{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B7MF5LI262YXEHTKZSAJJIFVUL","short_pith_number":"pith:B7MF5LI2","schema_version":"1.0","canonical_sha256":"0fd85ead1af6b1721e6acc8094a0b5a2c631ed02c55cc079e0e3d625e7e53463","source":{"kind":"arxiv","id":"2411.05049","version":3},"attestation_state":"computed","paper":{"title":"ProverbEval: Exploring LLM Evaluation Challenges for Low-resource Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Assefa Atsbiha tesfau, Atnafu Lambebo Tonja, Bontu Fufa Balcha, Debela Desalegn Yadeta, Derartu Dagne Geremew, Dietrich Klakow, Henok Biadglign Ademtew, Israel Abebe Azime, Mulubrhan Abebe Nerea, Negasi Haile Abadi, Philipp Slusallek, Tadesse Destaw Belay, Thamar Solorio, Yonas Chanie","submitted_at":"2024-11-07T06:34:48Z","abstract_excerpt":"With the rapid development of evaluation datasets to assess LLMs understanding across a wide range of subjects and domains, identifying a suitable language understanding benchmark has become increasingly challenging. In this work, we explore LLM evaluation challenges for low-resource language understanding and introduce \\proverbeval, LLM evaluation benchmark for low-resource languages, focusing on low-resource language understanding in culture-specific scenarios. We benchmark various LLMs and explore factors that create variability in the benchmarking process. We observed performance variances"},"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":"2411.05049","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-07T06:34:48Z","cross_cats_sorted":[],"title_canon_sha256":"45106e656c7c02983cc374442a9406934ab73ab696b10528d5b7393f1d341c41","abstract_canon_sha256":"710dbee0f4c188f9cbc5c914d8642d850f30632995e7032c2ff3698267b0980f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:28.388468Z","signature_b64":"1n+69D4avlI8WoiIjY0OnBf5qgOs+bNquES6ac3pI4TsDWzpFcE6if0qqihkMA1J5f4IhGzJEuVm+BUNmcJ+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fd85ead1af6b1721e6acc8094a0b5a2c631ed02c55cc079e0e3d625e7e53463","last_reissued_at":"2026-07-05T10:11:28.387985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:28.387985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProverbEval: Exploring LLM Evaluation Challenges for Low-resource Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Assefa Atsbiha tesfau, Atnafu Lambebo Tonja, Bontu Fufa Balcha, Debela Desalegn Yadeta, Derartu Dagne Geremew, Dietrich Klakow, Henok Biadglign Ademtew, Israel Abebe Azime, Mulubrhan Abebe Nerea, Negasi Haile Abadi, Philipp Slusallek, Tadesse Destaw Belay, Thamar Solorio, Yonas Chanie","submitted_at":"2024-11-07T06:34:48Z","abstract_excerpt":"With the rapid development of evaluation datasets to assess LLMs understanding across a wide range of subjects and domains, identifying a suitable language understanding benchmark has become increasingly challenging. In this work, we explore LLM evaluation challenges for low-resource language understanding and introduce \\proverbeval, LLM evaluation benchmark for low-resource languages, focusing on low-resource language understanding in culture-specific scenarios. We benchmark various LLMs and explore factors that create variability in the benchmarking process. We observed performance variances"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05049","kind":"arxiv","version":3},"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/2411.05049/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":"2411.05049","created_at":"2026-07-05T10:11:28.388052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05049v3","created_at":"2026-07-05T10:11:28.388052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05049","created_at":"2026-07-05T10:11:28.388052+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7MF5LI262YX","created_at":"2026-07-05T10:11:28.388052+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7MF5LI262YXEHTK","created_at":"2026-07-05T10:11:28.388052+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7MF5LI2","created_at":"2026-07-05T10:11:28.388052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B7MF5LI262YXEHTKZSAJJIFVUL","json":"https://pith.science/pith/B7MF5LI262YXEHTKZSAJJIFVUL.json","graph_json":"https://pith.science/api/pith-number/B7MF5LI262YXEHTKZSAJJIFVUL/graph.json","events_json":"https://pith.science/api/pith-number/B7MF5LI262YXEHTKZSAJJIFVUL/events.json","paper":"https://pith.science/paper/B7MF5LI2"},"agent_actions":{"view_html":"https://pith.science/pith/B7MF5LI262YXEHTKZSAJJIFVUL","download_json":"https://pith.science/pith/B7MF5LI262YXEHTKZSAJJIFVUL.json","view_paper":"https://pith.science/paper/B7MF5LI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05049&json=true","fetch_graph":"https://pith.science/api/pith-number/B7MF5LI262YXEHTKZSAJJIFVUL/graph.json","fetch_events":"https://pith.science/api/pith-number/B7MF5LI262YXEHTKZSAJJIFVUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7MF5LI262YXEHTKZSAJJIFVUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7MF5LI262YXEHTKZSAJJIFVUL/action/storage_attestation","attest_author":"https://pith.science/pith/B7MF5LI262YXEHTKZSAJJIFVUL/action/author_attestation","sign_citation":"https://pith.science/pith/B7MF5LI262YXEHTKZSAJJIFVUL/action/citation_signature","submit_replication":"https://pith.science/pith/B7MF5LI262YXEHTKZSAJJIFVUL/action/replication_record"}},"created_at":"2026-07-05T10:11:28.388052+00:00","updated_at":"2026-07-05T10:11:28.388052+00:00"}