{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6CW7IOH5NZNFHNWEEJQP2RAPPT","short_pith_number":"pith:6CW7IOH5","schema_version":"1.0","canonical_sha256":"f0adf438fd6e5a53b6c42260fd440f7cdc286f13e05b88c653686d7a422776ef","source":{"kind":"arxiv","id":"2403.03690","version":1},"attestation_state":"computed","paper":{"title":"Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenhui Chu, Fei Cheng, Nobuhiro Ueda, Sadao Kurohashi, Sakiko Yahata, Yikun Sun, Zhen Wan","submitted_at":"2024-03-06T13:17:07Z","abstract_excerpt":"The creation of instruction data and evaluation benchmarks for serving Large language models often involves enormous human annotation. This issue becomes particularly pronounced when rapidly developing such resources for a non-English language like Japanese. Instead of following the popular practice of directly translating existing English resources into Japanese (e.g., Japanese-Alpaca), we propose an efficient self-instruct method based on GPT-4. We first translate a small amount of English instructions into Japanese and post-edit them to obtain native-level quality. GPT-4 then utilizes them "},"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":"2403.03690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T13:17:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6dda8350d65ab1a439e1fb6fffba42d8844a9b0016eb90d65f731727a0c14215","abstract_canon_sha256":"817fc3f6b420e6417fa7a031a1888a85a6d80bc430fb3ff3403c2349f1a4a930"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:51.764077Z","signature_b64":"F4jve2+JU1rQNE3b8HOwIUfelmoz5oIkUxoTHQ8yt0aEyR1j6fCv8d5NtLWe2Pj3nfqN/3+3uOiugToym36tDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0adf438fd6e5a53b6c42260fd440f7cdc286f13e05b88c653686d7a422776ef","last_reissued_at":"2026-07-05T07:52:51.763691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:51.763691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenhui Chu, Fei Cheng, Nobuhiro Ueda, Sadao Kurohashi, Sakiko Yahata, Yikun Sun, Zhen Wan","submitted_at":"2024-03-06T13:17:07Z","abstract_excerpt":"The creation of instruction data and evaluation benchmarks for serving Large language models often involves enormous human annotation. This issue becomes particularly pronounced when rapidly developing such resources for a non-English language like Japanese. Instead of following the popular practice of directly translating existing English resources into Japanese (e.g., Japanese-Alpaca), we propose an efficient self-instruct method based on GPT-4. We first translate a small amount of English instructions into Japanese and post-edit them to obtain native-level quality. GPT-4 then utilizes them "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03690","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/2403.03690/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":"2403.03690","created_at":"2026-07-05T07:52:51.763753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03690v1","created_at":"2026-07-05T07:52:51.763753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03690","created_at":"2026-07-05T07:52:51.763753+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CW7IOH5NZNF","created_at":"2026-07-05T07:52:51.763753+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CW7IOH5NZNFHNWE","created_at":"2026-07-05T07:52:51.763753+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CW7IOH5","created_at":"2026-07-05T07:52:51.763753+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT","json":"https://pith.science/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT.json","graph_json":"https://pith.science/api/pith-number/6CW7IOH5NZNFHNWEEJQP2RAPPT/graph.json","events_json":"https://pith.science/api/pith-number/6CW7IOH5NZNFHNWEEJQP2RAPPT/events.json","paper":"https://pith.science/paper/6CW7IOH5"},"agent_actions":{"view_html":"https://pith.science/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT","download_json":"https://pith.science/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT.json","view_paper":"https://pith.science/paper/6CW7IOH5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03690&json=true","fetch_graph":"https://pith.science/api/pith-number/6CW7IOH5NZNFHNWEEJQP2RAPPT/graph.json","fetch_events":"https://pith.science/api/pith-number/6CW7IOH5NZNFHNWEEJQP2RAPPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT/action/storage_attestation","attest_author":"https://pith.science/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT/action/author_attestation","sign_citation":"https://pith.science/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT/action/citation_signature","submit_replication":"https://pith.science/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT/action/replication_record"}},"created_at":"2026-07-05T07:52:51.763753+00:00","updated_at":"2026-07-05T07:52:51.763753+00:00"}