{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LEMF5WMIJK4EKCRIHLH3NFPRR5","short_pith_number":"pith:LEMF5WMI","schema_version":"1.0","canonical_sha256":"59185ed9884ab8450a283acfb695f18f5d10bba0b82d5e9919b35c36e48520bd","source":{"kind":"arxiv","id":"2306.16636","version":1},"attestation_state":"computed","paper":{"title":"CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Wang, Jian Luan, Shuang Dong, Tianwen Wei, Wei Liu","submitted_at":"2023-06-29T02:19:50Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.16636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-29T02:19:50Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2e61103a5ce2205c356b0ff3544a1cb8c6dbcf33280da90c949759b44d5353ac","abstract_canon_sha256":"ea4813890cb407d3837eafd890bdda3ea7b9aafdf7fc2e5ffdcdd55444e1c9b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:07.451446Z","signature_b64":"IipzIUW6+7Vlurc3D5GXmPCYZ72/DUB26QFwU0l4Nh4AxCXi81i/jJxmr+6FiszJmqE2J22Qe9GUxsVjMvQ/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59185ed9884ab8450a283acfb695f18f5d10bba0b82d5e9919b35c36e48520bd","last_reissued_at":"2026-07-05T06:26:07.451030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:07.451030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Wang, Jian Luan, Shuang Dong, Tianwen Wei, Wei Liu","submitted_at":"2023-06-29T02:19:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16636","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.16636/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.16636","created_at":"2026-07-05T06:26:07.451088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.16636v1","created_at":"2026-07-05T06:26:07.451088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16636","created_at":"2026-07-05T06:26:07.451088+00:00"},{"alias_kind":"pith_short_12","alias_value":"LEMF5WMIJK4E","created_at":"2026-07-05T06:26:07.451088+00:00"},{"alias_kind":"pith_short_16","alias_value":"LEMF5WMIJK4EKCRI","created_at":"2026-07-05T06:26:07.451088+00:00"},{"alias_kind":"pith_short_8","alias_value":"LEMF5WMI","created_at":"2026-07-05T06:26:07.451088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17175","citing_title":"Self-Generated Error Training for Token Editing in Diffusion Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08728","citing_title":"Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery","ref_index":223,"is_internal_anchor":false},{"citing_arxiv_id":"2606.15079","citing_title":"Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00997","citing_title":"Decoding in Order-Agnostic Language Models: Chain-Rule Deviation and Uniform Spreading","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25704","citing_title":"PowLU: An Activation Function for Stable Pre-Training of LLMs","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26496","citing_title":"Dense2MoE: Pushing the Pareto Frontier of On-Device LLMs via Unified Pruning and Upcycling","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20722","citing_title":"AGPO: Adaptive Group Policy Optimization with Dual Statistical Feedback","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15593","citing_title":"Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08022","citing_title":"Capacity-Aware Mixture Law Enables Efficient LLM Data Optimization","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15745","citing_title":"LLaDA2.0: Scaling Up Diffusion Language Models to 100B","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04078","citing_title":"Validity-Calibrated Reasoning Distillation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04078","citing_title":"Validity-Calibrated Reasoning Distillation","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2507.20534","citing_title":"Kimi K2: Open Agentic Intelligence","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18738","citing_title":"Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Large Language Models","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LEMF5WMIJK4EKCRIHLH3NFPRR5","json":"https://pith.science/pith/LEMF5WMIJK4EKCRIHLH3NFPRR5.json","graph_json":"https://pith.science/api/pith-number/LEMF5WMIJK4EKCRIHLH3NFPRR5/graph.json","events_json":"https://pith.science/api/pith-number/LEMF5WMIJK4EKCRIHLH3NFPRR5/events.json","paper":"https://pith.science/paper/LEMF5WMI"},"agent_actions":{"view_html":"https://pith.science/pith/LEMF5WMIJK4EKCRIHLH3NFPRR5","download_json":"https://pith.science/pith/LEMF5WMIJK4EKCRIHLH3NFPRR5.json","view_paper":"https://pith.science/paper/LEMF5WMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.16636&json=true","fetch_graph":"https://pith.science/api/pith-number/LEMF5WMIJK4EKCRIHLH3NFPRR5/graph.json","fetch_events":"https://pith.science/api/pith-number/LEMF5WMIJK4EKCRIHLH3NFPRR5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LEMF5WMIJK4EKCRIHLH3NFPRR5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LEMF5WMIJK4EKCRIHLH3NFPRR5/action/storage_attestation","attest_author":"https://pith.science/pith/LEMF5WMIJK4EKCRIHLH3NFPRR5/action/author_attestation","sign_citation":"https://pith.science/pith/LEMF5WMIJK4EKCRIHLH3NFPRR5/action/citation_signature","submit_replication":"https://pith.science/pith/LEMF5WMIJK4EKCRIHLH3NFPRR5/action/replication_record"}},"created_at":"2026-07-05T06:26:07.451088+00:00","updated_at":"2026-07-05T06:26:07.451088+00:00"}