{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_92ca43fb8400c09cca88fed4b2cb834690a36bf61ff3d7091f3d8642298c6ba7","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_92ca43fb8400c09cca88fed4b2cb834690a36bf61ff3d7091f3d8642298c6ba7","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"e1d06ad5495126e64a84d1397b9184ccd60eadbb74db893a5b63288e394dbae5","published":"Wed, 10 Jun 2026 00:00:00 -0400","receipt_hash":"e1d06ad5495126e64a84d1397b9184ccd60eadbb74db893a5b63288e394dbae5","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"e1d06ad5495126e64a84d1397b9184ccd60eadbb74db893a5b63288e394dbae5","observed_at":"2026-06-10T04:43:37.461885Z","parent_run_hash":"23aff1a6f676ba7ca33f70f4ddfae1dd282fb86104d577ce9be510d81a94c5dc","published":"Wed, 10 Jun 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2606.10254v1 Announce Type: new \nAbstract: 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 contrast this performance with a control setting where the same judges evaluate synthetic LLM-generated solutions. We identify a stark ``Evaluation Gap'': judges are considerably more accurate and consistent on synthetic text (MSE $\\sim$1.17) but struggle to generalize to authentic student reasoning. Through semantic embedding analysis, we find that synth","title":"RealMath-Eval: Why SOTA Judges Struggle with Real Human Reasoning","url":"https://arxiv.org/abs/2606.10254","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.10254v1 Announce Type: new \nAbstract: While Large Language Models (LLMs) have achieved near-perfect performance in \\emph{solving} high-school mathematics, their ability to \\emph{evaluate} the diverse reasoning processes of real human students remains under-examined. To bridge this gap, we introduce \\textbf{RealMath-Eval}, a rigorously annotated benchmark of 224 real-world exam responses from high schools. Our initial evaluation reveals that even state-of-the-art LLM judges struggle significantly on this task, exhibiting a high Mean Squared Error ($\\sim$2.96) against expert human grading. To probe a plausible explanation, we contrast this performance with a control setting where the same judges evaluate synthetic LLM-generated solutions. We identify a stark ``Evaluation Gap'': judges are considerably more accurate and consistent on synthetic text (MSE $\\sim$1.17) but struggle to generalize to authentic student reasoning. Through semantic embedding analysis, we find that synth","title":"RealMath-Eval: Why SOTA Judges Struggle with Real Human Reasoning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-10T04:43:37Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.10254"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:ad229879d1963183dd77ff35108e2a7e6eee2570412f96156f50a6d5babe68675de27de3730e8425d94125581d8424a07657ee61fb64082d47c6a06a00745807","signer":"crovia.substrate","subject":{"observed_at":"2026-06-10T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.10254"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"853ecb669ae1edfd2ceef13ff73dffc61705a85a27e6f7968308f2cd47b5d9b6","leaf_index":225845,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"a549ee7b2ec014d556dcc4a12ef9ba57ab29ed4f132ec221fc1b5832dc831a66","side":"left"},{"sibling":"c318878b9fb70f7c259663d744db2f181419b860059144ad97d2448e7aa13698","side":"right"},{"sibling":"2d80804179eba946cc2d9a2af801c477fdef8b71eeead0e0d6b88129859df406","side":"left"},{"sibling":"3c72452f323d005f509ddbd6e499a6b99757977e0b2c34c201e3134717371aba","side":"right"},{"sibling":"2972ba12364fac7d14bdfc19a09c10224b5db4c1ee56a8df9ffeebf489ddb04c","side":"left"},{"sibling":"fd3a8e9b48f97a29aa606df99952b4b89a4b5719f790913e9488e0c8bbbac72b","side":"left"},{"sibling":"57d96121c87d0ee7fbc594e4eafe8e8c0c5e450de342e0b28773f2c89ff64a79","side":"right"},{"sibling":"b42fc5e6a220ca97d9fe75065fb0dafd72b915ddda12e63083678d3813da9eee","side":"right"},{"sibling":"ac698c3a6027f35b513fe892f166e70344e855625238cbb581d0bf06c131db80","side":"right"},{"sibling":"a4d17aefe58175050dc159af6246658fcf1c9f3ed57aacf1b350fc3261de4e69","side":"left"},{"sibling":"280b980aa0c7756b0b0cb22658f26466d36f0e70fbc3312cd2311d9898e30b8f","side":"right"},{"sibling":"c98954d4b658b1dda60fe52576fcf9bf21a2d49c67fb63f8c30f16ab5f721938","side":"right"},{"sibling":"cdb58f86163046d3b15f857b03372ec75e1ad9ea4548e086793d528b9eed364d","side":"left"},{"sibling":"533d82482604463aa4a281b9d8b85917b383b7c5f924b2b494039524c55e8797","side":"left"},{"sibling":"b2590791b920ca2a4ed39de126d2c0b1a10d9e7e62f572f12425f214e767b6e1","side":"left"},{"sibling":"6cea4964f32722eb370847c2f7c9d6a9f0622c239538b07e6815a59d6fd8d49c","side":"right"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":228173,"merkle_root":"7e416202c0bfd759bd2eea4236713b403993d99793fe8badb5065040080bece3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260611T143708Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-11T21:59:35Z","sig_algorithm":"ed25519","signature":"231c80024bc3982dd493c45b31af95097e97aabc6d712a4e5bad7d0cbdd3c08e01ff395b0f8e72754bac97016e0cd0eed88b8a13cb71edbbcb9b6d72c10a7b03","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_92ca43fb8400c09cca88fed4b2cb834690a36bf61ff3d7091f3d8642298c6ba7"}}