{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DWGTHPAAU5BTKJYL7ZDA7E42LP","short_pith_number":"pith:DWGTHPAA","schema_version":"1.0","canonical_sha256":"1d8d33bc00a74335270bfe460f939a5bf5be569c2e0388fe37b975564a1e3de9","source":{"kind":"arxiv","id":"2404.06644","version":1},"attestation_state":"computed","paper":{"title":"Khayyam Challenge (PersianMMLU): Is Your LLM Truly Wise to The Persian Language?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alireza Sahebi, Doratossadat Dastgheib, Ehsaneddin Asgari, Mahdieh Soleymani Baghshah, Marzia Nouri, Mohammad Hossein Rohban, Mohammad Vali Sanian, Omid Ghahroodi","submitted_at":"2024-04-09T22:38:13Z","abstract_excerpt":"Evaluating Large Language Models (LLMs) is challenging due to their generative nature, necessitating precise evaluation methodologies. Additionally, non-English LLM evaluation lags behind English, resulting in the absence or weakness of LLMs for many languages. In response to this necessity, we introduce Khayyam Challenge (also known as PersianMMLU), a meticulously curated collection comprising 20,192 four-choice questions sourced from 38 diverse tasks extracted from Persian examinations, spanning a wide spectrum of subjects, complexities, and ages. The primary objective of the Khayyam Challen"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.06644","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-09T22:38:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"57a23339a3c1da93aee4409ff0800cb3ca4f2b789f9f53d62b42d2c943659cd1","abstract_canon_sha256":"9113763896225dbb39166335f0c7b54344cd7ad988f6cb5b5bd2dcaaeeda182e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:15.266096Z","signature_b64":"1X2hlOABQYHxnwQ+NX57LhdHJPGNohN77biQunId1SmtlpMxJ58g0TeaBubK42Ayb0i79f0Ibv32EysPiQ+WAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d8d33bc00a74335270bfe460f939a5bf5be569c2e0388fe37b975564a1e3de9","last_reissued_at":"2026-07-05T08:06:15.265587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:15.265587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Khayyam Challenge (PersianMMLU): Is Your LLM Truly Wise to The Persian Language?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alireza Sahebi, Doratossadat Dastgheib, Ehsaneddin Asgari, Mahdieh Soleymani Baghshah, Marzia Nouri, Mohammad Hossein Rohban, Mohammad Vali Sanian, Omid Ghahroodi","submitted_at":"2024-04-09T22:38:13Z","abstract_excerpt":"Evaluating Large Language Models (LLMs) is challenging due to their generative nature, necessitating precise evaluation methodologies. Additionally, non-English LLM evaluation lags behind English, resulting in the absence or weakness of LLMs for many languages. In response to this necessity, we introduce Khayyam Challenge (also known as PersianMMLU), a meticulously curated collection comprising 20,192 four-choice questions sourced from 38 diverse tasks extracted from Persian examinations, spanning a wide spectrum of subjects, complexities, and ages. The primary objective of the Khayyam Challen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06644","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.06644/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.06644","created_at":"2026-07-05T08:06:15.265645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.06644v1","created_at":"2026-07-05T08:06:15.265645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06644","created_at":"2026-07-05T08:06:15.265645+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWGTHPAAU5BT","created_at":"2026-07-05T08:06:15.265645+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWGTHPAAU5BTKJYL","created_at":"2026-07-05T08:06:15.265645+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWGTHPAA","created_at":"2026-07-05T08:06:15.265645+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07422","citing_title":"The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27015","citing_title":"PersLitEval: Fine-grained Benchmark and Evaluation of LLMs on Persian Literature Questions","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2406.04244","citing_title":"Benchmark Data Contamination of Large Language Models: A Survey","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DWGTHPAAU5BTKJYL7ZDA7E42LP","json":"https://pith.science/pith/DWGTHPAAU5BTKJYL7ZDA7E42LP.json","graph_json":"https://pith.science/api/pith-number/DWGTHPAAU5BTKJYL7ZDA7E42LP/graph.json","events_json":"https://pith.science/api/pith-number/DWGTHPAAU5BTKJYL7ZDA7E42LP/events.json","paper":"https://pith.science/paper/DWGTHPAA"},"agent_actions":{"view_html":"https://pith.science/pith/DWGTHPAAU5BTKJYL7ZDA7E42LP","download_json":"https://pith.science/pith/DWGTHPAAU5BTKJYL7ZDA7E42LP.json","view_paper":"https://pith.science/paper/DWGTHPAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.06644&json=true","fetch_graph":"https://pith.science/api/pith-number/DWGTHPAAU5BTKJYL7ZDA7E42LP/graph.json","fetch_events":"https://pith.science/api/pith-number/DWGTHPAAU5BTKJYL7ZDA7E42LP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWGTHPAAU5BTKJYL7ZDA7E42LP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWGTHPAAU5BTKJYL7ZDA7E42LP/action/storage_attestation","attest_author":"https://pith.science/pith/DWGTHPAAU5BTKJYL7ZDA7E42LP/action/author_attestation","sign_citation":"https://pith.science/pith/DWGTHPAAU5BTKJYL7ZDA7E42LP/action/citation_signature","submit_replication":"https://pith.science/pith/DWGTHPAAU5BTKJYL7ZDA7E42LP/action/replication_record"}},"created_at":"2026-07-05T08:06:15.265645+00:00","updated_at":"2026-07-05T08:06:15.265645+00:00"}