{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J2ZGI2I7DGVP5K67PW5E6TWIZP","short_pith_number":"pith:J2ZGI2I7","schema_version":"1.0","canonical_sha256":"4eb264691f19aafeabdf7dba4f4ec8cbe0379872c8867d9f10848de6de3c33c2","source":{"kind":"arxiv","id":"2304.02015","version":1},"attestation_state":"computed","paper":{"title":"How well do Large Language Models perform in Arithmetic tasks?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuanqi Tan, Hongyi Yuan, Songfang Huang, Wei Wang, Zheng Yuan","submitted_at":"2023-03-16T09:28:15Z","abstract_excerpt":"Large language models have emerged abilities including chain-of-thought to answer math word problems step by step. Solving math word problems not only requires abilities to disassemble problems via chain-of-thought but also needs to calculate arithmetic expressions correctly for each step. To the best of our knowledge, there is no work to focus on evaluating the arithmetic ability of large language models. In this work, we propose an arithmetic dataset MATH 401 to test the latest large language models including GPT-4, ChatGPT, InstrctGPT, Galactica, and LLaMA with various arithmetic expression"},"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":"2304.02015","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-16T09:28:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0cc23cc2ccf485a8080603358ed8d08a1c81bbb24a5d918394c5a98323ada7e9","abstract_canon_sha256":"db31b758088e5e9a3fa0f96de54eebf93899ff6fa592c4cf06a6227c633cacfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:21.152426Z","signature_b64":"QEwARQ67CmmjOiCxYktFPl2Lhxu2ONkMuo5BEpFKcEfLZeYs0LYO+clZ3vm/nDRe2bEICCWc5GlFRdxUlYByCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eb264691f19aafeabdf7dba4f4ec8cbe0379872c8867d9f10848de6de3c33c2","last_reissued_at":"2026-07-05T05:58:21.151931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:21.151931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How well do Large Language Models perform in Arithmetic tasks?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuanqi Tan, Hongyi Yuan, Songfang Huang, Wei Wang, Zheng Yuan","submitted_at":"2023-03-16T09:28:15Z","abstract_excerpt":"Large language models have emerged abilities including chain-of-thought to answer math word problems step by step. Solving math word problems not only requires abilities to disassemble problems via chain-of-thought but also needs to calculate arithmetic expressions correctly for each step. To the best of our knowledge, there is no work to focus on evaluating the arithmetic ability of large language models. In this work, we propose an arithmetic dataset MATH 401 to test the latest large language models including GPT-4, ChatGPT, InstrctGPT, Galactica, and LLaMA with various arithmetic expression"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02015","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/2304.02015/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":"2304.02015","created_at":"2026-07-05T05:58:21.151989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.02015v1","created_at":"2026-07-05T05:58:21.151989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02015","created_at":"2026-07-05T05:58:21.151989+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2ZGI2I7DGVP","created_at":"2026-07-05T05:58:21.151989+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2ZGI2I7DGVP5K67","created_at":"2026-07-05T05:58:21.151989+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2ZGI2I7","created_at":"2026-07-05T05:58:21.151989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03645","citing_title":"The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20369","citing_title":"DEL: Digit Entropy Loss for Numerical Learning of Large Language Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2308.01825","citing_title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18203","citing_title":"Multiplication in Multimodal LLMs: Computation with Text, Image, and Audio Inputs","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13533","citing_title":"Evolvable Embodied Agent for Robotic Manipulation via Long Short-Term Reflection and Optimization","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP","json":"https://pith.science/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP.json","graph_json":"https://pith.science/api/pith-number/J2ZGI2I7DGVP5K67PW5E6TWIZP/graph.json","events_json":"https://pith.science/api/pith-number/J2ZGI2I7DGVP5K67PW5E6TWIZP/events.json","paper":"https://pith.science/paper/J2ZGI2I7"},"agent_actions":{"view_html":"https://pith.science/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP","download_json":"https://pith.science/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP.json","view_paper":"https://pith.science/paper/J2ZGI2I7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.02015&json=true","fetch_graph":"https://pith.science/api/pith-number/J2ZGI2I7DGVP5K67PW5E6TWIZP/graph.json","fetch_events":"https://pith.science/api/pith-number/J2ZGI2I7DGVP5K67PW5E6TWIZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP/action/storage_attestation","attest_author":"https://pith.science/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP/action/author_attestation","sign_citation":"https://pith.science/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP/action/citation_signature","submit_replication":"https://pith.science/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP/action/replication_record"}},"created_at":"2026-07-05T05:58:21.151989+00:00","updated_at":"2026-07-05T05:58:21.151989+00:00"}