{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3G274RG4QB2FZOEGHOWH6FBOY5","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":"9d81ed171b320c8675fd14d5a85e12430b3bc408b3dd76cda950858bc5b7991b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T11:38:10Z","title_canon_sha256":"437b5730c3f6f9af25d8a35ef00398f003241bcd0fd254321091f7a51bc984c7"},"schema_version":"1.0","source":{"id":"2412.10056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10056","created_at":"2026-07-05T09:48:46Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10056v1","created_at":"2026-07-05T09:48:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10056","created_at":"2026-07-05T09:48:46Z"},{"alias_kind":"pith_short_12","alias_value":"3G274RG4QB2F","created_at":"2026-07-05T09:48:46Z"},{"alias_kind":"pith_short_16","alias_value":"3G274RG4QB2FZOEG","created_at":"2026-07-05T09:48:46Z"},{"alias_kind":"pith_short_8","alias_value":"3G274RG4","created_at":"2026-07-05T09:48:46Z"}],"graph_snapshots":[{"event_id":"sha256:cd819b62391dee5214b3960381ebf250da4a9952d562a4328953f1660ef462dc","target":"graph","created_at":"2026-07-05T09:48:46Z","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/2412.10056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are commonly evaluated using human-crafted benchmarks, under the premise that higher scores implicitly reflect stronger human-like performance. However, there is growing concern that LLMs may ``game\" these benchmarks due to data leakage, achieving high scores while struggling with tasks simple for humans. To substantively address the problem, we create GAOKAO-Eval, a comprehensive benchmark based on China's National College Entrance Examination (Gaokao), and conduct ``closed-book\" evaluations for representative models released prior to Gaokao. Contrary to prevailin","authors_text":"Changbo Wang, Chenchui Li, Hanglei Hu, Hang Yan, Jin Zhang, Linyang Li, Qipeng Guo, Tianyi Liang, Yunfan Shao, Yunhua Zhou, Zhikai Lei","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T11:38:10Z","title":"GAOKAO-Eval: Does high scores truly reflect strong capabilities in LLMs?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10056","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":"sha256:13a02cb36acc8b605ec909cc8b775f196a9d02330da65abbd6fe0b218dc5f40a","target":"record","created_at":"2026-07-05T09:48:46Z","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":"9d81ed171b320c8675fd14d5a85e12430b3bc408b3dd76cda950858bc5b7991b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T11:38:10Z","title_canon_sha256":"437b5730c3f6f9af25d8a35ef00398f003241bcd0fd254321091f7a51bc984c7"},"schema_version":"1.0","source":{"id":"2412.10056","kind":"arxiv","version":1}},"canonical_sha256":"d9b5fe44dc80745cb8863bac7f142ec75b28b80bc40c4fb8e71da4c6a8001a77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9b5fe44dc80745cb8863bac7f142ec75b28b80bc40c4fb8e71da4c6a8001a77","first_computed_at":"2026-07-05T09:48:46.374424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:46.374424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QRjIrTgXry6qH3/1Ej8ssMFnzLiFEl1gMYqGRfOLTm8wDfuZhKND76OfF9QC90l8oJVO9X1Fo/h7TnsA3HGhDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:46.374823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13a02cb36acc8b605ec909cc8b775f196a9d02330da65abbd6fe0b218dc5f40a","sha256:cd819b62391dee5214b3960381ebf250da4a9952d562a4328953f1660ef462dc"],"state_sha256":"cac3540114c9a8f64450a00d80c3d8b0d80382dc546b7d3f8cf9809e279cef9d"}