{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WBZT7YJKLARN2DZXBSWX3NUYAH","short_pith_number":"pith:WBZT7YJK","canonical_record":{"source":{"id":"2606.22009","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T12:17:03Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"4e469c8f0c6b3ea1290da391b168b36898c4a036e6eb3bc3a8c97b64d46ab7f3","abstract_canon_sha256":"4b350322981d7790d4d8142f4d2780cde0eb9a715ba4de2f63e268e449eeed80"},"schema_version":"1.0"},"canonical_sha256":"b0733fe12a5822dd0f370cad7db69801c0731ca83b7209d5d402a7a6c6acc6c7","source":{"kind":"arxiv","id":"2606.22009","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22009","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22009v1","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22009","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"pith_short_12","alias_value":"WBZT7YJKLARN","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"pith_short_16","alias_value":"WBZT7YJKLARN2DZX","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"pith_short_8","alias_value":"WBZT7YJK","created_at":"2026-06-23T02:13:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WBZT7YJKLARN2DZXBSWX3NUYAH","target":"record","payload":{"canonical_record":{"source":{"id":"2606.22009","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T12:17:03Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"4e469c8f0c6b3ea1290da391b168b36898c4a036e6eb3bc3a8c97b64d46ab7f3","abstract_canon_sha256":"4b350322981d7790d4d8142f4d2780cde0eb9a715ba4de2f63e268e449eeed80"},"schema_version":"1.0"},"canonical_sha256":"b0733fe12a5822dd0f370cad7db69801c0731ca83b7209d5d402a7a6c6acc6c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:05.484797Z","signature_b64":"dbgRyJOZdOTJQ8R3pXVUfpT21/fe6c81R1WiWz4ID9Bw1kPlGDDQCUfbnCY6liB7oeOHvH9joO3Rbzh44cTADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0733fe12a5822dd0f370cad7db69801c0731ca83b7209d5d402a7a6c6acc6c7","last_reissued_at":"2026-06-23T02:13:05.484410Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:05.484410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.22009","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":"2026-06-23T02:13:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fHniO4qagi/isOV5/oA7gbEUxX9CwXtqPnaI1nIWYcy8IuqYeBf6c3qrlAGvasWVZ54gKy0jAYWrRPp0GrwMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T20:51:27.146529Z"},"content_sha256":"486f4fc23f26ee0b838b8d49c738c13e90b6f0585e62003749da4d24eb29bd60","schema_version":"1.0","event_id":"sha256:486f4fc23f26ee0b838b8d49c738c13e90b6f0585e62003749da4d24eb29bd60"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WBZT7YJKLARN2DZXBSWX3NUYAH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Large Language Models for Grapheme-to-Phoneme Conversion: A Japanese Case Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Tomoki Koriyama","submitted_at":"2026-06-20T12:17:03Z","abstract_excerpt":"Grapheme-to-phoneme (G2P) conversion is essential for controllable and robust text-to-speech, and large language models (LLMs), with broad linguistic knowledge, offer a promising approach. We benchmarked over 30 LLMs on Japanese G2P, comparing them with conventional morphological analyzers on 3000 manually annotated sentences. We evaluated two prompting strategies: a parse mode, where the LLM performs morphological analysis followed by rule-based kana conversion, and a direct mode, where the LLM directly predicts kana readings. The results show that model size, version, and Japanese-specialize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22009","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/2606.22009/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":"2026-06-23T02:13:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YtewBBLL9i+Eb6mDEQDAEymhWZRH8fyUaAo3Au27Y2Wv5Et5MWioOipvLU9iHu2kJ78DxGy+KkyGgWDHMxumAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T20:51:27.146897Z"},"content_sha256":"e4ec021f814c32aeb8d7162cad93cbaa54cc45de093fc9e67fb88787307eb9a8","schema_version":"1.0","event_id":"sha256:e4ec021f814c32aeb8d7162cad93cbaa54cc45de093fc9e67fb88787307eb9a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WBZT7YJKLARN2DZXBSWX3NUYAH/bundle.json","state_url":"https://pith.science/pith/WBZT7YJKLARN2DZXBSWX3NUYAH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WBZT7YJKLARN2DZXBSWX3NUYAH/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":"2026-07-04T20:51:27Z","links":{"resolver":"https://pith.science/pith/WBZT7YJKLARN2DZXBSWX3NUYAH","bundle":"https://pith.science/pith/WBZT7YJKLARN2DZXBSWX3NUYAH/bundle.json","state":"https://pith.science/pith/WBZT7YJKLARN2DZXBSWX3NUYAH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WBZT7YJKLARN2DZXBSWX3NUYAH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WBZT7YJKLARN2DZXBSWX3NUYAH","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":"4b350322981d7790d4d8142f4d2780cde0eb9a715ba4de2f63e268e449eeed80","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T12:17:03Z","title_canon_sha256":"4e469c8f0c6b3ea1290da391b168b36898c4a036e6eb3bc3a8c97b64d46ab7f3"},"schema_version":"1.0","source":{"id":"2606.22009","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22009","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22009v1","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22009","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"pith_short_12","alias_value":"WBZT7YJKLARN","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"pith_short_16","alias_value":"WBZT7YJKLARN2DZX","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"pith_short_8","alias_value":"WBZT7YJK","created_at":"2026-06-23T02:13:05Z"}],"graph_snapshots":[{"event_id":"sha256:e4ec021f814c32aeb8d7162cad93cbaa54cc45de093fc9e67fb88787307eb9a8","target":"graph","created_at":"2026-06-23T02:13:05Z","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/2606.22009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grapheme-to-phoneme (G2P) conversion is essential for controllable and robust text-to-speech, and large language models (LLMs), with broad linguistic knowledge, offer a promising approach. We benchmarked over 30 LLMs on Japanese G2P, comparing them with conventional morphological analyzers on 3000 manually annotated sentences. We evaluated two prompting strategies: a parse mode, where the LLM performs morphological analysis followed by rule-based kana conversion, and a direct mode, where the LLM directly predicts kana readings. The results show that model size, version, and Japanese-specialize","authors_text":"Tomoki Koriyama","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T12:17:03Z","title":"Benchmarking Large Language Models for Grapheme-to-Phoneme Conversion: A Japanese Case Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22009","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":"sha256:486f4fc23f26ee0b838b8d49c738c13e90b6f0585e62003749da4d24eb29bd60","target":"record","created_at":"2026-06-23T02:13:05Z","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":"4b350322981d7790d4d8142f4d2780cde0eb9a715ba4de2f63e268e449eeed80","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T12:17:03Z","title_canon_sha256":"4e469c8f0c6b3ea1290da391b168b36898c4a036e6eb3bc3a8c97b64d46ab7f3"},"schema_version":"1.0","source":{"id":"2606.22009","kind":"arxiv","version":1}},"canonical_sha256":"b0733fe12a5822dd0f370cad7db69801c0731ca83b7209d5d402a7a6c6acc6c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0733fe12a5822dd0f370cad7db69801c0731ca83b7209d5d402a7a6c6acc6c7","first_computed_at":"2026-06-23T02:13:05.484410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:05.484410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dbgRyJOZdOTJQ8R3pXVUfpT21/fe6c81R1WiWz4ID9Bw1kPlGDDQCUfbnCY6liB7oeOHvH9joO3Rbzh44cTADA==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:05.484797Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22009","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:486f4fc23f26ee0b838b8d49c738c13e90b6f0585e62003749da4d24eb29bd60","sha256:e4ec021f814c32aeb8d7162cad93cbaa54cc45de093fc9e67fb88787307eb9a8"],"state_sha256":"37583c4f3f01eb96f0043b2cb4888360de47353ff7d059179f600906c0c8053b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+i/adr9xu741U2bC4giNuefbdsoKKh0J4KNtnTkxMCQVPmA1ZxMKHnB7wJmEtWnOJptY2TwauiDEOE2dWThVBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T20:51:27.148979Z","bundle_sha256":"08985e513393704e05508dd7a4151be46f77b30946e45f6d8ef909229cd41697"}}