{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ESGZ4K6WYU7JYGZFADGVBOYEBF","short_pith_number":"pith:ESGZ4K6W","canonical_record":{"source":{"id":"2403.18058","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T19:24:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e1b78218a117376b2105987ddbdf34d141f0c01bda5c1b88bc73638152353004","abstract_canon_sha256":"d6938066e3b00a6cffbdb5088ee70b1915507615f2bb82a90d75445ec8f1fbf1"},"schema_version":"1.0"},"canonical_sha256":"248d9e2bd6c53e9c1b2500cd50bb0409720133e4fe657162755f30cbd196b17a","source":{"kind":"arxiv","id":"2403.18058","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.18058","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.18058v2","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18058","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"pith_short_12","alias_value":"ESGZ4K6WYU7J","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"pith_short_16","alias_value":"ESGZ4K6WYU7JYGZF","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"pith_short_8","alias_value":"ESGZ4K6W","created_at":"2026-07-05T09:30:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ESGZ4K6WYU7JYGZFADGVBOYEBF","target":"record","payload":{"canonical_record":{"source":{"id":"2403.18058","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T19:24:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e1b78218a117376b2105987ddbdf34d141f0c01bda5c1b88bc73638152353004","abstract_canon_sha256":"d6938066e3b00a6cffbdb5088ee70b1915507615f2bb82a90d75445ec8f1fbf1"},"schema_version":"1.0"},"canonical_sha256":"248d9e2bd6c53e9c1b2500cd50bb0409720133e4fe657162755f30cbd196b17a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:11.817719Z","signature_b64":"aIDPZ+XBjb1+tr9dMyLH6uAx8gf0nSLvhWBp8UYMevaOAXrKyGH0AwRG2GRV6SOGduFjSZqGC+72Jn0pjOw4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"248d9e2bd6c53e9c1b2500cd50bb0409720133e4fe657162755f30cbd196b17a","last_reissued_at":"2026-07-05T09:30:11.817243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:11.817243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.18058","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m3Q9cdeEZuMGYc1wzI5K68uXXa/hpImQKJOxP+oZprWsZXwVBV6y/XuhhPE5VTaZwDhCBQGiK/lxGswxy3KbAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:28:54.395713Z"},"content_sha256":"cb81e418117b771beb0b4f9d2776097f9ae6d2937e8269f21ee0b3362accb39b","schema_version":"1.0","event_id":"sha256:cb81e418117b771beb0b4f9d2776097f9ae6d2937e8269f21ee0b3362accb39b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ESGZ4K6WYU7JYGZFADGVBOYEBF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenghua Lin, Feiteng Fang, Ge Zhang, Haihong Wu, Hongquan Lin, Jiajun Zhang, Jie Fu, Junting Zhou, Mingshan Chang, Min Yang, Nuo Ma, Ruibin Yuan, Shiwen Ni, Tianyu Zheng, Wenhao Huang, Xincheng Zhang, Xinrun Du, Yiming Liang, Yonggang Jin, Yuelin Bai, Zekun Wang, Ziqiang Liu","submitted_at":"2024-03-26T19:24:18Z","abstract_excerpt":"Remarkable progress on English instruction tuning has facilitated the efficacy and reliability of large language models (LLMs). However, there remains a noticeable gap in instruction tuning for Chinese, where the complex linguistic features pose significant challenges. Existing datasets, generally distilled from English-centric LLMs, are not well-aligned with Chinese users' interaction patterns. To bridge this gap, we introduce COIG-CQIA, a new Chinese instruction tuning dataset derived from various real-world resources and undergoing rigorous human verification. We conduct extensive experimen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18058","kind":"arxiv","version":2},"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/2403.18058/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":"2026-07-05T09:30:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O33xX1dusA2PSoc1bjQ7rveXm/HUSmAqTVXdtvACfbWdIj66J4XMcsVIay0YZ5golnMxDoTEM2Z5Kq9G5zzWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:28:54.396249Z"},"content_sha256":"2af1ee72101cfb88285f36dab96ab23817727654fb10a05588105857f8c9fef9","schema_version":"1.0","event_id":"sha256:2af1ee72101cfb88285f36dab96ab23817727654fb10a05588105857f8c9fef9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ESGZ4K6WYU7JYGZFADGVBOYEBF/bundle.json","state_url":"https://pith.science/pith/ESGZ4K6WYU7JYGZFADGVBOYEBF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ESGZ4K6WYU7JYGZFADGVBOYEBF/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":"2026-08-10T18:28:54Z","links":{"resolver":"https://pith.science/pith/ESGZ4K6WYU7JYGZFADGVBOYEBF","bundle":"https://pith.science/pith/ESGZ4K6WYU7JYGZFADGVBOYEBF/bundle.json","state":"https://pith.science/pith/ESGZ4K6WYU7JYGZFADGVBOYEBF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ESGZ4K6WYU7JYGZFADGVBOYEBF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ESGZ4K6WYU7JYGZFADGVBOYEBF","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":"d6938066e3b00a6cffbdb5088ee70b1915507615f2bb82a90d75445ec8f1fbf1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T19:24:18Z","title_canon_sha256":"e1b78218a117376b2105987ddbdf34d141f0c01bda5c1b88bc73638152353004"},"schema_version":"1.0","source":{"id":"2403.18058","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.18058","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.18058v2","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18058","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"pith_short_12","alias_value":"ESGZ4K6WYU7J","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"pith_short_16","alias_value":"ESGZ4K6WYU7JYGZF","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"pith_short_8","alias_value":"ESGZ4K6W","created_at":"2026-07-05T09:30:11Z"}],"graph_snapshots":[{"event_id":"sha256:2af1ee72101cfb88285f36dab96ab23817727654fb10a05588105857f8c9fef9","target":"graph","created_at":"2026-07-05T09:30:11Z","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/2403.18058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Remarkable progress on English instruction tuning has facilitated the efficacy and reliability of large language models (LLMs). However, there remains a noticeable gap in instruction tuning for Chinese, where the complex linguistic features pose significant challenges. Existing datasets, generally distilled from English-centric LLMs, are not well-aligned with Chinese users' interaction patterns. To bridge this gap, we introduce COIG-CQIA, a new Chinese instruction tuning dataset derived from various real-world resources and undergoing rigorous human verification. We conduct extensive experimen","authors_text":"Chenghua Lin, Feiteng Fang, Ge Zhang, Haihong Wu, Hongquan Lin, Jiajun Zhang, Jie Fu, Junting Zhou, Mingshan Chang, Min Yang, Nuo Ma, Ruibin Yuan, Shiwen Ni, Tianyu Zheng, Wenhao Huang, Xincheng Zhang, Xinrun Du, Yiming Liang, Yonggang Jin, Yuelin Bai, Zekun Wang, Ziqiang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T19:24:18Z","title":"COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18058","kind":"arxiv","version":2},"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:cb81e418117b771beb0b4f9d2776097f9ae6d2937e8269f21ee0b3362accb39b","target":"record","created_at":"2026-07-05T09:30:11Z","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":"d6938066e3b00a6cffbdb5088ee70b1915507615f2bb82a90d75445ec8f1fbf1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T19:24:18Z","title_canon_sha256":"e1b78218a117376b2105987ddbdf34d141f0c01bda5c1b88bc73638152353004"},"schema_version":"1.0","source":{"id":"2403.18058","kind":"arxiv","version":2}},"canonical_sha256":"248d9e2bd6c53e9c1b2500cd50bb0409720133e4fe657162755f30cbd196b17a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"248d9e2bd6c53e9c1b2500cd50bb0409720133e4fe657162755f30cbd196b17a","first_computed_at":"2026-07-05T09:30:11.817243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:11.817243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aIDPZ+XBjb1+tr9dMyLH6uAx8gf0nSLvhWBp8UYMevaOAXrKyGH0AwRG2GRV6SOGduFjSZqGC+72Jn0pjOw4Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:11.817719Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.18058","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb81e418117b771beb0b4f9d2776097f9ae6d2937e8269f21ee0b3362accb39b","sha256:2af1ee72101cfb88285f36dab96ab23817727654fb10a05588105857f8c9fef9"],"state_sha256":"5f0db97e0dc92f7cf135f408ea7d47f921d792e0dd1a77b23c4ad3a9e91f7a12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7TXKIaoO/HliSVi4jHwS2NXn2JmduW88BDJl1F+wDYtDztIyqC8zT+uBYbU0kGv7b8EL1On/anYFjP4aMfw7DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:28:54.400191Z","bundle_sha256":"a3cc3082ea0d0658c8475d24624021a49a41f005ffa00a5d56a1ff75324d98e5"}}