{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FDV6NMC53G3AJQ266TK2456VUL","short_pith_number":"pith:FDV6NMC5","canonical_record":{"source":{"id":"2504.05535","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T22:15:51Z","cross_cats_sorted":[],"title_canon_sha256":"8e4f2ffe68c4e59c2b21a44192f79d229b80a68636918006b46bdf74e4462a76","abstract_canon_sha256":"14bb593277373e79a88c642a0c5b2a5facc717f7947da91d3d93326a41612e11"},"schema_version":"1.0"},"canonical_sha256":"28ebe6b05dd9b604c35ef4d5ae77d5a2d4c76cb733eecf93c4f37a57a5f103f9","source":{"kind":"arxiv","id":"2504.05535","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05535","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05535v1","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05535","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"pith_short_12","alias_value":"FDV6NMC53G3A","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"pith_short_16","alias_value":"FDV6NMC53G3AJQ26","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"pith_short_8","alias_value":"FDV6NMC5","created_at":"2026-07-05T10:46:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FDV6NMC53G3AJQ266TK2456VUL","target":"record","payload":{"canonical_record":{"source":{"id":"2504.05535","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T22:15:51Z","cross_cats_sorted":[],"title_canon_sha256":"8e4f2ffe68c4e59c2b21a44192f79d229b80a68636918006b46bdf74e4462a76","abstract_canon_sha256":"14bb593277373e79a88c642a0c5b2a5facc717f7947da91d3d93326a41612e11"},"schema_version":"1.0"},"canonical_sha256":"28ebe6b05dd9b604c35ef4d5ae77d5a2d4c76cb733eecf93c4f37a57a5f103f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:05.448949Z","signature_b64":"XJsqHX2wW6PTzOOQflwRSQDOnAOamzf99kAXR0thM2NUJG0WUoX7ZpobASo2GfteQe3n9WUDxSpDie/Ukt8iBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28ebe6b05dd9b604c35ef4d5ae77d5a2d4c76cb733eecf93c4f37a57a5f103f9","last_reissued_at":"2026-07-05T10:46:05.448454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:05.448454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.05535","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":"2026-07-05T10:46:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tY7bPdkWVr73tbQyq7u9NIXLg1Qw29gaV6iO/pXFfBfnQSYNBUybhWW9Xsn9Rb3GUtDJljnOZgUy1i++Aog4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:59:10.023566Z"},"content_sha256":"c023462d310f753b6ddeef90361d7600d0c98e4edcc03c25f602463798c7e51c","schema_version":"1.0","event_id":"sha256:c023462d310f753b6ddeef90361d7600d0c98e4edcc03c25f602463798c7e51c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FDV6NMC53G3AJQ266TK2456VUL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boyu Feng, Chenghua Lin, Chenglin Cai, Ding Pan, Ge Zhang, Guoyin Wang, Haoran Que, Huaqing Yuan, Jiaheng Liu, Jian Yang, Jie Liu, Jincheng Ren, M-A-P Team, Minghao Liu, Qunshu Lin, Shenzhi Wang, Shuyue Guo, Siwei Wu, Tiannan Wang, Tianyu Zheng, Wangchunshu Zhou, Wenhao Huang, Xingwei Qu, Xingyuan Bu, Xinrun Du, Yiming Liang, Yuchen Jiang, Yuelin Bai, Yunwen Li, Zekun Moore Wang, Zenith Wang, Zhouliang Yu","submitted_at":"2025-04-07T22:15:51Z","abstract_excerpt":"Aligning large language models (LLMs) with human preferences has achieved remarkable success. However, existing Chinese preference datasets are limited by small scale, narrow domain coverage, and lack of rigorous data validation. Additionally, the reliance on human annotators for instruction and response labeling significantly constrains the scalability of human preference datasets. To address these challenges, we design an LLM-based Chinese preference dataset annotation pipeline with no human intervention. Specifically, we crawled and carefully filtered 92k high-quality Chinese queries and em"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05535","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/2504.05535/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":"2026-07-05T10:46:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tv8UJHdvcuJuXLqRx64TS7BY6O6TwGTkqgQF1gSSmEY1TEKn++8c1KOpbWyJhnQ/xH+rgNMMHMTxww6sABV5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:59:10.023942Z"},"content_sha256":"9387675dafbe83f84b04239e5f3d28911bdc4089aeafad2ef2252d4a4d7ce004","schema_version":"1.0","event_id":"sha256:9387675dafbe83f84b04239e5f3d28911bdc4089aeafad2ef2252d4a4d7ce004"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FDV6NMC53G3AJQ266TK2456VUL/bundle.json","state_url":"https://pith.science/pith/FDV6NMC53G3AJQ266TK2456VUL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FDV6NMC53G3AJQ266TK2456VUL/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":"2026-07-07T15:59:10Z","links":{"resolver":"https://pith.science/pith/FDV6NMC53G3AJQ266TK2456VUL","bundle":"https://pith.science/pith/FDV6NMC53G3AJQ266TK2456VUL/bundle.json","state":"https://pith.science/pith/FDV6NMC53G3AJQ266TK2456VUL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FDV6NMC53G3AJQ266TK2456VUL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FDV6NMC53G3AJQ266TK2456VUL","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":"14bb593277373e79a88c642a0c5b2a5facc717f7947da91d3d93326a41612e11","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T22:15:51Z","title_canon_sha256":"8e4f2ffe68c4e59c2b21a44192f79d229b80a68636918006b46bdf74e4462a76"},"schema_version":"1.0","source":{"id":"2504.05535","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05535","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05535v1","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05535","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"pith_short_12","alias_value":"FDV6NMC53G3A","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"pith_short_16","alias_value":"FDV6NMC53G3AJQ26","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"pith_short_8","alias_value":"FDV6NMC5","created_at":"2026-07-05T10:46:05Z"}],"graph_snapshots":[{"event_id":"sha256:9387675dafbe83f84b04239e5f3d28911bdc4089aeafad2ef2252d4a4d7ce004","target":"graph","created_at":"2026-07-05T10:46:05Z","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/2504.05535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning large language models (LLMs) with human preferences has achieved remarkable success. However, existing Chinese preference datasets are limited by small scale, narrow domain coverage, and lack of rigorous data validation. Additionally, the reliance on human annotators for instruction and response labeling significantly constrains the scalability of human preference datasets. To address these challenges, we design an LLM-based Chinese preference dataset annotation pipeline with no human intervention. Specifically, we crawled and carefully filtered 92k high-quality Chinese queries and em","authors_text":"Boyu Feng, Chenghua Lin, Chenglin Cai, Ding Pan, Ge Zhang, Guoyin Wang, Haoran Que, Huaqing Yuan, Jiaheng Liu, Jian Yang, Jie Liu, Jincheng Ren, M-A-P Team, Minghao Liu, Qunshu Lin, Shenzhi Wang, Shuyue Guo, Siwei Wu, Tiannan Wang, Tianyu Zheng, Wangchunshu Zhou, Wenhao Huang, Xingwei Qu, Xingyuan Bu, Xinrun Du, Yiming Liang, Yuchen Jiang, Yuelin Bai, Yunwen Li, Zekun Moore Wang, Zenith Wang, Zhouliang Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T22:15:51Z","title":"COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05535","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:c023462d310f753b6ddeef90361d7600d0c98e4edcc03c25f602463798c7e51c","target":"record","created_at":"2026-07-05T10:46:05Z","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":"14bb593277373e79a88c642a0c5b2a5facc717f7947da91d3d93326a41612e11","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T22:15:51Z","title_canon_sha256":"8e4f2ffe68c4e59c2b21a44192f79d229b80a68636918006b46bdf74e4462a76"},"schema_version":"1.0","source":{"id":"2504.05535","kind":"arxiv","version":1}},"canonical_sha256":"28ebe6b05dd9b604c35ef4d5ae77d5a2d4c76cb733eecf93c4f37a57a5f103f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28ebe6b05dd9b604c35ef4d5ae77d5a2d4c76cb733eecf93c4f37a57a5f103f9","first_computed_at":"2026-07-05T10:46:05.448454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:05.448454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XJsqHX2wW6PTzOOQflwRSQDOnAOamzf99kAXR0thM2NUJG0WUoX7ZpobASo2GfteQe3n9WUDxSpDie/Ukt8iBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:05.448949Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.05535","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c023462d310f753b6ddeef90361d7600d0c98e4edcc03c25f602463798c7e51c","sha256:9387675dafbe83f84b04239e5f3d28911bdc4089aeafad2ef2252d4a4d7ce004"],"state_sha256":"e4ee5c5c4e830be5933f226b062bf19c4719825375ab25c768ef31fb65f8d20e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Elre4mbvkPyJ5e6+00VYWzBgHzsRNGuM17eHQO7NV5o34wauTeoo2JCvTPP1KII0zG2uhzRfnBCTmd+I476DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:59:10.026639Z","bundle_sha256":"75b49d76d3347b7628ed6fde946096425fad72b3ada4a8c5553139d887c83068"}}