{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LSYEBA2WL6AJPNULX56ULQRT2T","short_pith_number":"pith:LSYEBA2W","schema_version":"1.0","canonical_sha256":"5cb04083565f8097b68bbf7d45c233d4df42ae8421f41968f904587df4220169","source":{"kind":"arxiv","id":"2404.02403","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Edalat, Amirhossein Abaskohi, Danial Namazifard, Mohammad Hadi Babalou, Mostafa Masoudi, Nesa Abbasi, Nikoo Naghavian, Pouya Sadeghi, Samin Mahdizadeh Sani, Sara Baruni, Sepehr Kamahi, Yadollah Yaghoobzadeh","submitted_at":"2024-04-03T02:12:29Z","abstract_excerpt":"This paper explores the efficacy of large language models (LLMs) for Persian. While ChatGPT and consequent LLMs have shown remarkable performance in English, their efficiency for more low-resource languages remains an open question. We present the first comprehensive benchmarking study of LLMs across diverse Persian language tasks. Our primary focus is on GPT-3.5-turbo, but we also include GPT-4 and OpenChat-3.5 to provide a more holistic evaluation. Our assessment encompasses a diverse set of tasks categorized into classic, reasoning, and knowledge-based domains. To enable a thorough comparis"},"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":"2404.02403","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T02:12:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f30ac3ce5fe02d09da607150d7da425e1d30133d7c927fe52a4e23b97445e437","abstract_canon_sha256":"c1dd432ee456194d1ab95189434269f8d430a1b4412a96e8fc08738890738f88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:55.662890Z","signature_b64":"i0VTEqZ19kc3rfsPNCTH77h9gXat44seHyCGrnX99/tx/KzyX8Yqtc53O/HKiF7g9DHRmj8EB9aIZh57aT5BDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cb04083565f8097b68bbf7d45c233d4df42ae8421f41968f904587df4220169","last_reissued_at":"2026-07-05T08:03:55.662402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:55.662402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Edalat, Amirhossein Abaskohi, Danial Namazifard, Mohammad Hadi Babalou, Mostafa Masoudi, Nesa Abbasi, Nikoo Naghavian, Pouya Sadeghi, Samin Mahdizadeh Sani, Sara Baruni, Sepehr Kamahi, Yadollah Yaghoobzadeh","submitted_at":"2024-04-03T02:12:29Z","abstract_excerpt":"This paper explores the efficacy of large language models (LLMs) for Persian. While ChatGPT and consequent LLMs have shown remarkable performance in English, their efficiency for more low-resource languages remains an open question. We present the first comprehensive benchmarking study of LLMs across diverse Persian language tasks. Our primary focus is on GPT-3.5-turbo, but we also include GPT-4 and OpenChat-3.5 to provide a more holistic evaluation. Our assessment encompasses a diverse set of tasks categorized into classic, reasoning, and knowledge-based domains. To enable a thorough comparis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02403","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/2404.02403/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":"2404.02403","created_at":"2026-07-05T08:03:55.662460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02403v1","created_at":"2026-07-05T08:03:55.662460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02403","created_at":"2026-07-05T08:03:55.662460+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSYEBA2WL6AJ","created_at":"2026-07-05T08:03:55.662460+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSYEBA2WL6AJPNUL","created_at":"2026-07-05T08:03:55.662460+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSYEBA2W","created_at":"2026-07-05T08:03:55.662460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27015","citing_title":"PersLitEval: Fine-grained Benchmark and Evaluation of LLMs on Persian Literature Questions","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSYEBA2WL6AJPNULX56ULQRT2T","json":"https://pith.science/pith/LSYEBA2WL6AJPNULX56ULQRT2T.json","graph_json":"https://pith.science/api/pith-number/LSYEBA2WL6AJPNULX56ULQRT2T/graph.json","events_json":"https://pith.science/api/pith-number/LSYEBA2WL6AJPNULX56ULQRT2T/events.json","paper":"https://pith.science/paper/LSYEBA2W"},"agent_actions":{"view_html":"https://pith.science/pith/LSYEBA2WL6AJPNULX56ULQRT2T","download_json":"https://pith.science/pith/LSYEBA2WL6AJPNULX56ULQRT2T.json","view_paper":"https://pith.science/paper/LSYEBA2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02403&json=true","fetch_graph":"https://pith.science/api/pith-number/LSYEBA2WL6AJPNULX56ULQRT2T/graph.json","fetch_events":"https://pith.science/api/pith-number/LSYEBA2WL6AJPNULX56ULQRT2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSYEBA2WL6AJPNULX56ULQRT2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSYEBA2WL6AJPNULX56ULQRT2T/action/storage_attestation","attest_author":"https://pith.science/pith/LSYEBA2WL6AJPNULX56ULQRT2T/action/author_attestation","sign_citation":"https://pith.science/pith/LSYEBA2WL6AJPNULX56ULQRT2T/action/citation_signature","submit_replication":"https://pith.science/pith/LSYEBA2WL6AJPNULX56ULQRT2T/action/replication_record"}},"created_at":"2026-07-05T08:03:55.662460+00:00","updated_at":"2026-07-05T08:03:55.662460+00:00"}