{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M2RDTAFXAD65H2DQRSIXVNLY3D","short_pith_number":"pith:M2RDTAFX","schema_version":"1.0","canonical_sha256":"66a23980b700fdd3e8708c917ab578d8df7c97c253d9c6b35f6276b4fb384bc2","source":{"kind":"arxiv","id":"2501.00559","version":1},"attestation_state":"computed","paper":{"title":"AraSTEM: A Native Arabic Multiple Choice Question Benchmark for Evaluating LLMs Knowledge In STEM Subjects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmad Mustapha, Aya Mourad, Hadi Al-Khansa, Hadi Al-Mubasher, Hasan El-Husseini, Mariette Awad, Marwah Al-Sakkaf, Ranam Hamoud","submitted_at":"2024-12-31T17:45:12Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable capabilities, not only in generating human-like text, but also in acquiring knowledge. This highlights the need to go beyond the typical Natural Language Processing downstream benchmarks and asses the various aspects of LLMs including knowledge and reasoning. Numerous benchmarks have been developed to evaluate LLMs knowledge, but they predominantly focus on the English language. Given that many LLMs are multilingual, relying solely on benchmarking English knowledge is insufficient. To address this issue, we introduce AraSTEM, a new Arabic mult"},"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":"2501.00559","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T17:45:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"999688ff2f0f014345da7c88a99da79061a4847dbd5f2a5b186ec53060ed3872","abstract_canon_sha256":"6b2619e2d42a67929fee35ea5c9507db80f0ce9319406d60c274f1a243410e15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:07.519462Z","signature_b64":"ZpuaWX8GC7XXPAGAazN1h1kNu0I+xo7NlxijuCtWE4VEVq7aV8lF4KAQnyX+XeD0+Bd48YbZl+kFnYnX3UqsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66a23980b700fdd3e8708c917ab578d8df7c97c253d9c6b35f6276b4fb384bc2","last_reissued_at":"2026-07-05T09:56:07.518680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:07.518680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AraSTEM: A Native Arabic Multiple Choice Question Benchmark for Evaluating LLMs Knowledge In STEM Subjects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmad Mustapha, Aya Mourad, Hadi Al-Khansa, Hadi Al-Mubasher, Hasan El-Husseini, Mariette Awad, Marwah Al-Sakkaf, Ranam Hamoud","submitted_at":"2024-12-31T17:45:12Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable capabilities, not only in generating human-like text, but also in acquiring knowledge. This highlights the need to go beyond the typical Natural Language Processing downstream benchmarks and asses the various aspects of LLMs including knowledge and reasoning. Numerous benchmarks have been developed to evaluate LLMs knowledge, but they predominantly focus on the English language. Given that many LLMs are multilingual, relying solely on benchmarking English knowledge is insufficient. To address this issue, we introduce AraSTEM, a new Arabic mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00559","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/2501.00559/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":"2501.00559","created_at":"2026-07-05T09:56:07.518779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00559v1","created_at":"2026-07-05T09:56:07.518779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00559","created_at":"2026-07-05T09:56:07.518779+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2RDTAFXAD65","created_at":"2026-07-05T09:56:07.518779+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2RDTAFXAD65H2DQ","created_at":"2026-07-05T09:56:07.518779+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2RDTAFX","created_at":"2026-07-05T09:56:07.518779+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15850","citing_title":"3LM: Bridging Arabic, STEM, and Code through Benchmarking","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2RDTAFXAD65H2DQRSIXVNLY3D","json":"https://pith.science/pith/M2RDTAFXAD65H2DQRSIXVNLY3D.json","graph_json":"https://pith.science/api/pith-number/M2RDTAFXAD65H2DQRSIXVNLY3D/graph.json","events_json":"https://pith.science/api/pith-number/M2RDTAFXAD65H2DQRSIXVNLY3D/events.json","paper":"https://pith.science/paper/M2RDTAFX"},"agent_actions":{"view_html":"https://pith.science/pith/M2RDTAFXAD65H2DQRSIXVNLY3D","download_json":"https://pith.science/pith/M2RDTAFXAD65H2DQRSIXVNLY3D.json","view_paper":"https://pith.science/paper/M2RDTAFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00559&json=true","fetch_graph":"https://pith.science/api/pith-number/M2RDTAFXAD65H2DQRSIXVNLY3D/graph.json","fetch_events":"https://pith.science/api/pith-number/M2RDTAFXAD65H2DQRSIXVNLY3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2RDTAFXAD65H2DQRSIXVNLY3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2RDTAFXAD65H2DQRSIXVNLY3D/action/storage_attestation","attest_author":"https://pith.science/pith/M2RDTAFXAD65H2DQRSIXVNLY3D/action/author_attestation","sign_citation":"https://pith.science/pith/M2RDTAFXAD65H2DQRSIXVNLY3D/action/citation_signature","submit_replication":"https://pith.science/pith/M2RDTAFXAD65H2DQRSIXVNLY3D/action/replication_record"}},"created_at":"2026-07-05T09:56:07.518779+00:00","updated_at":"2026-07-05T09:56:07.518779+00:00"}