{"_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_1f6493c99cf383def6edbde7e8739eb032d5e70e69eb5ca63af1fdf8f44b72ec","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_1f6493c99cf383def6edbde7e8739eb032d5e70e69eb5ca63af1fdf8f44b72ec","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"efaf96a177dc11d1f3d31dfccd07419f712efb9473f65d30f2012f422f8ae64e","published":"Thu, 28 May 2026 00:00:00 -0400","receipt_hash":"efaf96a177dc11d1f3d31dfccd07419f712efb9473f65d30f2012f422f8ae64e","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":"efaf96a177dc11d1f3d31dfccd07419f712efb9473f65d30f2012f422f8ae64e","observed_at":"2026-05-28T04:43:38.862500Z","parent_run_hash":"58f8b4a134069e0a15ea3949252489597eb86dd27c9ca3fb15c6fb838ce49ef3","published":"Thu, 28 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:2605.27567v1 Announce Type: new \nAbstract: Causal discovery is a cornerstone of scientific reasoning, yet whether large language models can perform it reliably remains an open question. Recent benchmarks show that even fine-tuned models plateau on simple causal graphs and degrade as complexity grows, but why they fail has not been established. We prove the failure is fundamental: supervised fine-tuning, direct preference optimization, and in-context learning all produce predictors that cannot distinguish between causal graphs generating similar observational data, and any attempt to do so requires the model's internal representations to grow unboundedly, violating the very conditions under which these methods work. We formalize this as a kernel obstruction theorem, establishing that the limitation is intrinsic to the learning paradigm, \\emph{not any particular model or dataset}. We propose Agentic Causal Bayesian Optimization (A-CBO), wherein a frozen language model serves as an ","title":"Why LLMs Fail at Causal Discovery and How Interventional Agents Escape","url":"https://arxiv.org/abs/2605.27567","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.27567v1 Announce Type: new \nAbstract: Causal discovery is a cornerstone of scientific reasoning, yet whether large language models can perform it reliably remains an open question. Recent benchmarks show that even fine-tuned models plateau on simple causal graphs and degrade as complexity grows, but why they fail has not been established. We prove the failure is fundamental: supervised fine-tuning, direct preference optimization, and in-context learning all produce predictors that cannot distinguish between causal graphs generating similar observational data, and any attempt to do so requires the model's internal representations to grow unboundedly, violating the very conditions under which these methods work. We formalize this as a kernel obstruction theorem, establishing that the limitation is intrinsic to the learning paradigm, \\emph{not any particular model or dataset}. We propose Agentic Causal Bayesian Optimization (A-CBO), wherein a frozen language model serves as an ","title":"Why LLMs Fail at Causal Discovery and How Interventional Agents Escape","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-28T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.27567"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:437a278bef69779a584fb32a8f91262ab0c81863318f074ffb01ada0073035a48e1fc9ccd893addbd6a2c2c0c57c18cace32fbc4b9bc986ebe41b449e3e05a06","signer":"crovia.substrate","subject":{"observed_at":"2026-05-28T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.27567"},"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":"6aed12426abbaa32f6a407143acbc0140761bc45bc25221c8ae7c00164dcfd92","leaf_index":155572,"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":"c6cf888ba3702dca2c74e70d6b0f855a22bc54d7b6987065495f16d369b02932","side":"right"},{"sibling":"6b1a106420649422210553e7ccf807dc5ca18f941d082c96488d05b850a56386","side":"right"},{"sibling":"7061dd785c07a39b03bed38dd3f88c78f6123970e23187c2581ea03cbc06ec83","side":"left"},{"sibling":"8604ca5e4cf31aaa7ca4319a1cd9c148f93b63a3e5882b0aff4ee795b9ef37c9","side":"right"},{"sibling":"ac510179125e994c30940481a28bb6a5212d1fbf8b6f4deac06dd9384ddf24b3","side":"left"},{"sibling":"94910a3334cfe6711b343e38a4080ec57f42eca4bb95cb4a89133993dfb2249e","side":"left"},{"sibling":"4774677923a89de1c2868262943d04bd69f24de1727dd8c9b782582c677915ac","side":"right"},{"sibling":"70e73f197ecea5d12ff2f9cf2ca33087110a782ea956c539b3058422ada4b2bd","side":"left"},{"sibling":"8c9c7b64ca041ef0029c35e402972d0bebed706fe997b9c587da6f5c811dcce1","side":"left"},{"sibling":"aa7a574eaea239ab8851da225206477d62a6ea5a15b65834f22d1c10288348e7","side":"left"},{"sibling":"7fcba2ee8232873e5d864902f28968d2be38867751c238f238f629eddb98b226","side":"left"},{"sibling":"816f233274bb10f5a122aac086a0c8c697b78fec67a4af55190bb596b7506fab","side":"left"},{"sibling":"d415e6939aee710631f5062799379b547d2c3e3d9a68f263bbb5a693285ab2ca","side":"left"},{"sibling":"d422d38e0ffe6e849b6ce3259d90c9d36497b4d7391a003e15591668c79028a7","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"7b6f0bea4291a5e63574dfca9aa0f9756f450c9478c3d07474d39a7ababb51f9","side":"right"},{"sibling":"1d39fe14b21e2ebbfb87e882423b24ee9469eae1e4c77af5b799ac4db9537467","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":156177,"merkle_root":"c5705a0243d16afd8b1ebfd731b7aa304079c442c2a7906493c5bbed374c69ec","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260528T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-28T05:37:36Z","sig_algorithm":"ed25519","signature":"f087e13febc8bb6a2e0812610de64cebc65be92915518d9c4b230799c3b161839b04c4eb1b02741f938f35545a76ab76555b04c782bdc2f9a44852d171d65909","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_1f6493c99cf383def6edbde7e8739eb032d5e70e69eb5ca63af1fdf8f44b72ec"}}