{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MRTEPNNEXIV3BUUV75EQ7KDQ3W","short_pith_number":"pith:MRTEPNNE","schema_version":"1.0","canonical_sha256":"646647b5a4ba2bb0d295ff490fa870dd81f8febf1eb9f81771f2889eb880eeb4","source":{"kind":"arxiv","id":"2606.10254","version":1},"attestation_state":"computed","paper":{"title":"RealMath-Eval: Why SOTA Judges Struggle with Real Human Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jianlong Chen, Kenan Xu, Wenhao Li, Xiangfeng Wang, Yijia Lyu, Yiteng Mao","submitted_at":"2026-06-08T23:40:34Z","abstract_excerpt":"While Large Language Models (LLMs) have achieved near-perfect performance in \\emph{solving} high-school mathematics, their ability to \\emph{evaluate} the diverse reasoning processes of real human students remains under-examined. To bridge this gap, we introduce \\textbf{RealMath-Eval}, a rigorously annotated benchmark of 224 real-world exam responses from high schools. Our initial evaluation reveals that even state-of-the-art LLM judges struggle significantly on this task, exhibiting a high Mean Squared Error ($\\sim$2.96) against expert human grading. To probe a plausible explanation, we contra"},"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":"2606.10254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T23:40:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"44d46051b152254972ed858bf43bf6580c737c2977e87126a857ee3283a3119f","abstract_canon_sha256":"70d1faec6367d8a596a0eb31eb9840963eef09c6ca2a3b3bd9cd04eba21b8df8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:02.742049Z","signature_b64":"+sbiOFKaKxT5Ijve/S5QXdFqetHP3Mn2eNHjQrUDLvB5P5wJomqETiNIQk9vMIiGiVDGCUdaS7y2HyOnblCCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"646647b5a4ba2bb0d295ff490fa870dd81f8febf1eb9f81771f2889eb880eeb4","last_reissued_at":"2026-06-10T01:09:02.741200Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:02.741200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RealMath-Eval: Why SOTA Judges Struggle with Real Human Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jianlong Chen, Kenan Xu, Wenhao Li, Xiangfeng Wang, Yijia Lyu, Yiteng Mao","submitted_at":"2026-06-08T23:40:34Z","abstract_excerpt":"While Large Language Models (LLMs) have achieved near-perfect performance in \\emph{solving} high-school mathematics, their ability to \\emph{evaluate} the diverse reasoning processes of real human students remains under-examined. To bridge this gap, we introduce \\textbf{RealMath-Eval}, a rigorously annotated benchmark of 224 real-world exam responses from high schools. Our initial evaluation reveals that even state-of-the-art LLM judges struggle significantly on this task, exhibiting a high Mean Squared Error ($\\sim$2.96) against expert human grading. To probe a plausible explanation, we contra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10254","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/2606.10254/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":"2606.10254","created_at":"2026-06-10T01:09:02.741350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10254v1","created_at":"2026-06-10T01:09:02.741350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10254","created_at":"2026-06-10T01:09:02.741350+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRTEPNNEXIV3","created_at":"2026-06-10T01:09:02.741350+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRTEPNNEXIV3BUUV","created_at":"2026-06-10T01:09:02.741350+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRTEPNNE","created_at":"2026-06-10T01:09:02.741350+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/MRTEPNNEXIV3BUUV75EQ7KDQ3W","json":"https://pith.science/pith/MRTEPNNEXIV3BUUV75EQ7KDQ3W.json","graph_json":"https://pith.science/api/pith-number/MRTEPNNEXIV3BUUV75EQ7KDQ3W/graph.json","events_json":"https://pith.science/api/pith-number/MRTEPNNEXIV3BUUV75EQ7KDQ3W/events.json","paper":"https://pith.science/paper/MRTEPNNE"},"agent_actions":{"view_html":"https://pith.science/pith/MRTEPNNEXIV3BUUV75EQ7KDQ3W","download_json":"https://pith.science/pith/MRTEPNNEXIV3BUUV75EQ7KDQ3W.json","view_paper":"https://pith.science/paper/MRTEPNNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10254&json=true","fetch_graph":"https://pith.science/api/pith-number/MRTEPNNEXIV3BUUV75EQ7KDQ3W/graph.json","fetch_events":"https://pith.science/api/pith-number/MRTEPNNEXIV3BUUV75EQ7KDQ3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRTEPNNEXIV3BUUV75EQ7KDQ3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRTEPNNEXIV3BUUV75EQ7KDQ3W/action/storage_attestation","attest_author":"https://pith.science/pith/MRTEPNNEXIV3BUUV75EQ7KDQ3W/action/author_attestation","sign_citation":"https://pith.science/pith/MRTEPNNEXIV3BUUV75EQ7KDQ3W/action/citation_signature","submit_replication":"https://pith.science/pith/MRTEPNNEXIV3BUUV75EQ7KDQ3W/action/replication_record"}},"created_at":"2026-06-10T01:09:02.741350+00:00","updated_at":"2026-06-10T01:09:02.741350+00:00"}