{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QFHRRIKRVZGH65EP3JCPGZ3DQC","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":"e8ebe98e1d8a5da4415180120e85829b158afb29ea0544c8289ba2bc4c88ac39","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-08T13:21:29Z","title_canon_sha256":"7f5c1bd70cf534856a44a7b1dd095d7148eaba405afa0a008a80f63e30915861"},"schema_version":"1.0","source":{"id":"2306.05179","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05179","created_at":"2026-07-05T07:11:16Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05179v2","created_at":"2026-07-05T07:11:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05179","created_at":"2026-07-05T07:11:16Z"},{"alias_kind":"pith_short_12","alias_value":"QFHRRIKRVZGH","created_at":"2026-07-05T07:11:16Z"},{"alias_kind":"pith_short_16","alias_value":"QFHRRIKRVZGH65EP","created_at":"2026-07-05T07:11:16Z"},{"alias_kind":"pith_short_8","alias_value":"QFHRRIKR","created_at":"2026-07-05T07:11:16Z"}],"graph_snapshots":[{"event_id":"sha256:e02e80eee93292ec500f8719e4d4caa406b8d8b6c96a77733a76b513cae7bd4f","target":"graph","created_at":"2026-07-05T07:11:16Z","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/2306.05179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the existence of various benchmarks for evaluating natural language processing models, we argue that human exams are a more suitable means of evaluating general intelligence for large language models (LLMs), as they inherently demand a much wider range of abilities such as language understanding, domain knowledge, and problem-solving skills. To this end, we introduce M3Exam, a novel benchmark sourced from real and official human exam questions for evaluating LLMs in a multilingual, multimodal, and multilevel context. M3Exam exhibits three unique characteristics: (1) multilingualism, en","authors_text":"Chang Gao, Lidong Bing, Sharifah Mahani Aljunied, Wenxuan Zhang, Yew Ken Chia","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-08T13:21:29Z","title":"M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05179","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:f964ab023883554153549f9b1e527b9ceea00f19e26cbcbaed9a484f9ae3de04","target":"record","created_at":"2026-07-05T07:11:16Z","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":"e8ebe98e1d8a5da4415180120e85829b158afb29ea0544c8289ba2bc4c88ac39","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-08T13:21:29Z","title_canon_sha256":"7f5c1bd70cf534856a44a7b1dd095d7148eaba405afa0a008a80f63e30915861"},"schema_version":"1.0","source":{"id":"2306.05179","kind":"arxiv","version":2}},"canonical_sha256":"814f18a151ae4c7f748fda44f367638086394073034a559d9a33d468df89a928","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"814f18a151ae4c7f748fda44f367638086394073034a559d9a33d468df89a928","first_computed_at":"2026-07-05T07:11:16.264511Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:16.264511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0+l8XgDD3mfwumJIpa5q94gZYCdwNO3Xk9llLrjXjRQjP/yDzzoSnEbNLf0i+/1urdCwenI0h9CXF9iiK4miDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:16.264998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05179","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f964ab023883554153549f9b1e527b9ceea00f19e26cbcbaed9a484f9ae3de04","sha256:e02e80eee93292ec500f8719e4d4caa406b8d8b6c96a77733a76b513cae7bd4f"],"state_sha256":"612d7e61a64129e794455601f692fa96abf5d8dedc88a4ba424d77c5dfeca5b1"}