{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3LOUCYKGIDGCFARGLT5CLA6SWV","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":"3e8a323c6ce8d8bd821eb791f986ac0411257384678534e322919c3788b43aff","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T16:02:12Z","title_canon_sha256":"0ff781b691451f90d82cd63719a47a9aad88d12861f3f022bdc2b821117f255b"},"schema_version":"1.0","source":{"id":"2402.13109","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13109","created_at":"2026-07-05T08:27:04Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13109v2","created_at":"2026-07-05T08:27:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13109","created_at":"2026-07-05T08:27:04Z"},{"alias_kind":"pith_short_12","alias_value":"3LOUCYKGIDGC","created_at":"2026-07-05T08:27:04Z"},{"alias_kind":"pith_short_16","alias_value":"3LOUCYKGIDGCFARG","created_at":"2026-07-05T08:27:04Z"},{"alias_kind":"pith_short_8","alias_value":"3LOUCYKG","created_at":"2026-07-05T08:27:04Z"}],"graph_snapshots":[{"event_id":"sha256:db200c6d82ed460ed0bde55c8fc33f40fb90ad9445d634d9ca2b7932c368d98b","target":"graph","created_at":"2026-07-05T08:27:04Z","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/2402.13109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advancement of large language models (LLMs) has enhanced the ability to generalize across a wide range of unseen natural language processing (NLP) tasks through instruction-following. Yet, their effectiveness often diminishes in low-resource languages like Chinese, exacerbated by biased evaluations from data leakage, casting doubt on their true generalizability to new linguistic territories. In response, we introduce the Chinese Instruction-Following Benchmark (CIF-Bench), designed to evaluate the zero-shot generalizability of LLMs to the Chinese language. CIF-Bench comprises 150 tasks and","authors_text":"Chenghua Lin, Ge Zhang, Hao Li, Jiajun Zhang, Jiali Li, Jie Fu, Kai Zhang, Lei Ma, Lei Zhang, Ruibin Yuan, Stephen W. Huang, Wangchunshu Zhou, Xingwei Qu, Yiming Liang, Yinghao Ma, Yizhi Li, Zekun Wang, Zhaoqun Li, Zuowen Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T16:02:12Z","title":"CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13109","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":"sha256:0d008df68df818f870938c314604507157126d8bb143fe5afabad71a8ea29f66","target":"record","created_at":"2026-07-05T08:27:04Z","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":"3e8a323c6ce8d8bd821eb791f986ac0411257384678534e322919c3788b43aff","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T16:02:12Z","title_canon_sha256":"0ff781b691451f90d82cd63719a47a9aad88d12861f3f022bdc2b821117f255b"},"schema_version":"1.0","source":{"id":"2402.13109","kind":"arxiv","version":2}},"canonical_sha256":"dadd41614640cc2282265cfa2583d2b569c6fb11cdb17aaccd07d0007a1df8fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dadd41614640cc2282265cfa2583d2b569c6fb11cdb17aaccd07d0007a1df8fd","first_computed_at":"2026-07-05T08:27:04.339035Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:04.339035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h5awY6k07IvdfMgUnaMR/wA8t6ckBAJqsD3EWECq/xjRXH6Uwy7Wu5XTkVZtnKAc729MPjqXoBxv+spLBBkiCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:04.339646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13109","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d008df68df818f870938c314604507157126d8bb143fe5afabad71a8ea29f66","sha256:db200c6d82ed460ed0bde55c8fc33f40fb90ad9445d634d9ca2b7932c368d98b"],"state_sha256":"3daa72efbcd49d2490c2d4b480829589c75dae6434052bebd4a6c6f018222769"}