{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LEMF5WMIJK4EKCRIHLH3NFPRR5","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":"ea4813890cb407d3837eafd890bdda3ea7b9aafdf7fc2e5ffdcdd55444e1c9b8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-29T02:19:50Z","title_canon_sha256":"2e61103a5ce2205c356b0ff3544a1cb8c6dbcf33280da90c949759b44d5353ac"},"schema_version":"1.0","source":{"id":"2306.16636","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.16636","created_at":"2026-07-05T06:26:07Z"},{"alias_kind":"arxiv_version","alias_value":"2306.16636v1","created_at":"2026-07-05T06:26:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16636","created_at":"2026-07-05T06:26:07Z"},{"alias_kind":"pith_short_12","alias_value":"LEMF5WMIJK4E","created_at":"2026-07-05T06:26:07Z"},{"alias_kind":"pith_short_16","alias_value":"LEMF5WMIJK4EKCRI","created_at":"2026-07-05T06:26:07Z"},{"alias_kind":"pith_short_8","alias_value":"LEMF5WMI","created_at":"2026-07-05T06:26:07Z"}],"graph_snapshots":[{"event_id":"sha256:49fa4c82876881a827f074739498878b6c4f5cf771b5af3a03afca311df92fab","target":"graph","created_at":"2026-07-05T06:26:07Z","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/2306.16636/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the Chinese Elementary School Math Word Problems (CMATH) dataset, comprising 1.7k elementary school-level math word problems with detailed annotations, source from actual Chinese workbooks and exams. This dataset aims to provide a benchmark tool for assessing the following question: to what grade level of elementary school math do the abilities of popular large language models (LLMs) correspond? We evaluate a variety of popular LLMs, including both commercial and open-source options, and discover that only GPT-4 achieves success (accuracy $\\geq$ 60\\%) across all six elementary schoo","authors_text":"Bin Wang, Jian Luan, Shuang Dong, Tianwen Wei, Wei Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-29T02:19:50Z","title":"CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16636","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":"sha256:08587a4b04286d221855e21528c48ffed93d9f26f1a815c12e3e775b06a23833","target":"record","created_at":"2026-07-05T06:26:07Z","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":"ea4813890cb407d3837eafd890bdda3ea7b9aafdf7fc2e5ffdcdd55444e1c9b8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-29T02:19:50Z","title_canon_sha256":"2e61103a5ce2205c356b0ff3544a1cb8c6dbcf33280da90c949759b44d5353ac"},"schema_version":"1.0","source":{"id":"2306.16636","kind":"arxiv","version":1}},"canonical_sha256":"59185ed9884ab8450a283acfb695f18f5d10bba0b82d5e9919b35c36e48520bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59185ed9884ab8450a283acfb695f18f5d10bba0b82d5e9919b35c36e48520bd","first_computed_at":"2026-07-05T06:26:07.451030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:07.451030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IipzIUW6+7Vlurc3D5GXmPCYZ72/DUB26QFwU0l4Nh4AxCXi81i/jJxmr+6FiszJmqE2J22Qe9GUxsVjMvQ/CA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:07.451446Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.16636","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08587a4b04286d221855e21528c48ffed93d9f26f1a815c12e3e775b06a23833","sha256:49fa4c82876881a827f074739498878b6c4f5cf771b5af3a03afca311df92fab"],"state_sha256":"ee6a6b3f488741e1a11820b4387931f025e3c2e48ee0b3c86e6ddd8321758dae"}