{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EOU2TFT2WOESQKUOQ42Z4JIB2F","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":"68799af5fc94272da63cfbf140602c944df454970e203be93602b8edc36d2afa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T04:59:33Z","title_canon_sha256":"a894baa9a9a96b8a4b77f7dad82feda97eb3962252e843c18ab0223ea7adc905"},"schema_version":"1.0","source":{"id":"2305.12720","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12720","created_at":"2026-07-05T06:12:13Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12720v1","created_at":"2026-07-05T06:12:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12720","created_at":"2026-07-05T06:12:13Z"},{"alias_kind":"pith_short_12","alias_value":"EOU2TFT2WOES","created_at":"2026-07-05T06:12:13Z"},{"alias_kind":"pith_short_16","alias_value":"EOU2TFT2WOESQKUO","created_at":"2026-07-05T06:12:13Z"},{"alias_kind":"pith_short_8","alias_value":"EOU2TFT2","created_at":"2026-07-05T06:12:13Z"}],"graph_snapshots":[{"event_id":"sha256:41500623e56cda706686e8cec6d51bbb70c922237aab22bf38cf510a00ef29c0","target":"graph","created_at":"2026-07-05T06:12:13Z","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/2305.12720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study constructed a Japanese chat dataset for tuning large language models (LLMs), which consist of about 8.4 million records. Recently, LLMs have been developed and gaining popularity. However, high-performing LLMs are usually mainly for English. There are two ways to support languages other than English by those LLMs: constructing LLMs from scratch or tuning existing models. However, in both ways, datasets are necessary parts. In this study, we focused on supporting Japanese in those LLMs and making a dataset for training or tuning LLMs in Japanese. The dataset we constructed consisted ","authors_text":"Hiroki Sakaji, Masahiro Suzuki, Masanori Hirano","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T04:59:33Z","title":"llm-japanese-dataset v0: Construction of Japanese Chat Dataset for Large Language Models and its Methodology"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12720","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":"sha256:4fef7f2779e1c7378bb098f936b643b8e0cd99173ba150386d0e3a37b1ca3f77","target":"record","created_at":"2026-07-05T06:12:13Z","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":"68799af5fc94272da63cfbf140602c944df454970e203be93602b8edc36d2afa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T04:59:33Z","title_canon_sha256":"a894baa9a9a96b8a4b77f7dad82feda97eb3962252e843c18ab0223ea7adc905"},"schema_version":"1.0","source":{"id":"2305.12720","kind":"arxiv","version":1}},"canonical_sha256":"23a9a9967ab389282a8e87359e2501d16b06c261ab81d2afb4a95d4d5518a8e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23a9a9967ab389282a8e87359e2501d16b06c261ab81d2afb4a95d4d5518a8e9","first_computed_at":"2026-07-05T06:12:13.467552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:13.467552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7brOcfBOyvv6ps9fzggVAgV/O6NzSDJCl9xFNkqmIEtPfYJeAyQCMQTPbz4Js6WTYIAdNfgOUMQ+RiQfhPvLAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:13.467938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12720","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fef7f2779e1c7378bb098f936b643b8e0cd99173ba150386d0e3a37b1ca3f77","sha256:41500623e56cda706686e8cec6d51bbb70c922237aab22bf38cf510a00ef29c0"],"state_sha256":"6b856908817cce0933b24dd9e009718df98d7647852a191aa753a74bbd497708"}