{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YI3ZOHVZZ6M3O2AQ3IJ33VG6AX","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":"d494d9709a2a06a056a9fcbae0dde242f972a3f228edcd1c6bbd76e8a43bcb74","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T12:38:02Z","title_canon_sha256":"a2333a3a8881ce8b002c4d2788b3e04d9ddfc58646dd5fec54ab676c890c416d"},"schema_version":"1.0","source":{"id":"2507.08538","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08538","created_at":"2026-07-05T11:35:41Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08538v1","created_at":"2026-07-05T11:35:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08538","created_at":"2026-07-05T11:35:41Z"},{"alias_kind":"pith_short_12","alias_value":"YI3ZOHVZZ6M3","created_at":"2026-07-05T11:35:41Z"},{"alias_kind":"pith_short_16","alias_value":"YI3ZOHVZZ6M3O2AQ","created_at":"2026-07-05T11:35:41Z"},{"alias_kind":"pith_short_8","alias_value":"YI3ZOHVZ","created_at":"2026-07-05T11:35:41Z"}],"graph_snapshots":[{"event_id":"sha256:2b6d4688771e210e1d33dad83acf119c217a6c466b77a20d5681b1ad11fc3e4e","target":"graph","created_at":"2026-07-05T11:35:41Z","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/2507.08538/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To ensure equitable access to the benefits of large language models (LLMs), it is essential to evaluate their capabilities across the world's languages. We introduce the AI Language Proficiency Monitor, a comprehensive multilingual benchmark that systematically assesses LLM performance across up to 200 languages, with a particular focus on low-resource languages. Our benchmark aggregates diverse tasks including translation, question answering, math, and reasoning, using datasets such as FLORES+, MMLU, GSM8K, TruthfulQA, and ARC. We provide an open-source, auto-updating leaderboard and dashboar","authors_text":"David Pomerenke, Jonas Nothnagel, Simon Ostermann","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T12:38:02Z","title":"The AI Language Proficiency Monitor -- Tracking the Progress of LLMs on Multilingual Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08538","kind":"arxiv","version":1},"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:a17dcc599f6fb50c72a89113406d2638f54dfc90edfe6dd7fb66e2a3a76fb610","target":"record","created_at":"2026-07-05T11:35:41Z","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":"d494d9709a2a06a056a9fcbae0dde242f972a3f228edcd1c6bbd76e8a43bcb74","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T12:38:02Z","title_canon_sha256":"a2333a3a8881ce8b002c4d2788b3e04d9ddfc58646dd5fec54ab676c890c416d"},"schema_version":"1.0","source":{"id":"2507.08538","kind":"arxiv","version":1}},"canonical_sha256":"c237971eb9cf99b76810da13bdd4de05ff42c5555cbcdcb6c56fe34349d8cc7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c237971eb9cf99b76810da13bdd4de05ff42c5555cbcdcb6c56fe34349d8cc7a","first_computed_at":"2026-07-05T11:35:41.711484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:41.711484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fVk4LZmfZ7bLloRLWHgATztSFvEDmFjTUi9qKye7M9/ToP/PzwRYv8pwPpd9BXf/26XkYEO6NScAR//X9GRCCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:41.711997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.08538","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a17dcc599f6fb50c72a89113406d2638f54dfc90edfe6dd7fb66e2a3a76fb610","sha256:2b6d4688771e210e1d33dad83acf119c217a6c466b77a20d5681b1ad11fc3e4e"],"state_sha256":"2b9d7cd508792ecf7050cfa893aec4b80e7ce4e759511155667b40b182936a48"}