ3HRMJST5JZP","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"ZJYIJ3HR","created_at":"2026-05-22T01:04:24Z"}],"graph_snapshots":[{"event_id":"sha256:3abdc462b95483b9039825096f2f14767804f69b7572d7224ae42beeb61890f7","target":"graph","created_at":"2026-05-22T01:04:24Z","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/2605.22083/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issues, particularly skip and repeat errors from imperfect alignment. We propose RobustSpeechFlow, a training strategy that improves alignment robustness by extending contrastive flow matching with length-preserving repeat and skip latent augmentations. Requiring no external aligners or preference data, our method directly penalizes realistic failure modes and readily integrates into existing pipelines. On Seed-TTS-eval, it reduces the word error rat","authors_text":"Frederik Bous, Hyeongju Kim, Jinhyeok Yang, Joon Byun, Juheon Lee, Yechan Yu","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-21T07:22:28Z","title":"RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22083","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:b81e2af20a16c17112b6316cd7f6be2982381dac4c7734c0cd52ef08215900c7","target":"record","created_at":"2026-05-22T01:04:24Z","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":"67a2a88b42d3d61a71df1130a913fd259e3364050750b0c41cd280e59a694396","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-21T07:22:28Z","title_canon_sha256":"92baeea7bb64cfef676b459a2d94dfa881d1a7d7f147e86a6ccbf9c3a265df3d"},"schema_version":"1.0","source":{"id":"2605.22083","kind":"arxiv","version":1}},"canonical_sha256":"ca7084ecf162653ea72f61b40aca87bc8007b08e6d370464e9171e345cf3234c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca7084ecf162653ea72f61b40aca87bc8007b08e6d370464e9171e345cf3234c","first_computed_at":"2026-05-22T01:04:24.544494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:24.544494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l1iiLLP+D6rY36HdqRk+kp4yU7kzfPo4FIjIyw1WuedbJ2ogXPJaUw3nGNAJVS/t+pvtwKCsyqkvkKcTry5NCw==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:24.545450Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22083","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b81e2af20a16c17112b6316cd7f6be2982381dac4c7734c0cd52ef08215900c7","sha256:3abdc462b95483b9039825096f2f14767804f69b7572d7224ae42beeb61890f7"],"state_sha256":"7eb30792a374d74da778a89a162ca63ae21fa1061202dbf80cabf1e52ba3a26e"}