{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6K5QI4RBVOLPRR3YK6YL7WYHS3","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":"6c4cb375442bba73543bfc6d553deaac345fdfb3b6e07049c95df34ac66e6081","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T03:18:16Z","title_canon_sha256":"63ae94aca07a92257011b5ea3fba1fccc6d2fa01faf5cd9c37553a9f1a9ec865"},"schema_version":"1.0","source":{"id":"2401.06961","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06961","created_at":"2026-07-05T08:29:20Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06961v2","created_at":"2026-07-05T08:29:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06961","created_at":"2026-07-05T08:29:20Z"},{"alias_kind":"pith_short_12","alias_value":"6K5QI4RBVOLP","created_at":"2026-07-05T08:29:20Z"},{"alias_kind":"pith_short_16","alias_value":"6K5QI4RBVOLPRR3Y","created_at":"2026-07-05T08:29:20Z"},{"alias_kind":"pith_short_8","alias_value":"6K5QI4RB","created_at":"2026-07-05T08:29:20Z"}],"graph_snapshots":[{"event_id":"sha256:9de424b22184c63f9724fd068ae83f148db473765f1e036841194bae3fcb14dc","target":"graph","created_at":"2026-07-05T08:29:20Z","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/2401.06961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Yilun Zhou, Yoon Kim, Yujun Mao","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T03:18:16Z","title":"CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06961","kind":"arxiv","version":2},"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:adb690a1a36bad8bb442825900b8b6148747e182738b137a6db062d4233c1fb6","target":"record","created_at":"2026-07-05T08:29:20Z","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":"6c4cb375442bba73543bfc6d553deaac345fdfb3b6e07049c95df34ac66e6081","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T03:18:16Z","title_canon_sha256":"63ae94aca07a92257011b5ea3fba1fccc6d2fa01faf5cd9c37553a9f1a9ec865"},"schema_version":"1.0","source":{"id":"2401.06961","kind":"arxiv","version":2}},"canonical_sha256":"f2bb047221ab96f8c77857b0bfdb0796e57fb6929fe30dcecddd843a70b81c11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2bb047221ab96f8c77857b0bfdb0796e57fb6929fe30dcecddd843a70b81c11","first_computed_at":"2026-07-05T08:29:20.199170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:20.199170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RSyAh7TsqCjh6MGZrRtIZfHFimw4yGSau+3crgL3gHXRLyTjJcf6FjUkSk9wE53l7jp4r/u9IXmTfuuSrp6RAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:20.199595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06961","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adb690a1a36bad8bb442825900b8b6148747e182738b137a6db062d4233c1fb6","sha256:9de424b22184c63f9724fd068ae83f148db473765f1e036841194bae3fcb14dc"],"state_sha256":"d0d8617de99f410817d16437d5bbd6892db57310fda27c4be4c5894270bb5aad"}