{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ACDRMG47ITXLVTTBDH32RRSEWC","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":"4a1ea0c653a2945f8f10e82e10aeef21f9d862379f301d81e68d5a584062099b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T16:45:37Z","title_canon_sha256":"6ba099ea119b9383ba6f1c0bcdda0feab9fbb66a2ce4cbec4c2dc39a4ad34407"},"schema_version":"1.0","source":{"id":"2311.07463","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07463","created_at":"2026-07-05T08:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07463v2","created_at":"2026-07-05T08:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07463","created_at":"2026-07-05T08:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"ACDRMG47ITXL","created_at":"2026-07-05T08:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"ACDRMG47ITXLVTTB","created_at":"2026-07-05T08:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"ACDRMG47","created_at":"2026-07-05T08:03:45Z"}],"graph_snapshots":[{"event_id":"sha256:64fd9f7187252ada060fdc42a90c629dd15c5c3ca6d71121a7644748247099ca","target":"graph","created_at":"2026-07-05T08:03:45Z","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/2311.07463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There has been a surge in LLM evaluation research to understand LLM capabilities and limitations. However, much of this research has been confined to English, leaving LLM building and evaluation for non-English languages relatively unexplored. Several new LLMs have been introduced recently, necessitating their evaluation on non-English languages. This study aims to perform a thorough evaluation of the non-English capabilities of SoTA LLMs (GPT-3.5-Turbo, GPT-4, PaLM2, Gemini-Pro, Mistral, Llama2, and Gemma) by comparing them on the same set of multilingual datasets. Our benchmark comprises 22 ","authors_text":"Ashutosh Sathe, Divyanshu Aggarwal, Ishaan Watts, Kalika Bali, Maxamed Axmed, Millicent Ochieng, Prachi Jain, Rishav Hada, Sanchit Ahuja, Sunayana Sitaram, Varun Gumma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T16:45:37Z","title":"MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07463","kind":"arxiv","version":2},"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":"sha256:95e0cef3110cf5b36c8e6a3abb93884478b50003023fa1780575a5bfba445bd7","target":"record","created_at":"2026-07-05T08:03:45Z","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":"4a1ea0c653a2945f8f10e82e10aeef21f9d862379f301d81e68d5a584062099b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T16:45:37Z","title_canon_sha256":"6ba099ea119b9383ba6f1c0bcdda0feab9fbb66a2ce4cbec4c2dc39a4ad34407"},"schema_version":"1.0","source":{"id":"2311.07463","kind":"arxiv","version":2}},"canonical_sha256":"0087161b9f44eebace6119f7a8c644b09c518a8e83d23f474053d06dc237d0ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0087161b9f44eebace6119f7a8c644b09c518a8e83d23f474053d06dc237d0ec","first_computed_at":"2026-07-05T08:03:45.668293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:45.668293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AI07LOYTgxJjB7nbjI0Z2ji/jcuQVvKE5bgtb/htABiyuG8vTrD2n/aEQ/NOylvvprGGZCTO89eTCdcZCFe9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:45.668826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07463","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95e0cef3110cf5b36c8e6a3abb93884478b50003023fa1780575a5bfba445bd7","sha256:64fd9f7187252ada060fdc42a90c629dd15c5c3ca6d71121a7644748247099ca"],"state_sha256":"4b6547c6c9b12d2a16cbd0e7903753fa284b9d76f65365f446e891ae09890cbb"}