{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OTYNPOJBJXWFXQ76H77RGAYOE7","short_pith_number":"pith:OTYNPOJB","schema_version":"1.0","canonical_sha256":"74f0d7b9214dec5bc3fe3fff13030e27d466e1c2b2e25c13a6e9cec74f6120d6","source":{"kind":"arxiv","id":"2501.16516","version":1},"attestation_state":"computed","paper":{"title":"How well can LLMs Grade Essays in Arabic?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Edwin Simpson, Rayed Ghazawi","submitted_at":"2025-01-27T21:30:02Z","abstract_excerpt":"This research assesses the effectiveness of state-of-the-art large language models (LLMs), including ChatGPT, Llama, Aya, Jais, and ACEGPT, in the task of Arabic automated essay scoring (AES) using the AR-AES dataset. It explores various evaluation methodologies, including zero-shot, few-shot in-context learning, and fine-tuning, and examines the influence of instruction-following capabilities through the inclusion of marking guidelines within the prompts. A mixed-language prompting strategy, integrating English prompts with Arabic content, was implemented to improve model comprehension and pe"},"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":"2501.16516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T21:30:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f122ed34710495749da2de247e6ba1d74554cb9a131566c9a0d33761bee54f2a","abstract_canon_sha256":"50a6164ec7a5e078dc013666b3661e3db59c8c89b0f4f387c188363d9d102c42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:14.467715Z","signature_b64":"wfjEy0TRKWWs2FLVLo9hN/xW3QL2XT79iGzAqsuZENGBLvYrHVcB45RV7WqvhXwXMd/BHkLpKCMsceTWoKJtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74f0d7b9214dec5bc3fe3fff13030e27d466e1c2b2e25c13a6e9cec74f6120d6","last_reissued_at":"2026-07-05T10:06:14.467219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:14.467219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How well can LLMs Grade Essays in Arabic?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Edwin Simpson, Rayed Ghazawi","submitted_at":"2025-01-27T21:30:02Z","abstract_excerpt":"This research assesses the effectiveness of state-of-the-art large language models (LLMs), including ChatGPT, Llama, Aya, Jais, and ACEGPT, in the task of Arabic automated essay scoring (AES) using the AR-AES dataset. It explores various evaluation methodologies, including zero-shot, few-shot in-context learning, and fine-tuning, and examines the influence of instruction-following capabilities through the inclusion of marking guidelines within the prompts. A mixed-language prompting strategy, integrating English prompts with Arabic content, was implemented to improve model comprehension and pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16516","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/2501.16516/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":"2501.16516","created_at":"2026-07-05T10:06:14.467284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16516v1","created_at":"2026-07-05T10:06:14.467284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16516","created_at":"2026-07-05T10:06:14.467284+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTYNPOJBJXWF","created_at":"2026-07-05T10:06:14.467284+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTYNPOJBJXWFXQ76","created_at":"2026-07-05T10:06:14.467284+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTYNPOJB","created_at":"2026-07-05T10:06:14.467284+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20287","citing_title":"PsyScore: A Psychometrically-Aware Framework for Trait-Adaptive Essay Scoring and ZPD-Scaffolded Feedback","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTYNPOJBJXWFXQ76H77RGAYOE7","json":"https://pith.science/pith/OTYNPOJBJXWFXQ76H77RGAYOE7.json","graph_json":"https://pith.science/api/pith-number/OTYNPOJBJXWFXQ76H77RGAYOE7/graph.json","events_json":"https://pith.science/api/pith-number/OTYNPOJBJXWFXQ76H77RGAYOE7/events.json","paper":"https://pith.science/paper/OTYNPOJB"},"agent_actions":{"view_html":"https://pith.science/pith/OTYNPOJBJXWFXQ76H77RGAYOE7","download_json":"https://pith.science/pith/OTYNPOJBJXWFXQ76H77RGAYOE7.json","view_paper":"https://pith.science/paper/OTYNPOJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16516&json=true","fetch_graph":"https://pith.science/api/pith-number/OTYNPOJBJXWFXQ76H77RGAYOE7/graph.json","fetch_events":"https://pith.science/api/pith-number/OTYNPOJBJXWFXQ76H77RGAYOE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTYNPOJBJXWFXQ76H77RGAYOE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTYNPOJBJXWFXQ76H77RGAYOE7/action/storage_attestation","attest_author":"https://pith.science/pith/OTYNPOJBJXWFXQ76H77RGAYOE7/action/author_attestation","sign_citation":"https://pith.science/pith/OTYNPOJBJXWFXQ76H77RGAYOE7/action/citation_signature","submit_replication":"https://pith.science/pith/OTYNPOJBJXWFXQ76H77RGAYOE7/action/replication_record"}},"created_at":"2026-07-05T10:06:14.467284+00:00","updated_at":"2026-07-05T10:06:14.467284+00:00"}