{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RPHBKFSUHP5CEEOH3II6HZBWCH","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":"4b65e438753295611fd03d17708200ec44e4304dadd470d20fc525fa39f322ef","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-27T00:02:45Z","title_canon_sha256":"82c14b99606de47ff03e5d48f6663b4110732e1362c337e0d1064fbf2b981e44"},"schema_version":"1.0","source":{"id":"2404.17733","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17733","created_at":"2026-07-05T08:12:53Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17733v1","created_at":"2026-07-05T08:12:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17733","created_at":"2026-07-05T08:12:53Z"},{"alias_kind":"pith_short_12","alias_value":"RPHBKFSUHP5C","created_at":"2026-07-05T08:12:53Z"},{"alias_kind":"pith_short_16","alias_value":"RPHBKFSUHP5CEEOH","created_at":"2026-07-05T08:12:53Z"},{"alias_kind":"pith_short_8","alias_value":"RPHBKFSU","created_at":"2026-07-05T08:12:53Z"}],"graph_snapshots":[{"event_id":"sha256:3a650861dccd496d6da7a72da63dc1b75346533addf72bd706b31034c128454d","target":"graph","created_at":"2026-07-05T08:12:53Z","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/2404.17733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open Japanese large language models (LLMs) have been trained on the Japanese portions of corpora such as CC-100, mC4, and OSCAR. However, these corpora were not created for the quality of Japanese texts. This study builds a large Japanese web corpus by extracting and refining text from the Common Crawl archive (21 snapshots of approximately 63.4 billion pages crawled between 2020 and 2023). This corpus consists of approximately 312.1 billion characters (approximately 173 million pages), which is the largest of all available training corpora for Japanese LLMs, surpassing CC-100 (approximately 2","authors_text":"Hirai Shota, Hiroki Iida, Kakeru Hattori, Kazuki Fujii, Masanari Ohi, Mengsay Loem, Naoaki Okazaki, Rio Yokota, Sakae Mizuki, Taishi Nakamura","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-27T00:02:45Z","title":"Building a Large Japanese Web Corpus for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17733","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":"sha256:133b1424d1448ed44ee91e14d7434b0e167b74d423c2e78188062d2676cac3c3","target":"record","created_at":"2026-07-05T08:12:53Z","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":"4b65e438753295611fd03d17708200ec44e4304dadd470d20fc525fa39f322ef","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-27T00:02:45Z","title_canon_sha256":"82c14b99606de47ff03e5d48f6663b4110732e1362c337e0d1064fbf2b981e44"},"schema_version":"1.0","source":{"id":"2404.17733","kind":"arxiv","version":1}},"canonical_sha256":"8bce1516543bfa2211c7da11e3e43611e106726853a1e7cc0a0ad36b791ca9dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bce1516543bfa2211c7da11e3e43611e106726853a1e7cc0a0ad36b791ca9dc","first_computed_at":"2026-07-05T08:12:53.524804Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:53.524804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OLkykRxgxpLfUOAyI5MgrAnazcc0/Rt+S7Atg9Afbn9R+pGvKpkW1adHg63nt7qZofmJNJsoHV3HwBHca9QVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:53.525273Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.17733","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:133b1424d1448ed44ee91e14d7434b0e167b74d423c2e78188062d2676cac3c3","sha256:3a650861dccd496d6da7a72da63dc1b75346533addf72bd706b31034c128454d"],"state_sha256":"512dbc025b07861e5785cbb18a3e6d68d0549c1e4ecacc513f3a82c453868d1f"}