{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FRJ3HHYIWDAMXDDWYCCHHFAO6Q","short_pith_number":"pith:FRJ3HHYI","canonical_record":{"source":{"id":"2304.06364","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-13T09:39:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f2904bd4ffe5ce96b3b972e1fc8a8968dd88d028084d4c7c8955b278e7f449e","abstract_canon_sha256":"ec90ca1ff59448b9db5895e41cc3b23fbad0354bb6abf73b36ab1cb6cf7a9874"},"schema_version":"1.0"},"canonical_sha256":"2c53b39f08b0c0cb8c76c08473940ef436e2b446e9800fbd3d8aa67c194021d3","source":{"kind":"arxiv","id":"2304.06364","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.06364","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2304.06364v2","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06364","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"FRJ3HHYIWDAM","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"FRJ3HHYIWDAMXDDW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"FRJ3HHYI","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FRJ3HHYIWDAMXDDWYCCHHFAO6Q","target":"record","payload":{"canonical_record":{"source":{"id":"2304.06364","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-13T09:39:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f2904bd4ffe5ce96b3b972e1fc8a8968dd88d028084d4c7c8955b278e7f449e","abstract_canon_sha256":"ec90ca1ff59448b9db5895e41cc3b23fbad0354bb6abf73b36ab1cb6cf7a9874"},"schema_version":"1.0"},"canonical_sha256":"2c53b39f08b0c0cb8c76c08473940ef436e2b446e9800fbd3d8aa67c194021d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.257154Z","signature_b64":"ejqvxDIZ11uGstVmswye68n/vSAVK5FJw1mGZSL6R10JoMuS7cEHpSo/KPfzxDY9qbxQX2udZkcBectxc3OFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c53b39f08b0c0cb8c76c08473940ef436e2b446e9800fbd3d8aa67c194021d3","last_reissued_at":"2026-05-17T23:38:48.256487Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.256487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.06364","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":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lazr4yVYTbnyXPLwsIYc9yei9NRV4sONPk1IYpEt0nDY/blvS28SFnWjv1EEEj13Dbe/MJY2dRJqxjbqKC7oBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:13:39.833033Z"},"content_sha256":"6954bee0ff95d931f13612a783a08b0ed58dd2936f3e3938efd373923968ab0f","schema_version":"1.0","event_id":"sha256:6954bee0ff95d931f13612a783a08b0ed58dd2936f3e3938efd373923968ab0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FRJ3HHYIWDAMXDDWYCCHHFAO6Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AGIEval benchmark shows GPT-4 surpassing average humans on SAT math at 95 percent and LSAT.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amin Saied, Nan Duan, Ruixiang Cui, Shuai Lu, Wanjun Zhong, Weizhu Chen, Yanlin Wang, Yaobo Liang, Yiduo Guo","submitted_at":"2023-04-13T09:39:30Z","abstract_excerpt":"Evaluating the general abilities of foundation models to tackle human-level tasks is a vital aspect of their development and application in the pursuit of Artificial General Intelligence (AGI). Traditional benchmarks, which rely on artificial datasets, may not accurately represent human-level capabilities. In this paper, we introduce AGIEval, a novel benchmark specifically designed to assess foundation model in the context of human-centric standardized exams, such as college entrance exams, law school admission tests, math competitions, and lawyer qualification tests. We evaluate several state"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"GPT-4 surpasses average human performance on SAT, LSAT, and math competitions, attaining a 95% accuracy rate on the SAT Math test and a 92.5% accuracy on the English test of the Chinese national college entrance exam.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That standardized human exams are valid and representative proxies for general human-level cognitive capabilities without significant selection bias or format advantages for current model architectures.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AGIEval shows GPT-4 exceeding average human scores on SAT Math at 95% and Chinese college entrance English at 92.5%, while revealing weaker results on complex reasoning tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AGIEval benchmark shows GPT-4 surpassing average humans on SAT math at 95 percent and LSAT.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d7b2d23d251b913928ce3f45aa96b82d7a80957aa443931c8947354c3da3b233"},"source":{"id":"2304.06364","kind":"arxiv","version":2},"verdict":{"id":"35bdc164-9f80-46b8-8082-15b60c51cf65","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T09:59:54.385025Z","strongest_claim":"GPT-4 surpasses average human performance on SAT, LSAT, and math competitions, attaining a 95% accuracy rate on the SAT Math test and a 92.5% accuracy on the English test of the Chinese national college entrance exam.","one_line_summary":"AGIEval shows GPT-4 exceeding average human scores on SAT Math at 95% and Chinese college entrance English at 92.5%, while revealing weaker results on complex reasoning tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That standardized human exams are valid and representative proxies for general human-level cognitive capabilities without significant selection bias or format advantages for current model architectures.","pith_extraction_headline":"AGIEval benchmark shows GPT-4 surpassing average humans on SAT math at 95 percent and LSAT."},"references":{"count":287,"sample":[{"doi":"10.24963/ijcai.2022/629","year":2022,"title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence,","work_id":"c4f3637d-3692-46a9-bfea-c7bd6b57ae7f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics , pages=","work_id":"c6b78093-c72e-47cb-afc3-1e6df42e13ca","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"2023 , publisher =","work_id":"ec5f4dd4-c17c-4ada-92fd-e4e521e15710","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Communications of the ACM , volume=","work_id":"d5c1eec5-fe7c-47e3-b110-9b2ca7817689","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=","work_id":"83cfc672-4920-4faa-8e23-5c30b4777e6f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":287,"snapshot_sha256":"82933c7ffcb95de91c268d61a400ba36d7f656730ad69d223ad26b41a33716bc","internal_anchors":12},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0957bd48e13f7caae39084c23b61c2e1a362a81a1c84c48e796139f1b6f376fa"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"35bdc164-9f80-46b8-8082-15b60c51cf65"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fAVB6cjvZKzOfalThwRRIv+PDEJJOtGrhYfUXzQnFeNqB/IBHx7WF8HDWHlYWBLZ77FRKeDnxIxoFs0CQ85JCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:13:39.834013Z"},"content_sha256":"085e46b3ebe88be099a4a38f018e51ba1b174d09aa334d7793f9648479e78775","schema_version":"1.0","event_id":"sha256:085e46b3ebe88be099a4a38f018e51ba1b174d09aa334d7793f9648479e78775"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/bundle.json","state_url":"https://pith.science/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/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":"2026-05-25T16:13:39Z","links":{"resolver":"https://pith.science/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q","bundle":"https://pith.science/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/bundle.json","state":"https://pith.science/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FRJ3HHYIWDAMXDDWYCCHHFAO6Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FRJ3HHYIWDAMXDDWYCCHHFAO6Q","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":"ec90ca1ff59448b9db5895e41cc3b23fbad0354bb6abf73b36ab1cb6cf7a9874","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-13T09:39:30Z","title_canon_sha256":"7f2904bd4ffe5ce96b3b972e1fc8a8968dd88d028084d4c7c8955b278e7f449e"},"schema_version":"1.0","source":{"id":"2304.06364","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.06364","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2304.06364v2","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06364","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"FRJ3HHYIWDAM","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"FRJ3HHYIWDAMXDDW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"FRJ3HHYI","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:085e46b3ebe88be099a4a38f018e51ba1b174d09aa334d7793f9648479e78775","target":"graph","created_at":"2026-05-17T23:38:48Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"GPT-4 surpasses average human performance on SAT, LSAT, and math competitions, attaining a 95% accuracy rate on the SAT Math test and a 92.5% accuracy on the English test of the Chinese national college entrance exam."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That standardized human exams are valid and representative proxies for general human-level cognitive capabilities without significant selection bias or format advantages for current model architectures."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"AGIEval shows GPT-4 exceeding average human scores on SAT Math at 95% and Chinese college entrance English at 92.5%, while revealing weaker results on complex reasoning tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"AGIEval benchmark shows GPT-4 surpassing average humans on SAT math at 95 percent and LSAT."}],"snapshot_sha256":"d7b2d23d251b913928ce3f45aa96b82d7a80957aa443931c8947354c3da3b233"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0957bd48e13f7caae39084c23b61c2e1a362a81a1c84c48e796139f1b6f376fa"},"paper":{"abstract_excerpt":"Evaluating the general abilities of foundation models to tackle human-level tasks is a vital aspect of their development and application in the pursuit of Artificial General Intelligence (AGI). Traditional benchmarks, which rely on artificial datasets, may not accurately represent human-level capabilities. In this paper, we introduce AGIEval, a novel benchmark specifically designed to assess foundation model in the context of human-centric standardized exams, such as college entrance exams, law school admission tests, math competitions, and lawyer qualification tests. We evaluate several state","authors_text":"Amin Saied, Nan Duan, Ruixiang Cui, Shuai Lu, Wanjun Zhong, Weizhu Chen, Yanlin Wang, Yaobo Liang, Yiduo Guo","cross_cats":["cs.AI"],"headline":"AGIEval benchmark shows GPT-4 surpassing average humans on SAT math at 95 percent and LSAT.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-13T09:39:30Z","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models"},"references":{"count":287,"internal_anchors":12,"resolved_work":287,"sample":[{"cited_arxiv_id":"","doi":"10.24963/ijcai.2022/629","is_internal_anchor":false,"ref_index":1,"title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence,","work_id":"c4f3637d-3692-46a9-bfea-c7bd6b57ae7f","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics , pages=","work_id":"c6b78093-c72e-47cb-afc3-1e6df42e13ca","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"2023 , publisher =","work_id":"ec5f4dd4-c17c-4ada-92fd-e4e521e15710","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Communications of the ACM , volume=","work_id":"d5c1eec5-fe7c-47e3-b110-9b2ca7817689","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=","work_id":"83cfc672-4920-4faa-8e23-5c30b4777e6f","year":null}],"snapshot_sha256":"82933c7ffcb95de91c268d61a400ba36d7f656730ad69d223ad26b41a33716bc"},"source":{"id":"2304.06364","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T09:59:54.385025Z","id":"35bdc164-9f80-46b8-8082-15b60c51cf65","model_set":{"reader":"grok-4.3"},"one_line_summary":"AGIEval shows GPT-4 exceeding average human scores on SAT Math at 95% and Chinese college entrance English at 92.5%, while revealing weaker results on complex reasoning tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"AGIEval benchmark shows GPT-4 surpassing average humans on SAT math at 95 percent and LSAT.","strongest_claim":"GPT-4 surpasses average human performance on SAT, LSAT, and math competitions, attaining a 95% accuracy rate on the SAT Math test and a 92.5% accuracy on the English test of the Chinese national college entrance exam.","weakest_assumption":"That standardized human exams are valid and representative proxies for general human-level cognitive capabilities without significant selection bias or format advantages for current model architectures."}},"verdict_id":"35bdc164-9f80-46b8-8082-15b60c51cf65"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6954bee0ff95d931f13612a783a08b0ed58dd2936f3e3938efd373923968ab0f","target":"record","created_at":"2026-05-17T23:38:48Z","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":"ec90ca1ff59448b9db5895e41cc3b23fbad0354bb6abf73b36ab1cb6cf7a9874","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-13T09:39:30Z","title_canon_sha256":"7f2904bd4ffe5ce96b3b972e1fc8a8968dd88d028084d4c7c8955b278e7f449e"},"schema_version":"1.0","source":{"id":"2304.06364","kind":"arxiv","version":2}},"canonical_sha256":"2c53b39f08b0c0cb8c76c08473940ef436e2b446e9800fbd3d8aa67c194021d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c53b39f08b0c0cb8c76c08473940ef436e2b446e9800fbd3d8aa67c194021d3","first_computed_at":"2026-05-17T23:38:48.256487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:48.256487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ejqvxDIZ11uGstVmswye68n/vSAVK5FJw1mGZSL6R10JoMuS7cEHpSo/KPfzxDY9qbxQX2udZkcBectxc3OFAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:48.257154Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.06364","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6954bee0ff95d931f13612a783a08b0ed58dd2936f3e3938efd373923968ab0f","sha256:085e46b3ebe88be099a4a38f018e51ba1b174d09aa334d7793f9648479e78775"],"state_sha256":"9a4b4b4364cf33856c800bac070107f226a9650512206012a3a02a698b8f65a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x53Eo5Q99EgXEZCW9SKlpx2leT4LldOR4qcsuHbL1I/me6jeYxpp700Lhx2h4Mq3xRcfGER7LMVxCSOx8GVuBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:13:39.838277Z","bundle_sha256":"e5eb76247f88cadca5105676c14f71ae9a39a8feed9ddbb420d04ffca861712d"}}