{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3TVZLTPSMHDBGT6QI4TFN2EWXE","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":"9dab3b5c58720012776d71be953cc75040f8292a71e688f3dce333a1aff21d87","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T14:58:38Z","title_canon_sha256":"70910d3db0b4c695a91da3f48c219881f6d10716eed830d33f38bf0b3ec85582"},"schema_version":"1.0","source":{"id":"2411.09492","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09492","created_at":"2026-07-05T09:35:27Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09492v1","created_at":"2026-07-05T09:35:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09492","created_at":"2026-07-05T09:35:27Z"},{"alias_kind":"pith_short_12","alias_value":"3TVZLTPSMHDB","created_at":"2026-07-05T09:35:27Z"},{"alias_kind":"pith_short_16","alias_value":"3TVZLTPSMHDBGT6Q","created_at":"2026-07-05T09:35:27Z"},{"alias_kind":"pith_short_8","alias_value":"3TVZLTPS","created_at":"2026-07-05T09:35:27Z"}],"graph_snapshots":[{"event_id":"sha256:dfd42cbf1cb41f2efc2113574567cbf9ab15534ff6b012097599102c616e6208","target":"graph","created_at":"2026-07-05T09:35:27Z","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/2411.09492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) excel in high-resource languages but face notable challenges in low-resource languages like Mongolian. This paper addresses these challenges by categorizing capabilities into language abilities (syntax and semantics) and cognitive abilities (knowledge and reasoning). To systematically evaluate these areas, we developed MM-Eval, a specialized dataset based on Modern Mongolian Language Textbook I and enriched with WebQSP and MGSM datasets.\n  Preliminary experiments on models including Qwen2-7B-Instruct, GLM4-9b-chat, Llama3.1-8B-Instruct, GPT-4, and DeepseekV2.5 reve","authors_text":"Bo Xia, Mengyuan Zhang, Ruihui Wang, Xiaobing Zhao, Yuan Sun","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T14:58:38Z","title":"MM-Eval: A Hierarchical Benchmark for Modern Mongolian Evaluation in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09492","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":"sha256:6b44cd59f80aa27b8372f0d45106fe2a37cf372bc668f0812561bb871426d6a7","target":"record","created_at":"2026-07-05T09:35:27Z","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":"9dab3b5c58720012776d71be953cc75040f8292a71e688f3dce333a1aff21d87","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T14:58:38Z","title_canon_sha256":"70910d3db0b4c695a91da3f48c219881f6d10716eed830d33f38bf0b3ec85582"},"schema_version":"1.0","source":{"id":"2411.09492","kind":"arxiv","version":1}},"canonical_sha256":"dceb95cdf261c6134fd0472656e896b90bd01a8e1d69446623db7a569e68f011","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dceb95cdf261c6134fd0472656e896b90bd01a8e1d69446623db7a569e68f011","first_computed_at":"2026-07-05T09:35:27.757538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:27.757538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VcQijU/uOv7KQ4S8JHm+8uG6WGahhSIN3WSatHEcu8mz0p4eiGXyZKRx0l4bi+rEjajf02kqCoGGWXURQQXAAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:27.757984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.09492","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b44cd59f80aa27b8372f0d45106fe2a37cf372bc668f0812561bb871426d6a7","sha256:dfd42cbf1cb41f2efc2113574567cbf9ab15534ff6b012097599102c616e6208"],"state_sha256":"87ad2ec704d839b19a6d2e6600b448d2e8ce03a4dac81fe0362023a496c3c43d"}