{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RFJUFKR3ZJZWPUTGSPJKVGDK4K","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":"5f2d429a709c62b0b840cd6494f54719d359902b347b761065cfd5a18255e973","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-07T21:49:38Z","title_canon_sha256":"0927c28916a46a0c536b14021c2e259e8ea4b5e8e5f85fbed5021170445fc2e6"},"schema_version":"1.0","source":{"id":"2310.04928","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04928","created_at":"2026-07-05T07:03:31Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04928v2","created_at":"2026-07-05T07:03:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04928","created_at":"2026-07-05T07:03:31Z"},{"alias_kind":"pith_short_12","alias_value":"RFJUFKR3ZJZW","created_at":"2026-07-05T07:03:31Z"},{"alias_kind":"pith_short_16","alias_value":"RFJUFKR3ZJZWPUTG","created_at":"2026-07-05T07:03:31Z"},{"alias_kind":"pith_short_8","alias_value":"RFJUFKR3","created_at":"2026-07-05T07:03:31Z"}],"graph_snapshots":[{"event_id":"sha256:16b61497668bf8fb173b52b75fa502536a46b1b81139cda4679ad1396146c031","target":"graph","created_at":"2026-07-05T07:03:31Z","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/2310.04928/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although large language models (LLMs) are often pre-trained on large-scale multilingual texts, their reasoning abilities and real-world knowledge are mainly evaluated based on English datasets. Assessing LLM capabilities beyond English is increasingly vital but hindered due to the lack of suitable datasets. In this work, we introduce IndoMMLU, the first multi-task language understanding benchmark for Indonesian culture and languages, which consists of questions from primary school to university entrance exams in Indonesia. By employing professional teachers, we obtain 14,981 questions across 6","authors_text":"Fajri Koto, Haonan Li, Nurul Aisyah, Timothy Baldwin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-07T21:49:38Z","title":"Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04928","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:f85d63f3f620640f3641c1e53a2f3c38bfc16500ece3701497ff009711e752a9","target":"record","created_at":"2026-07-05T07:03:31Z","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":"5f2d429a709c62b0b840cd6494f54719d359902b347b761065cfd5a18255e973","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-07T21:49:38Z","title_canon_sha256":"0927c28916a46a0c536b14021c2e259e8ea4b5e8e5f85fbed5021170445fc2e6"},"schema_version":"1.0","source":{"id":"2310.04928","kind":"arxiv","version":2}},"canonical_sha256":"895342aa3bca7367d26693d2aa986ae2bb468c61d52d156cd857004cc1f24249","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"895342aa3bca7367d26693d2aa986ae2bb468c61d52d156cd857004cc1f24249","first_computed_at":"2026-07-05T07:03:31.774499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:31.774499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pKPgScQSn7dov4L69WDkAv33PYYkcRBV6rT9n6QkDXRV+wTWMT3NPV2PVaqDiQ9U0LdupwSHAIqxQ9UaA35qDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:31.774929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.04928","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f85d63f3f620640f3641c1e53a2f3c38bfc16500ece3701497ff009711e752a9","sha256:16b61497668bf8fb173b52b75fa502536a46b1b81139cda4679ad1396146c031"],"state_sha256":"0d862477b66ad3c37184e4dfb7315ab865fab710bffdf16269c748a9d47f1714"}