{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GOI3GGPNMPK37Y6HGWBV6TSZN6","short_pith_number":"pith:GOI3GGPN","schema_version":"1.0","canonical_sha256":"3391b319ed63d5bfe3c735835f4e596f9a8fb1623c0d7780560a6275891f538f","source":{"kind":"arxiv","id":"2501.00593","version":2},"attestation_state":"computed","paper":{"title":"Setting Standards in Turkish NLP: TR-MMLU for Large Language Model Evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmet Semih G\\\"um\\\"u\\c{s}, Ali Arda Fincan, Banu Diri, M. Ali Bayram, \\\"Oner Ayta\\c{s}, Sava\\c{s} Y{\\i}ld{\\i}r{\\i}m","submitted_at":"2024-12-31T18:43:49Z","abstract_excerpt":"Language models have made remarkable advancements in understanding and generating human language, achieving notable success across a wide array of applications. However, evaluating these models remains a significant challenge, particularly for resource-limited languages such as Turkish. To address this gap, we introduce the Turkish MMLU (TR-MMLU) benchmark, a comprehensive evaluation framework designed to assess the linguistic and conceptual capabilities of large language models (LLMs) in Turkish. TR-MMLU is constructed from a carefully curated dataset comprising 6200 multiple-choice questions"},"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":"2501.00593","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T18:43:49Z","cross_cats_sorted":[],"title_canon_sha256":"c0d2b3c3b2ff7ba7403267e5cfa68ed7fb729d2414feaddad59baa977cfaa5a8","abstract_canon_sha256":"b0b98e68b2af26b5f0f42dc4c68ea29272f98f2380861e51e1dff5eedf8e8be5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:58.894475Z","signature_b64":"MGXIoF/agUje0IRH1q6JxtqUhLQ7sujIqRn5veGapKtvL4Ly40AG3rJuxGUaTZnJ+0I4Db0aW+3C5Y88hJmkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3391b319ed63d5bfe3c735835f4e596f9a8fb1623c0d7780560a6275891f538f","last_reissued_at":"2026-07-05T09:56:58.893968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:58.893968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Setting Standards in Turkish NLP: TR-MMLU for Large Language Model Evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmet Semih G\\\"um\\\"u\\c{s}, Ali Arda Fincan, Banu Diri, M. Ali Bayram, \\\"Oner Ayta\\c{s}, Sava\\c{s} Y{\\i}ld{\\i}r{\\i}m","submitted_at":"2024-12-31T18:43:49Z","abstract_excerpt":"Language models have made remarkable advancements in understanding and generating human language, achieving notable success across a wide array of applications. However, evaluating these models remains a significant challenge, particularly for resource-limited languages such as Turkish. To address this gap, we introduce the Turkish MMLU (TR-MMLU) benchmark, a comprehensive evaluation framework designed to assess the linguistic and conceptual capabilities of large language models (LLMs) in Turkish. TR-MMLU is constructed from a carefully curated dataset comprising 6200 multiple-choice questions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00593","kind":"arxiv","version":2},"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/2501.00593/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":"2501.00593","created_at":"2026-07-05T09:56:58.894029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00593v2","created_at":"2026-07-05T09:56:58.894029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00593","created_at":"2026-07-05T09:56:58.894029+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOI3GGPNMPK3","created_at":"2026-07-05T09:56:58.894029+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOI3GGPNMPK37Y6H","created_at":"2026-07-05T09:56:58.894029+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOI3GGPN","created_at":"2026-07-05T09:56:58.894029+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21445","citing_title":"Text2Cypher Across Languages: Evaluating and Finetuning LLMs","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GOI3GGPNMPK37Y6HGWBV6TSZN6","json":"https://pith.science/pith/GOI3GGPNMPK37Y6HGWBV6TSZN6.json","graph_json":"https://pith.science/api/pith-number/GOI3GGPNMPK37Y6HGWBV6TSZN6/graph.json","events_json":"https://pith.science/api/pith-number/GOI3GGPNMPK37Y6HGWBV6TSZN6/events.json","paper":"https://pith.science/paper/GOI3GGPN"},"agent_actions":{"view_html":"https://pith.science/pith/GOI3GGPNMPK37Y6HGWBV6TSZN6","download_json":"https://pith.science/pith/GOI3GGPNMPK37Y6HGWBV6TSZN6.json","view_paper":"https://pith.science/paper/GOI3GGPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00593&json=true","fetch_graph":"https://pith.science/api/pith-number/GOI3GGPNMPK37Y6HGWBV6TSZN6/graph.json","fetch_events":"https://pith.science/api/pith-number/GOI3GGPNMPK37Y6HGWBV6TSZN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOI3GGPNMPK37Y6HGWBV6TSZN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOI3GGPNMPK37Y6HGWBV6TSZN6/action/storage_attestation","attest_author":"https://pith.science/pith/GOI3GGPNMPK37Y6HGWBV6TSZN6/action/author_attestation","sign_citation":"https://pith.science/pith/GOI3GGPNMPK37Y6HGWBV6TSZN6/action/citation_signature","submit_replication":"https://pith.science/pith/GOI3GGPNMPK37Y6HGWBV6TSZN6/action/replication_record"}},"created_at":"2026-07-05T09:56:58.894029+00:00","updated_at":"2026-07-05T09:56:58.894029+00:00"}