{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7AIMDSR3YQHUQXRIODV3DMSSDN","short_pith_number":"pith:7AIMDSR3","schema_version":"1.0","canonical_sha256":"f810c1ca3bc40f485e2870ebb1b2521b719d7e1aa7ce504be418f70254807925","source":{"kind":"arxiv","id":"2506.04481","version":1},"attestation_state":"computed","paper":{"title":"CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng cheng, Enhong Chen, Jiayu Liu, Jing Sha, Jinze Wu, Qi Liu, Shijin Wang, Song Li, Wei Dai, Zhenya Huang","submitted_at":"2025-06-04T22:00:52Z","abstract_excerpt":"Although large language models (LLMs) show promise in solving complex mathematical tasks, existing evaluation paradigms rely solely on a coarse measure of overall answer accuracy, which are insufficient for assessing their authentic capabilities. In this paper, we propose \\textbf{CogMath}, which comprehensively assesses LLMs' mathematical abilities through the lens of human cognition. Specifically, inspired by psychological theories, CogMath formalizes human reasoning process into 3 stages: \\emph{problem comprehension}, \\emph{problem solving}, and \\emph{solution summarization}. Within these st"},"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":"2506.04481","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-04T22:00:52Z","cross_cats_sorted":[],"title_canon_sha256":"8bee0379d9e0076b96cd90828f029e95a62f3744fdcafef37a8d147b9c4968dd","abstract_canon_sha256":"df3cbfe0b9a51cfe39088dc3171c204c1d0f318a86a36c58f4af56bd22ef98ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:15.295054Z","signature_b64":"Y1uYo7aZLMRpGwMRfcJ+WK0FYIuiPBBDmYIyXvHqc3djNkcSPkvlSBTgEhICRmQUZQrPbA3yBP8dkLR7XP+RBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f810c1ca3bc40f485e2870ebb1b2521b719d7e1aa7ce504be418f70254807925","last_reissued_at":"2026-07-05T11:16:15.294569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:15.294569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng cheng, Enhong Chen, Jiayu Liu, Jing Sha, Jinze Wu, Qi Liu, Shijin Wang, Song Li, Wei Dai, Zhenya Huang","submitted_at":"2025-06-04T22:00:52Z","abstract_excerpt":"Although large language models (LLMs) show promise in solving complex mathematical tasks, existing evaluation paradigms rely solely on a coarse measure of overall answer accuracy, which are insufficient for assessing their authentic capabilities. In this paper, we propose \\textbf{CogMath}, which comprehensively assesses LLMs' mathematical abilities through the lens of human cognition. Specifically, inspired by psychological theories, CogMath formalizes human reasoning process into 3 stages: \\emph{problem comprehension}, \\emph{problem solving}, and \\emph{solution summarization}. Within these st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04481","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/2506.04481/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":"2506.04481","created_at":"2026-07-05T11:16:15.294633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04481v1","created_at":"2026-07-05T11:16:15.294633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04481","created_at":"2026-07-05T11:16:15.294633+00:00"},{"alias_kind":"pith_short_12","alias_value":"7AIMDSR3YQHU","created_at":"2026-07-05T11:16:15.294633+00:00"},{"alias_kind":"pith_short_16","alias_value":"7AIMDSR3YQHUQXRI","created_at":"2026-07-05T11:16:15.294633+00:00"},{"alias_kind":"pith_short_8","alias_value":"7AIMDSR3","created_at":"2026-07-05T11:16:15.294633+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7AIMDSR3YQHUQXRIODV3DMSSDN","json":"https://pith.science/pith/7AIMDSR3YQHUQXRIODV3DMSSDN.json","graph_json":"https://pith.science/api/pith-number/7AIMDSR3YQHUQXRIODV3DMSSDN/graph.json","events_json":"https://pith.science/api/pith-number/7AIMDSR3YQHUQXRIODV3DMSSDN/events.json","paper":"https://pith.science/paper/7AIMDSR3"},"agent_actions":{"view_html":"https://pith.science/pith/7AIMDSR3YQHUQXRIODV3DMSSDN","download_json":"https://pith.science/pith/7AIMDSR3YQHUQXRIODV3DMSSDN.json","view_paper":"https://pith.science/paper/7AIMDSR3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04481&json=true","fetch_graph":"https://pith.science/api/pith-number/7AIMDSR3YQHUQXRIODV3DMSSDN/graph.json","fetch_events":"https://pith.science/api/pith-number/7AIMDSR3YQHUQXRIODV3DMSSDN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7AIMDSR3YQHUQXRIODV3DMSSDN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7AIMDSR3YQHUQXRIODV3DMSSDN/action/storage_attestation","attest_author":"https://pith.science/pith/7AIMDSR3YQHUQXRIODV3DMSSDN/action/author_attestation","sign_citation":"https://pith.science/pith/7AIMDSR3YQHUQXRIODV3DMSSDN/action/citation_signature","submit_replication":"https://pith.science/pith/7AIMDSR3YQHUQXRIODV3DMSSDN/action/replication_record"}},"created_at":"2026-07-05T11:16:15.294633+00:00","updated_at":"2026-07-05T11:16:15.294633+00:00"}