{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5FIO742N4YDBQOLSLECYHMPIID","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":"26b33bd2731d5567bed3bf6fdcdd54fca08100e0a795ece3110ab1fd2d8adbb3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T09:56:57Z","title_canon_sha256":"cd093bedf1a8db9c8cd795ea558177824b88b1451ab2ba2c5fde5fcf4f29e74f"},"schema_version":"1.0","source":{"id":"2401.06477","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06477","created_at":"2026-07-05T09:30:58Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06477v4","created_at":"2026-07-05T09:30:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06477","created_at":"2026-07-05T09:30:58Z"},{"alias_kind":"pith_short_12","alias_value":"5FIO742N4YDB","created_at":"2026-07-05T09:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"5FIO742N4YDBQOLS","created_at":"2026-07-05T09:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"5FIO742N","created_at":"2026-07-05T09:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:aebb54400fb7bd43b6dccb833a56f91041bcf523d0e8bdcbf4516da98275646b","target":"graph","created_at":"2026-07-05T09:30:58Z","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/2401.06477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce Kun, a novel approach for creating high-quality instruction-tuning datasets for large language models (LLMs) without relying on manual annotations. Adapting a self-training algorithm based on instruction back-translation and answer polishment, Kun leverages unlabelled data from diverse sources such as Wudao, Wanjuan, and SkyPile to generate a substantial dataset of over a million Chinese instructional data points. This approach significantly deviates from traditional methods by using a self-curation process to refine and select the most effective instruction-output ","authors_text":"Chenghua Lin, Ge Zhang, Jiawei Guo, Jie Fu, Qi Jia, Shuyue Guo, Tianyu Zheng, Wenhao Huang, Xingwei Qu, Xinrun Du","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T09:56:57Z","title":"Kun: Answer Polishment for Chinese Self-Alignment with Instruction Back-Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06477","kind":"arxiv","version":4},"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":"sha256:02108ea0e8c8c641a0a42526fc6e356556479bf81632fe480f7a3b52c96b774e","target":"record","created_at":"2026-07-05T09:30:58Z","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":"26b33bd2731d5567bed3bf6fdcdd54fca08100e0a795ece3110ab1fd2d8adbb3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T09:56:57Z","title_canon_sha256":"cd093bedf1a8db9c8cd795ea558177824b88b1451ab2ba2c5fde5fcf4f29e74f"},"schema_version":"1.0","source":{"id":"2401.06477","kind":"arxiv","version":4}},"canonical_sha256":"e950eff34de606183972590583b1e840c5a7fb023b27b13a56863ead93070904","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e950eff34de606183972590583b1e840c5a7fb023b27b13a56863ead93070904","first_computed_at":"2026-07-05T09:30:58.708782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:58.708782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MtBGk701XtyKi9FJu+D6khS8OtXD7xoXN4fGaM36rDANGcMohnjSalS3R/CT4HuFoXNZ+TglZ5naqtm5U9vLAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:58.709293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06477","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02108ea0e8c8c641a0a42526fc6e356556479bf81632fe480f7a3b52c96b774e","sha256:aebb54400fb7bd43b6dccb833a56f91041bcf523d0e8bdcbf4516da98275646b"],"state_sha256":"51588c8be0ca2fed1da342db09c0fd03ede4fb01135adeddd8c4f24104a14cf7"}