{"_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_8745cbd358d5770d614bcf59b342b74695f28cb8c8aa0f717070ad7cbca5a98d","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_8745cbd358d5770d614bcf59b342b74695f28cb8c8aa0f717070ad7cbca5a98d","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"a18b0ae2f6e9791b6a4cd1f67194bdde4dd0b90ac6d1178c2f5b65f47a446eae","published":"Tue, 26 May 2026 00:00:00 -0400","receipt_hash":"a18b0ae2f6e9791b6a4cd1f67194bdde4dd0b90ac6d1178c2f5b65f47a446eae","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":"a18b0ae2f6e9791b6a4cd1f67194bdde4dd0b90ac6d1178c2f5b65f47a446eae","observed_at":"2026-05-26T04:43:39.018238Z","parent_run_hash":"dca8dedd754ad6a1772113d6b97ee4f4ab9a0afbdeb44aaace5ff2d2446b164b","published":"Tue, 26 May 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:2605.24305v1 Announce Type: cross \nAbstract: Standard accuracy on binary reasoning benchmarks hides critical failure modes: prior collapse, inconsistency under paraphrase, and inability to reason about parameter-dependent dynamics. We present ChaosBench-Logic v2, a 40,886-question benchmark over 165 dynamical systems with 27 FOL predicates and 78 axiom edges, together with CARE (Calibration- and Adversarial-Robust Evaluation), a protocol that surfaces these pathologies. Evaluating 14 models, we find that regime-transition reasoning remains near random (MCC = 0.05) even for frontier models, whereas FOL deduction with given premises reaches MCC = 0.52. Per-family decomposition shows that the proprietary-model advantage concentrates on cross-indicator (+0.40) and consistency tasks, while open-source Qwen 2.5-32B dominates indicator diagnostics (0.91 vs. 0.45). Two models exhibit negative MCC on bifurcation questions, confirmed as systematic anti-correlation via confusion-matrix anal","title":"ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale","url":"https://arxiv.org/abs/2605.24305","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.24305v1 Announce Type: cross \nAbstract: Standard accuracy on binary reasoning benchmarks hides critical failure modes: prior collapse, inconsistency under paraphrase, and inability to reason about parameter-dependent dynamics. We present ChaosBench-Logic v2, a 40,886-question benchmark over 165 dynamical systems with 27 FOL predicates and 78 axiom edges, together with CARE (Calibration- and Adversarial-Robust Evaluation), a protocol that surfaces these pathologies. Evaluating 14 models, we find that regime-transition reasoning remains near random (MCC = 0.05) even for frontier models, whereas FOL deduction with given premises reaches MCC = 0.52. Per-family decomposition shows that the proprietary-model advantage concentrates on cross-indicator (+0.40) and consistency tasks, while open-source Qwen 2.5-32B dominates indicator diagnostics (0.91 vs. 0.45). Two models exhibit negative MCC on bifurcation questions, confirmed as systematic anti-correlation via confusion-matrix anal","title":"ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-26T04:43:39Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.24305"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:1b370f1fb08e0adfd7607b8264b4cd64cd7f9b9a01330e253870443a94e1b2b5319a24ff5b7070bd9cae9a2424a2a38a5ea4451d67c825da6b6223e8f1bc1909","signer":"crovia.substrate","subject":{"observed_at":"2026-05-26T04:43:39Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.24305"},"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":"906485297e08241810117d291d9b934a613046054726472becdcbd58a139c509","leaf_index":151536,"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":"4e5dc35a334a76adcb2408607f125636ba82908d284f0fa5613bf14398dcc0e4","side":"right"},{"sibling":"4980c8b54effc3d5cde6c29f39a2c71575e5c32cf1a501df9c178a1c4c76db1f","side":"right"},{"sibling":"de33c2a2640ab5728aa6027a83c799705349cc9dd7feb12fd0a600c3b7cf92f1","side":"right"},{"sibling":"15d47b076ac1c1605ad084b8d2b0ec89627f40c2ac5a1f857364dc054a9c2858","side":"right"},{"sibling":"c5167fbcd46d2af54fb81294761b6bcbfd7fef495ff36d0730b5a13d0448d578","side":"left"},{"sibling":"e4c51922cc3a9dfa8ffcb4eac4ab29c5372c2bd53686548afdf9c6203620dbfe","side":"left"},{"sibling":"aca2ea5485625e14e9749df76cdae0268d37544ceeea42aec677e7b6cb11725a","side":"left"},{"sibling":"12607c0dd56c2db51bf46dd95ab0fe795f3f832d068cd7268fed3aeeb8a7cc29","side":"left"},{"sibling":"a808644c9a09dd75253c6c0ba9275dc94a6b6451ad5184ebdafda4a2722b36a5","side":"left"},{"sibling":"fdd22ebd87e5ba37d1153e47753a63818abb25df8fe45dbf735ba5c512c3355b","side":"left"},{"sibling":"cf593c482d17d202b94914915d0c65fb8713053548db64771d0ec5dbb404a07f","side":"left"},{"sibling":"134949308b15cffd6792ee2cf678119af34d69a64764d7c89cd47573c94e1cda","side":"left"},{"sibling":"e20a7391fed5b5f3b675af68344a3f5b050d6701e127b7db010af3941e59dfdb","side":"right"},{"sibling":"e5893793e3591ed7f5e58ca94ffcfba46bb30f69fb1c25d5ba8ef49eb99f9126","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"e3eecaf996dbe7229a7bb1d234c97aea97a252c5f7c89f8547b6d091db0f0e40","side":"right"},{"sibling":"55bcbd4da3e20d93931f7e58673f10232e81a5b1514d7396cb4b71e8f95788d0","side":"right"},{"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":152106,"merkle_root":"ac5182c6f3dd09931f2a689df5f4be36df7b55e55bcf106e195671f5ed55fd8f","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260526T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-26T05:37:34Z","sig_algorithm":"ed25519","signature":"a401243fbd2c077d29a623c6ef616c78fbd5c8ce1930afa7af7165b2386e5a8cf15d5094983a1c962e71b27b911a3f3ce09c8cfab9393be2ce5ce8ee6513da06","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_8745cbd358d5770d614bcf59b342b74695f28cb8c8aa0f717070ad7cbca5a98d"}}