{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6K5QI4RBVOLPRR3YK6YL7WYHS3","short_pith_number":"pith:6K5QI4RB","schema_version":"1.0","canonical_sha256":"f2bb047221ab96f8c77857b0bfdb0796e57fb6929fe30dcecddd843a70b81c11","source":{"kind":"arxiv","id":"2401.06961","version":2},"attestation_state":"computed","paper":{"title":"CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Yilun Zhou, Yoon Kim, Yujun Mao","submitted_at":"2024-01-13T03:18:16Z","abstract_excerpt":"Recent large language models (LLMs) have shown indications of mathematical reasoning ability on challenging competition-level problems, especially with self-generated verbalizations of intermediate reasoning steps (i.e., chain-of-thought prompting). However, current evaluations mainly focus on the end-to-end final answer correctness, and it is unclear whether LLMs can make use of helpful side information such as problem-specific hints. In this paper, we propose a challenging benchmark dataset for enabling such analyses. The Concept and Hint-Annotated Math Problems (CHAMP) consists of high scho"},"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":"2401.06961","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T03:18:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"63ae94aca07a92257011b5ea3fba1fccc6d2fa01faf5cd9c37553a9f1a9ec865","abstract_canon_sha256":"6c4cb375442bba73543bfc6d553deaac345fdfb3b6e07049c95df34ac66e6081"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:20.199595Z","signature_b64":"RSyAh7TsqCjh6MGZrRtIZfHFimw4yGSau+3crgL3gHXRLyTjJcf6FjUkSk9wE53l7jp4r/u9IXmTfuuSrp6RAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2bb047221ab96f8c77857b0bfdb0796e57fb6929fe30dcecddd843a70b81c11","last_reissued_at":"2026-07-05T08:29:20.199170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:20.199170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Yilun Zhou, Yoon Kim, Yujun Mao","submitted_at":"2024-01-13T03:18:16Z","abstract_excerpt":"Recent large language models (LLMs) have shown indications of mathematical reasoning ability on challenging competition-level problems, especially with self-generated verbalizations of intermediate reasoning steps (i.e., chain-of-thought prompting). However, current evaluations mainly focus on the end-to-end final answer correctness, and it is unclear whether LLMs can make use of helpful side information such as problem-specific hints. In this paper, we propose a challenging benchmark dataset for enabling such analyses. The Concept and Hint-Annotated Math Problems (CHAMP) consists of high scho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06961","kind":"arxiv","version":2},"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/2401.06961/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":"2401.06961","created_at":"2026-07-05T08:29:20.199224+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.06961v2","created_at":"2026-07-05T08:29:20.199224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06961","created_at":"2026-07-05T08:29:20.199224+00:00"},{"alias_kind":"pith_short_12","alias_value":"6K5QI4RBVOLP","created_at":"2026-07-05T08:29:20.199224+00:00"},{"alias_kind":"pith_short_16","alias_value":"6K5QI4RBVOLPRR3Y","created_at":"2026-07-05T08:29:20.199224+00:00"},{"alias_kind":"pith_short_8","alias_value":"6K5QI4RB","created_at":"2026-07-05T08:29:20.199224+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.22693","citing_title":"Bridging Language Models and Financial Analysis","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2410.07985","citing_title":"Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6K5QI4RBVOLPRR3YK6YL7WYHS3","json":"https://pith.science/pith/6K5QI4RBVOLPRR3YK6YL7WYHS3.json","graph_json":"https://pith.science/api/pith-number/6K5QI4RBVOLPRR3YK6YL7WYHS3/graph.json","events_json":"https://pith.science/api/pith-number/6K5QI4RBVOLPRR3YK6YL7WYHS3/events.json","paper":"https://pith.science/paper/6K5QI4RB"},"agent_actions":{"view_html":"https://pith.science/pith/6K5QI4RBVOLPRR3YK6YL7WYHS3","download_json":"https://pith.science/pith/6K5QI4RBVOLPRR3YK6YL7WYHS3.json","view_paper":"https://pith.science/paper/6K5QI4RB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.06961&json=true","fetch_graph":"https://pith.science/api/pith-number/6K5QI4RBVOLPRR3YK6YL7WYHS3/graph.json","fetch_events":"https://pith.science/api/pith-number/6K5QI4RBVOLPRR3YK6YL7WYHS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6K5QI4RBVOLPRR3YK6YL7WYHS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6K5QI4RBVOLPRR3YK6YL7WYHS3/action/storage_attestation","attest_author":"https://pith.science/pith/6K5QI4RBVOLPRR3YK6YL7WYHS3/action/author_attestation","sign_citation":"https://pith.science/pith/6K5QI4RBVOLPRR3YK6YL7WYHS3/action/citation_signature","submit_replication":"https://pith.science/pith/6K5QI4RBVOLPRR3YK6YL7WYHS3/action/replication_record"}},"created_at":"2026-07-05T08:29:20.199224+00:00","updated_at":"2026-07-05T08:29:20.199224+00:00"}