{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WL42RQ7ZYVX2GT7PLVJA5HXISQ","short_pith_number":"pith:WL42RQ7Z","schema_version":"1.0","canonical_sha256":"b2f9a8c3f9c56fa34fef5d520e9ee89431b7fe0b9c7c6c718a70b6d8c21d0c7e","source":{"kind":"arxiv","id":"2506.08400","version":3},"attestation_state":"computed","paper":{"title":"mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"David Ifeoluwa Adelani, Fabian David Schmidt, Jesujoba O. Alabi, Joyce Nakatumba-Nabende, Luel Hagos Beyene, Min Ma, Vivek Verma","submitted_at":"2025-06-10T03:15:08Z","abstract_excerpt":"Large Language models (LLMs) have demonstrated impressive performance on a wide range of tasks, including in multimodal settings such as speech. However, their evaluation is often limited to English and a few high-resource languages. For low-resource languages, there is no standardized evaluation benchmark. In this paper, we address this gap by introducing mSTEB, a new benchmark to evaluate the performance of LLMs on a wide range of tasks covering language identification, text classification, question answering, and translation tasks on both speech and text modalities. We evaluated the perform"},"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":"2506.08400","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T03:15:08Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"01ea2f7b382c5d00b388ba26ae5d2a80cfb51aa39b8c2cd3f47dd612a6f712dd","abstract_canon_sha256":"a550a2392bf66e8595be025e4cddfd32aa12b8c1e29572790af2e8b00aeee296"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:02.102122Z","signature_b64":"3e6NypkUgo4aaG3xOi8AzH+T/svE2EwFtzK98ybwK74DGktkuscA0D/gi8GCGzYdx4SqaTsAa3K/TtzSeD0sBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2f9a8c3f9c56fa34fef5d520e9ee89431b7fe0b9c7c6c718a70b6d8c21d0c7e","last_reissued_at":"2026-07-05T12:00:02.101535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:02.101535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"David Ifeoluwa Adelani, Fabian David Schmidt, Jesujoba O. Alabi, Joyce Nakatumba-Nabende, Luel Hagos Beyene, Min Ma, Vivek Verma","submitted_at":"2025-06-10T03:15:08Z","abstract_excerpt":"Large Language models (LLMs) have demonstrated impressive performance on a wide range of tasks, including in multimodal settings such as speech. However, their evaluation is often limited to English and a few high-resource languages. For low-resource languages, there is no standardized evaluation benchmark. In this paper, we address this gap by introducing mSTEB, a new benchmark to evaluate the performance of LLMs on a wide range of tasks covering language identification, text classification, question answering, and translation tasks on both speech and text modalities. We evaluated the perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08400","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/2506.08400/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":"2506.08400","created_at":"2026-07-05T12:00:02.101594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08400v3","created_at":"2026-07-05T12:00:02.101594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08400","created_at":"2026-07-05T12:00:02.101594+00:00"},{"alias_kind":"pith_short_12","alias_value":"WL42RQ7ZYVX2","created_at":"2026-07-05T12:00:02.101594+00:00"},{"alias_kind":"pith_short_16","alias_value":"WL42RQ7ZYVX2GT7P","created_at":"2026-07-05T12:00:02.101594+00:00"},{"alias_kind":"pith_short_8","alias_value":"WL42RQ7Z","created_at":"2026-07-05T12:00:02.101594+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08194","citing_title":"GlobeAudio: A Multilingual Multicultural Benchmark for Naturalistic Evaluation of Large Audio-Language Models","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WL42RQ7ZYVX2GT7PLVJA5HXISQ","json":"https://pith.science/pith/WL42RQ7ZYVX2GT7PLVJA5HXISQ.json","graph_json":"https://pith.science/api/pith-number/WL42RQ7ZYVX2GT7PLVJA5HXISQ/graph.json","events_json":"https://pith.science/api/pith-number/WL42RQ7ZYVX2GT7PLVJA5HXISQ/events.json","paper":"https://pith.science/paper/WL42RQ7Z"},"agent_actions":{"view_html":"https://pith.science/pith/WL42RQ7ZYVX2GT7PLVJA5HXISQ","download_json":"https://pith.science/pith/WL42RQ7ZYVX2GT7PLVJA5HXISQ.json","view_paper":"https://pith.science/paper/WL42RQ7Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08400&json=true","fetch_graph":"https://pith.science/api/pith-number/WL42RQ7ZYVX2GT7PLVJA5HXISQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WL42RQ7ZYVX2GT7PLVJA5HXISQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WL42RQ7ZYVX2GT7PLVJA5HXISQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WL42RQ7ZYVX2GT7PLVJA5HXISQ/action/storage_attestation","attest_author":"https://pith.science/pith/WL42RQ7ZYVX2GT7PLVJA5HXISQ/action/author_attestation","sign_citation":"https://pith.science/pith/WL42RQ7ZYVX2GT7PLVJA5HXISQ/action/citation_signature","submit_replication":"https://pith.science/pith/WL42RQ7ZYVX2GT7PLVJA5HXISQ/action/replication_record"}},"created_at":"2026-07-05T12:00:02.101594+00:00","updated_at":"2026-07-05T12:00:02.101594+00:00"}