{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EIVLGRFNA6TVCTXBL4GI6LEZAS","short_pith_number":"pith:EIVLGRFN","canonical_record":{"source":{"id":"2606.25369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-24T03:57:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"52e77e294e103c6ae4286170c82a575660112916b907ebebed37deda6b860eb6","abstract_canon_sha256":"5ddcff6e1ba6b72247248f0b6ee0825f6f6146c9a1f5d7b40dde4ced9cace956"},"schema_version":"1.0"},"canonical_sha256":"222ab344ad07a7514ee15f0c8f2c9904ac3dd7c232274f0e45c73986068bb1b2","source":{"kind":"arxiv","id":"2606.25369","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25369","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25369v1","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25369","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"EIVLGRFNA6TV","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_16","alias_value":"EIVLGRFNA6TVCTXB","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_8","alias_value":"EIVLGRFN","created_at":"2026-06-25T01:18:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EIVLGRFNA6TVCTXBL4GI6LEZAS","target":"record","payload":{"canonical_record":{"source":{"id":"2606.25369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-24T03:57:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"52e77e294e103c6ae4286170c82a575660112916b907ebebed37deda6b860eb6","abstract_canon_sha256":"5ddcff6e1ba6b72247248f0b6ee0825f6f6146c9a1f5d7b40dde4ced9cace956"},"schema_version":"1.0"},"canonical_sha256":"222ab344ad07a7514ee15f0c8f2c9904ac3dd7c232274f0e45c73986068bb1b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:03.477662Z","signature_b64":"YZKhB+tp2BO/7nP6BRMyFDY6JJ8aPwWTCD+IL6dOW4av61P+sezR1V0fb38RsokI/GJ+DN0N7iu06bbdxfDPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"222ab344ad07a7514ee15f0c8f2c9904ac3dd7c232274f0e45c73986068bb1b2","last_reissued_at":"2026-06-25T01:18:03.477232Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:03.477232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.25369","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-25T01:18:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e2pULeVNItFo+UbnHXpdouEhYkucP2Ew7IErh+agxvt/aHomLIOXx1yNQAVxbGUKA4Winmuijz3opdLyxXZZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T22:42:56.071654Z"},"content_sha256":"00f11d35d6a5fbd883d6701ff5f2da9b3cf744a8b51c473c2436db2c3f8c8f6d","schema_version":"1.0","event_id":"sha256:00f11d35d6a5fbd883d6701ff5f2da9b3cf744a8b51c473c2436db2c3f8c8f6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EIVLGRFNA6TVCTXBL4GI6LEZAS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SD","authors_text":"Haesung Jeon, Hao Shi, Kai Washizaki, Lianbo Liu, Mengjie Zhao, Nao Yoshida, Reo Yoneyama, Roman Koshkin, Shiao Zhu, Yuan Gao, Yui Sudo, Yukiya Hono, Yusuke Fujita","submitted_at":"2026-06-24T03:57:21Z","abstract_excerpt":"While large language model (LLM)-based text-to-speech (TTS) systems have achieved high-quality speech synthesis, most existing systems focus on English and Chinese. Japanese, however, remains under-explored, and its unique linguistic challenges, such as widespread context-dependent kanji polyphony, have yet to be adequately tackled. Here we introduce Sarashina2.2-TTS (https://github.com/sbintuitions/sarashina2.2-tts), a Japanese-centric LLM-TTS system that tackles these challenges through a dual approach: data strategy and evaluation methodology. First, we scale training to approximately 361k "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25369","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.25369/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-25T01:18:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DnIpEWX9CpFhWA0C/0/Nkjol31sRQI1i2PBLr0hegi09QdbvWEV+6sdwBo2topmlMxOdtHwvX9xaYN4k1NgaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T22:42:56.072041Z"},"content_sha256":"7957f572eecde187392509471a97dd2cfe55861f05cdd3625332d2a3250d83ef","schema_version":"1.0","event_id":"sha256:7957f572eecde187392509471a97dd2cfe55861f05cdd3625332d2a3250d83ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EIVLGRFNA6TVCTXBL4GI6LEZAS/bundle.json","state_url":"https://pith.science/pith/EIVLGRFNA6TVCTXBL4GI6LEZAS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EIVLGRFNA6TVCTXBL4GI6LEZAS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-25T22:42:56Z","links":{"resolver":"https://pith.science/pith/EIVLGRFNA6TVCTXBL4GI6LEZAS","bundle":"https://pith.science/pith/EIVLGRFNA6TVCTXBL4GI6LEZAS/bundle.json","state":"https://pith.science/pith/EIVLGRFNA6TVCTXBL4GI6LEZAS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EIVLGRFNA6TVCTXBL4GI6LEZAS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EIVLGRFNA6TVCTXBL4GI6LEZAS","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":"5ddcff6e1ba6b72247248f0b6ee0825f6f6146c9a1f5d7b40dde4ced9cace956","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-24T03:57:21Z","title_canon_sha256":"52e77e294e103c6ae4286170c82a575660112916b907ebebed37deda6b860eb6"},"schema_version":"1.0","source":{"id":"2606.25369","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25369","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25369v1","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25369","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"EIVLGRFNA6TV","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_16","alias_value":"EIVLGRFNA6TVCTXB","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_8","alias_value":"EIVLGRFN","created_at":"2026-06-25T01:18:03Z"}],"graph_snapshots":[{"event_id":"sha256:7957f572eecde187392509471a97dd2cfe55861f05cdd3625332d2a3250d83ef","target":"graph","created_at":"2026-06-25T01:18:03Z","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/2606.25369/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large language model (LLM)-based text-to-speech (TTS) systems have achieved high-quality speech synthesis, most existing systems focus on English and Chinese. Japanese, however, remains under-explored, and its unique linguistic challenges, such as widespread context-dependent kanji polyphony, have yet to be adequately tackled. Here we introduce Sarashina2.2-TTS (https://github.com/sbintuitions/sarashina2.2-tts), a Japanese-centric LLM-TTS system that tackles these challenges through a dual approach: data strategy and evaluation methodology. First, we scale training to approximately 361k ","authors_text":"Haesung Jeon, Hao Shi, Kai Washizaki, Lianbo Liu, Mengjie Zhao, Nao Yoshida, Reo Yoneyama, Roman Koshkin, Shiao Zhu, Yuan Gao, Yui Sudo, Yukiya Hono, Yusuke Fujita","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-24T03:57:21Z","title":"Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25369","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":"sha256:00f11d35d6a5fbd883d6701ff5f2da9b3cf744a8b51c473c2436db2c3f8c8f6d","target":"record","created_at":"2026-06-25T01:18:03Z","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":"5ddcff6e1ba6b72247248f0b6ee0825f6f6146c9a1f5d7b40dde4ced9cace956","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-24T03:57:21Z","title_canon_sha256":"52e77e294e103c6ae4286170c82a575660112916b907ebebed37deda6b860eb6"},"schema_version":"1.0","source":{"id":"2606.25369","kind":"arxiv","version":1}},"canonical_sha256":"222ab344ad07a7514ee15f0c8f2c9904ac3dd7c232274f0e45c73986068bb1b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"222ab344ad07a7514ee15f0c8f2c9904ac3dd7c232274f0e45c73986068bb1b2","first_computed_at":"2026-06-25T01:18:03.477232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:03.477232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YZKhB+tp2BO/7nP6BRMyFDY6JJ8aPwWTCD+IL6dOW4av61P+sezR1V0fb38RsokI/GJ+DN0N7iu06bbdxfDPAQ==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:03.477662Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25369","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00f11d35d6a5fbd883d6701ff5f2da9b3cf744a8b51c473c2436db2c3f8c8f6d","sha256:7957f572eecde187392509471a97dd2cfe55861f05cdd3625332d2a3250d83ef"],"state_sha256":"9ebb4d1e740e9645b02c8a7e3dbb18da58ea4b4da0ca710df887b47a83f8213b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4L0qEfZP2PMxNngtmlai6gb4EVItW8ltMylvs78kndxMCNtix9Zps3yA7heaIgB18yTBKV6rkM4bAaFuz0AsDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T22:42:56.074041Z","bundle_sha256":"727899f16d0f257d089ae410ce680f0a07663194bc73f83051cab2c7ae25f475"}}