{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RTJS76I344RX7V36GNW2TEVQTP","short_pith_number":"pith:RTJS76I3","schema_version":"1.0","canonical_sha256":"8cd32ff91be7237fd77e336da992b09bc613a85f4bd005a9078cab9f93cdd17b","source":{"kind":"arxiv","id":"2403.15484","version":1},"attestation_state":"computed","paper":{"title":"RakutenAI-7B: Extending Large Language Models for Japanese","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aaron Levine, Chenguang Wang, Connie Huang, Eduardo Batista, Ewa Szymanska, Hongyi Ding, Hou Wei Chou, Jean-Fran\\c{c}ois Pessiot, Johanes Effendi, Justin Chiu, Kai Torben Ohlhus, Karan Chopra, Keiji Shinzato, Koji Murakami, Lee Xiong, Lei Chen, Maki Kubota, Maksim Tkachenko, Miroku Lee, Naoki Takahashi, Prathyusha Jwalapuram, Rakuten Group Inc., Ryutaro Tatsushima, Saurabh Jain, Sunil Kumar Yadav, Ting Cai, Wei-Te Chen, Yandi Xia, Yuki Nakayama, Yutaka Higashiyama","submitted_at":"2024-03-21T06:56:07Z","abstract_excerpt":"We introduce RakutenAI-7B, a suite of Japanese-oriented large language models that achieve the best performance on the Japanese LM Harness benchmarks among the open 7B models. Along with the foundation model, we release instruction- and chat-tuned models, RakutenAI-7B-instruct and RakutenAI-7B-chat respectively, under the Apache 2.0 license."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.15484","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-21T06:56:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8050e87e565d7a73264561634ff5e3983a458cba733d44b9eca37a97414c256b","abstract_canon_sha256":"2bcb867c3137d5cd0cdfe509f04be9a2b0311679fb32096a578868be83774d47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:37.830796Z","signature_b64":"dyFYd+Ko/cncmedoXF9UkOoH00UYAG4tYg6S8tUA3ZjdXQXKEOeA+kBWr9IO1G9kO9xs90Xeo5ZTUGlWskwdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cd32ff91be7237fd77e336da992b09bc613a85f4bd005a9078cab9f93cdd17b","last_reissued_at":"2026-07-05T07:59:37.830234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:37.830234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RakutenAI-7B: Extending Large Language Models for Japanese","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aaron Levine, Chenguang Wang, Connie Huang, Eduardo Batista, Ewa Szymanska, Hongyi Ding, Hou Wei Chou, Jean-Fran\\c{c}ois Pessiot, Johanes Effendi, Justin Chiu, Kai Torben Ohlhus, Karan Chopra, Keiji Shinzato, Koji Murakami, Lee Xiong, Lei Chen, Maki Kubota, Maksim Tkachenko, Miroku Lee, Naoki Takahashi, Prathyusha Jwalapuram, Rakuten Group Inc., Ryutaro Tatsushima, Saurabh Jain, Sunil Kumar Yadav, Ting Cai, Wei-Te Chen, Yandi Xia, Yuki Nakayama, Yutaka Higashiyama","submitted_at":"2024-03-21T06:56:07Z","abstract_excerpt":"We introduce RakutenAI-7B, a suite of Japanese-oriented large language models that achieve the best performance on the Japanese LM Harness benchmarks among the open 7B models. Along with the foundation model, we release instruction- and chat-tuned models, RakutenAI-7B-instruct and RakutenAI-7B-chat respectively, under the Apache 2.0 license."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15484","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/2403.15484/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.15484","created_at":"2026-07-05T07:59:37.830304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15484v1","created_at":"2026-07-05T07:59:37.830304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15484","created_at":"2026-07-05T07:59:37.830304+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTJS76I344RX","created_at":"2026-07-05T07:59:37.830304+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTJS76I344RX7V36","created_at":"2026-07-05T07:59:37.830304+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTJS76I3","created_at":"2026-07-05T07:59:37.830304+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02983","citing_title":"A Locally Deployed RAG-Based Academic Advising System for Course Selection","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05662","citing_title":"XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTJS76I344RX7V36GNW2TEVQTP","json":"https://pith.science/pith/RTJS76I344RX7V36GNW2TEVQTP.json","graph_json":"https://pith.science/api/pith-number/RTJS76I344RX7V36GNW2TEVQTP/graph.json","events_json":"https://pith.science/api/pith-number/RTJS76I344RX7V36GNW2TEVQTP/events.json","paper":"https://pith.science/paper/RTJS76I3"},"agent_actions":{"view_html":"https://pith.science/pith/RTJS76I344RX7V36GNW2TEVQTP","download_json":"https://pith.science/pith/RTJS76I344RX7V36GNW2TEVQTP.json","view_paper":"https://pith.science/paper/RTJS76I3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15484&json=true","fetch_graph":"https://pith.science/api/pith-number/RTJS76I344RX7V36GNW2TEVQTP/graph.json","fetch_events":"https://pith.science/api/pith-number/RTJS76I344RX7V36GNW2TEVQTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTJS76I344RX7V36GNW2TEVQTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTJS76I344RX7V36GNW2TEVQTP/action/storage_attestation","attest_author":"https://pith.science/pith/RTJS76I344RX7V36GNW2TEVQTP/action/author_attestation","sign_citation":"https://pith.science/pith/RTJS76I344RX7V36GNW2TEVQTP/action/citation_signature","submit_replication":"https://pith.science/pith/RTJS76I344RX7V36GNW2TEVQTP/action/replication_record"}},"created_at":"2026-07-05T07:59:37.830304+00:00","updated_at":"2026-07-05T07:59:37.830304+00:00"}