{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6CW7IOH5NZNFHNWEEJQP2RAPPT","short_pith_number":"pith:6CW7IOH5","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"},"canonical_sha256":"f0adf438fd6e5a53b6c42260fd440f7cdc286f13e05b88c653686d7a422776ef","source":{"kind":"arxiv","id":"2403.03690","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03690","created_at":"2026-07-05T07:52:51Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03690v1","created_at":"2026-07-05T07:52:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03690","created_at":"2026-07-05T07:52:51Z"},{"alias_kind":"pith_short_12","alias_value":"6CW7IOH5NZNF","created_at":"2026-07-05T07:52:51Z"},{"alias_kind":"pith_short_16","alias_value":"6CW7IOH5NZNFHNWE","created_at":"2026-07-05T07:52:51Z"},{"alias_kind":"pith_short_8","alias_value":"6CW7IOH5","created_at":"2026-07-05T07:52:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6CW7IOH5NZNFHNWEEJQP2RAPPT","target":"record","payload":{"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"},"canonical_sha256":"f0adf438fd6e5a53b6c42260fd440f7cdc286f13e05b88c653686d7a422776ef","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"},"source_kind":"arxiv","source_id":"2403.03690","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":"2026-07-05T07:52:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pM/98wvQN+gWmhbjJGZAzyDGlQtnumwhSiiBAX3GwTIVYYglWuoRPzD8WFRulx/vbhf0Z6mXkBe+pLI5mLvHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T02:21:13.602193Z"},"content_sha256":"72d9d3f8a155a3b10415b401aa85f9c8bf412e45ec24e6a4023580e5f75d72e1","schema_version":"1.0","event_id":"sha256:72d9d3f8a155a3b10415b401aa85f9c8bf412e45ec24e6a4023580e5f75d72e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6CW7IOH5NZNFHNWEEJQP2RAPPT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:52:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MgMcZFGuNE1S4VsdAYz4B00NcjnS89phGqkOOiZKnGen5CLW2LnXfCwgM6l6pCa/5bMdPmrA6SzPKP5gCMhzAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T02:21:13.603261Z"},"content_sha256":"18279a75b36f691a7ef3583410429f3def70a8bc92c8e70b1cf9529b7b510559","schema_version":"1.0","event_id":"sha256:18279a75b36f691a7ef3583410429f3def70a8bc92c8e70b1cf9529b7b510559"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT/bundle.json","state_url":"https://pith.science/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT/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":"2026-08-24T02:21:13Z","links":{"resolver":"https://pith.science/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT","bundle":"https://pith.science/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT/bundle.json","state":"https://pith.science/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6CW7IOH5NZNFHNWEEJQP2RAPPT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6CW7IOH5NZNFHNWEEJQP2RAPPT","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":"817fc3f6b420e6417fa7a031a1888a85a6d80bc430fb3ff3403c2349f1a4a930","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T13:17:07Z","title_canon_sha256":"6dda8350d65ab1a439e1fb6fffba42d8844a9b0016eb90d65f731727a0c14215"},"schema_version":"1.0","source":{"id":"2403.03690","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03690","created_at":"2026-07-05T07:52:51Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03690v1","created_at":"2026-07-05T07:52:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03690","created_at":"2026-07-05T07:52:51Z"},{"alias_kind":"pith_short_12","alias_value":"6CW7IOH5NZNF","created_at":"2026-07-05T07:52:51Z"},{"alias_kind":"pith_short_16","alias_value":"6CW7IOH5NZNFHNWE","created_at":"2026-07-05T07:52:51Z"},{"alias_kind":"pith_short_8","alias_value":"6CW7IOH5","created_at":"2026-07-05T07:52:51Z"}],"graph_snapshots":[{"event_id":"sha256:18279a75b36f691a7ef3583410429f3def70a8bc92c8e70b1cf9529b7b510559","target":"graph","created_at":"2026-07-05T07:52:51Z","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/2403.03690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Chenhui Chu, Fei Cheng, Nobuhiro Ueda, Sadao Kurohashi, Sakiko Yahata, Yikun Sun, Zhen Wan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T13:17:07Z","title":"Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03690","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":"sha256:72d9d3f8a155a3b10415b401aa85f9c8bf412e45ec24e6a4023580e5f75d72e1","target":"record","created_at":"2026-07-05T07:52:51Z","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":"817fc3f6b420e6417fa7a031a1888a85a6d80bc430fb3ff3403c2349f1a4a930","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T13:17:07Z","title_canon_sha256":"6dda8350d65ab1a439e1fb6fffba42d8844a9b0016eb90d65f731727a0c14215"},"schema_version":"1.0","source":{"id":"2403.03690","kind":"arxiv","version":1}},"canonical_sha256":"f0adf438fd6e5a53b6c42260fd440f7cdc286f13e05b88c653686d7a422776ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0adf438fd6e5a53b6c42260fd440f7cdc286f13e05b88c653686d7a422776ef","first_computed_at":"2026-07-05T07:52:51.763691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:51.763691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F4jve2+JU1rQNE3b8HOwIUfelmoz5oIkUxoTHQ8yt0aEyR1j6fCv8d5NtLWe2Pj3nfqN/3+3uOiugToym36tDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:51.764077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03690","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72d9d3f8a155a3b10415b401aa85f9c8bf412e45ec24e6a4023580e5f75d72e1","sha256:18279a75b36f691a7ef3583410429f3def70a8bc92c8e70b1cf9529b7b510559"],"state_sha256":"12c05de7a9c68b6b00dd5a91ea9c5e809577ee4eb3f15de32a762d18c1ec74cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cp2y+SjEZGXhgS+En49JpH7G+t/BKZnqrJ1D9KG8brAVGIRjIPgzRQcz7I8Zj8XX9uCD+yhEinXjC7AvuG2xBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T02:21:13.608640Z","bundle_sha256":"11abb5470d7fc29750f92a344609422af45178a89e47955d47f0709e685384f5"}}