{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WL42RQ7ZYVX2GT7PLVJA5HXISQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a550a2392bf66e8595be025e4cddfd32aa12b8c1e29572790af2e8b00aeee296","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T03:15:08Z","title_canon_sha256":"01ea2f7b382c5d00b388ba26ae5d2a80cfb51aa39b8c2cd3f47dd612a6f712dd"},"schema_version":"1.0","source":{"id":"2506.08400","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08400","created_at":"2026-07-05T12:00:02Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08400v3","created_at":"2026-07-05T12:00:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08400","created_at":"2026-07-05T12:00:02Z"},{"alias_kind":"pith_short_12","alias_value":"WL42RQ7ZYVX2","created_at":"2026-07-05T12:00:02Z"},{"alias_kind":"pith_short_16","alias_value":"WL42RQ7ZYVX2GT7P","created_at":"2026-07-05T12:00:02Z"},{"alias_kind":"pith_short_8","alias_value":"WL42RQ7Z","created_at":"2026-07-05T12:00:02Z"}],"graph_snapshots":[{"event_id":"sha256:babad84478dff00f38a419a3af0bfe788fd9d0aefe46acc168a8f461b5990a54","target":"graph","created_at":"2026-07-05T12:00:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.08400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David Ifeoluwa Adelani, Fabian David Schmidt, Jesujoba O. Alabi, Joyce Nakatumba-Nabende, Luel Hagos Beyene, Min Ma, Vivek Verma","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T03:15:08Z","title":"mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08400","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:437eb276eb937297d9ebae34bf6e20f477235d6c1ed01c2e00b5b634946d9762","target":"record","created_at":"2026-07-05T12:00:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a550a2392bf66e8595be025e4cddfd32aa12b8c1e29572790af2e8b00aeee296","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T03:15:08Z","title_canon_sha256":"01ea2f7b382c5d00b388ba26ae5d2a80cfb51aa39b8c2cd3f47dd612a6f712dd"},"schema_version":"1.0","source":{"id":"2506.08400","kind":"arxiv","version":3}},"canonical_sha256":"b2f9a8c3f9c56fa34fef5d520e9ee89431b7fe0b9c7c6c718a70b6d8c21d0c7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2f9a8c3f9c56fa34fef5d520e9ee89431b7fe0b9c7c6c718a70b6d8c21d0c7e","first_computed_at":"2026-07-05T12:00:02.101535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:02.101535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3e6NypkUgo4aaG3xOi8AzH+T/svE2EwFtzK98ybwK74DGktkuscA0D/gi8GCGzYdx4SqaTsAa3K/TtzSeD0sBg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:02.102122Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08400","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:437eb276eb937297d9ebae34bf6e20f477235d6c1ed01c2e00b5b634946d9762","sha256:babad84478dff00f38a419a3af0bfe788fd9d0aefe46acc168a8f461b5990a54"],"state_sha256":"043066f5ec1ea75ca65fb811a239e5754cb369460b2c866aa2f5a1cd7725df85"}