{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:X4YKOF3MFEN43AL2D2WZWOLNUT","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":"080a361fefef4cb17973528734d9a117e70a6bd73ed5cd54c7fed83a3947585c","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-16T20:58:26Z","title_canon_sha256":"395b6e6a5fb7505fea6d82fde7b188f95b69af5edcbaf531f033b479e03bf2f6"},"schema_version":"1.0","source":{"id":"2606.18485","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18485","created_at":"2026-06-19T16:12:22Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18485v1","created_at":"2026-06-19T16:12:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18485","created_at":"2026-06-19T16:12:22Z"},{"alias_kind":"pith_short_12","alias_value":"X4YKOF3MFEN4","created_at":"2026-06-19T16:12:22Z"},{"alias_kind":"pith_short_16","alias_value":"X4YKOF3MFEN43AL2","created_at":"2026-06-19T16:12:22Z"},{"alias_kind":"pith_short_8","alias_value":"X4YKOF3M","created_at":"2026-06-19T16:12:22Z"}],"graph_snapshots":[{"event_id":"sha256:bd0a6f36a462dc6a8f2491b07b14213519a17ece8fe3a9840ef9865dbacec78f","target":"graph","created_at":"2026-06-19T16:12:22Z","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/2606.18485/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural Text-to-Speech (TTS) systems achieve remarkable quality on short utterances but long-form speech generation shows prosodic drift, speaker inconsistencies and sentence boundary artifacts. Existing approaches either compress sequences, increase context length or naively concatenate independently synthesized chunks. We present an inference-time approach called MagpieTTS-LF that enables MagpieTTS to produce coherent long-form speech without model retraining. Our method introduces three key innovations: (1) soft attention priors to guide monotonic alignment while preserving past and future c","authors_text":"Jason Li, Paarth Neekhara, Roy Fejgin, Ryan Langman, Shehzeen Hussain, Subhankar Ghosh, Xuesong Yang","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-16T20:58:26Z","title":"MagpieTTS-LF: Inference-Time Long-Form Speech Generation Without Training on Long-Form data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18485","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":"sha256:1404aa7391e66e7c82d1c55324cbb6ac49bd62a7dd40ef9734d413c74daedd83","target":"record","created_at":"2026-06-19T16:12:22Z","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":"080a361fefef4cb17973528734d9a117e70a6bd73ed5cd54c7fed83a3947585c","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-16T20:58:26Z","title_canon_sha256":"395b6e6a5fb7505fea6d82fde7b188f95b69af5edcbaf531f033b479e03bf2f6"},"schema_version":"1.0","source":{"id":"2606.18485","kind":"arxiv","version":1}},"canonical_sha256":"bf30a7176c291bcd817a1ead9b396da4d22c7901b2bdea9ef48c51a3975b8714","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf30a7176c291bcd817a1ead9b396da4d22c7901b2bdea9ef48c51a3975b8714","first_computed_at":"2026-06-19T16:12:22.146612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:22.146612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zsi4nDJkyT/cho/mjP0KGIOkn0NhtUDZMVTYXyoqb+KLJHrPm4rLYgay11Amw/wui2q2kiYvD5KJ7o8+Z9XkCg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:22.146968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18485","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1404aa7391e66e7c82d1c55324cbb6ac49bd62a7dd40ef9734d413c74daedd83","sha256:bd0a6f36a462dc6a8f2491b07b14213519a17ece8fe3a9840ef9865dbacec78f"],"state_sha256":"6aa07f059fba43ae370a4aad7169536d4400ebdb462526eabf3574b64b9ade8a"}