{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IZ345MUDLVLOMEVXB7U4LLPD7B","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":"8d6751cc187f6df31455ca27109ade6eab7631a25b405ada06ea80efa22332fc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-22T03:40:28Z","title_canon_sha256":"f34e3045c015c66132e4fc6f607f7c39352a74063c942d155d94bbedac44e06e"},"schema_version":"1.0","source":{"id":"2606.22811","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22811","created_at":"2026-06-23T02:14:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22811v1","created_at":"2026-06-23T02:14:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22811","created_at":"2026-06-23T02:14:00Z"},{"alias_kind":"pith_short_12","alias_value":"IZ345MUDLVLO","created_at":"2026-06-23T02:14:00Z"},{"alias_kind":"pith_short_16","alias_value":"IZ345MUDLVLOMEVX","created_at":"2026-06-23T02:14:00Z"},{"alias_kind":"pith_short_8","alias_value":"IZ345MUD","created_at":"2026-06-23T02:14:00Z"}],"graph_snapshots":[{"event_id":"sha256:5a5bc7c6d69a3a3bdc4e4191153d30fedfcb7f23b5338c9883e6974d2a311afa","target":"graph","created_at":"2026-06-23T02:14:00Z","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/2606.22811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Classical TTS systems typically rely on rigid input formats and predefined metadata slots, limiting their ability to fulfill flexible user requirements. This paper introduces Bagpiper-TTS, a universal speech synthesis system that deals with diverse natural language user requests. Given a natural language prompt, Bagpiper-TTS first reasons over the users' intent to derive a rich caption, i.e., a comprehensive textual blueprint encompassing both transcription and nuanced metadata. Subsequently, this caption guides the synthesis of the target speech. Our model inherently supports a broad spectrum","authors_text":"Chao-Han Huck Yang, Haoran Wang, Jinchuan Tian, Jin Sakuma, Keita Goto, Shinji Watanabe, Siddhant Arora, Takashi Maekaku, Yusuke Shinohara","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-22T03:40:28Z","title":"Bagpiper-TTS: Natural Language Guided Universal Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22811","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:fee2998dd2161c72003fa3c995c2ffced9748724d9dadf1a9054beabd8b980e5","target":"record","created_at":"2026-06-23T02:14:00Z","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":"8d6751cc187f6df31455ca27109ade6eab7631a25b405ada06ea80efa22332fc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-22T03:40:28Z","title_canon_sha256":"f34e3045c015c66132e4fc6f607f7c39352a74063c942d155d94bbedac44e06e"},"schema_version":"1.0","source":{"id":"2606.22811","kind":"arxiv","version":1}},"canonical_sha256":"4677ceb2835d56e612b70fe9c5ade3f8560e2d2787bcc6889a0383c9e9eb204e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4677ceb2835d56e612b70fe9c5ade3f8560e2d2787bcc6889a0383c9e9eb204e","first_computed_at":"2026-06-23T02:14:00.041252Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:14:00.041252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zKloir13tfq4RjyAVrSZVk20tt9+3sqdKUVj4PAq44IhqRAdMBS0Lkn19DV0MNfzMWlHvnipSyTqJiSsQlMSCg==","signature_status":"signed_v1","signed_at":"2026-06-23T02:14:00.041680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22811","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fee2998dd2161c72003fa3c995c2ffced9748724d9dadf1a9054beabd8b980e5","sha256:5a5bc7c6d69a3a3bdc4e4191153d30fedfcb7f23b5338c9883e6974d2a311afa"],"state_sha256":"bd331152d11ed8aafa64d5832ff24bdc6a864b57bc9204777c95bf0fe0ae5729"}