{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MRTEPNNEXIV3BUUV75EQ7KDQ3W","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":"70d1faec6367d8a596a0eb31eb9840963eef09c6ca2a3b3bd9cd04eba21b8df8","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T23:40:34Z","title_canon_sha256":"44d46051b152254972ed858bf43bf6580c737c2977e87126a857ee3283a3119f"},"schema_version":"1.0","source":{"id":"2606.10254","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10254","created_at":"2026-06-10T01:09:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10254v1","created_at":"2026-06-10T01:09:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10254","created_at":"2026-06-10T01:09:02Z"},{"alias_kind":"pith_short_12","alias_value":"MRTEPNNEXIV3","created_at":"2026-06-10T01:09:02Z"},{"alias_kind":"pith_short_16","alias_value":"MRTEPNNEXIV3BUUV","created_at":"2026-06-10T01:09:02Z"},{"alias_kind":"pith_short_8","alias_value":"MRTEPNNE","created_at":"2026-06-10T01:09:02Z"}],"graph_snapshots":[{"event_id":"sha256:ea59aa85b408c11959b1c28ea937084cddf792c06dc3f3d94a1179648486704b","target":"graph","created_at":"2026-06-10T01:09:02Z","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/2606.10254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jianlong Chen, Kenan Xu, Wenhao Li, Xiangfeng Wang, Yijia Lyu, Yiteng Mao","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T23:40:34Z","title":"RealMath-Eval: Why SOTA Judges Struggle with Real Human Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10254","kind":"arxiv","version":1},"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:b047b4d930b11965f35a002662c81dbfed94b051e9882ff989812840f3fcc9c9","target":"record","created_at":"2026-06-10T01:09:02Z","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":"70d1faec6367d8a596a0eb31eb9840963eef09c6ca2a3b3bd9cd04eba21b8df8","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T23:40:34Z","title_canon_sha256":"44d46051b152254972ed858bf43bf6580c737c2977e87126a857ee3283a3119f"},"schema_version":"1.0","source":{"id":"2606.10254","kind":"arxiv","version":1}},"canonical_sha256":"646647b5a4ba2bb0d295ff490fa870dd81f8febf1eb9f81771f2889eb880eeb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"646647b5a4ba2bb0d295ff490fa870dd81f8febf1eb9f81771f2889eb880eeb4","first_computed_at":"2026-06-10T01:09:02.741200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:09:02.741200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+sbiOFKaKxT5Ijve/S5QXdFqetHP3Mn2eNHjQrUDLvB5P5wJomqETiNIQk9vMIiGiVDGCUdaS7y2HyOnblCCCQ==","signature_status":"signed_v1","signed_at":"2026-06-10T01:09:02.742049Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10254","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b047b4d930b11965f35a002662c81dbfed94b051e9882ff989812840f3fcc9c9","sha256:ea59aa85b408c11959b1c28ea937084cddf792c06dc3f3d94a1179648486704b"],"state_sha256":"40d70e3721d40e9b237dd3df91eb403c92f16af2897104f48a0190dd3f31dd8a"}