{"_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_6289b86eb4b84faba1c3b6e69502e158e33a3bd3a51e7e5f3da9c31cfba112ec","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_6289b86eb4b84faba1c3b6e69502e158e33a3bd3a51e7e5f3da9c31cfba112ec","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"4a9a59cc1658bef67aef21f19931e8537fc190bde4ffe251cbc083d4cbdc0c4e","published":"Wed, 27 May 2026 00:00:00 -0400","receipt_hash":"4a9a59cc1658bef67aef21f19931e8537fc190bde4ffe251cbc083d4cbdc0c4e","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":"4a9a59cc1658bef67aef21f19931e8537fc190bde4ffe251cbc083d4cbdc0c4e","observed_at":"2026-05-27T04:43:18.926230Z","parent_run_hash":"6f581915edab4326e2b95fed7c82c2ee149e978d6d7c2443439442a927c31dfa","published":"Wed, 27 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:2605.26414v1 Announce Type: new \nAbstract: Large Language Models (LLMs) achieve impressive accuracy on mathematical reasoning benchmarks, yet their performance drops when problems are modified with simple changes like different names or numbers. Code execution methods, which let models generate and run Python code instead of reasoning in natural language, have been proposed as a solution, but their effect on reasoning robustness (the ability to maintain accuracy across problem variations) has not been systematically tested. This study evaluates three approaches on 1,000 problems from the GSM-Symbolic dataset: pure reasoning using chain-of-thought (CoT) prompting, single-shot code execution using Program-Aided Language models (PAL), and iterative code execution using Step-by-Step Coding (SBSC). All three were run on paired original and modified problems using Claude Haiku 4.5. CoT was the most robust method, with an accuracy drop of 1.3 percentage points and 1.8% of problems break","title":"Reasoning, Code, or Both? How Large Language Models Handle Variations in Math Questions","url":"https://arxiv.org/abs/2605.26414","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.26414v1 Announce Type: new \nAbstract: Large Language Models (LLMs) achieve impressive accuracy on mathematical reasoning benchmarks, yet their performance drops when problems are modified with simple changes like different names or numbers. Code execution methods, which let models generate and run Python code instead of reasoning in natural language, have been proposed as a solution, but their effect on reasoning robustness (the ability to maintain accuracy across problem variations) has not been systematically tested. This study evaluates three approaches on 1,000 problems from the GSM-Symbolic dataset: pure reasoning using chain-of-thought (CoT) prompting, single-shot code execution using Program-Aided Language models (PAL), and iterative code execution using Step-by-Step Coding (SBSC). All three were run on paired original and modified problems using Claude Haiku 4.5. CoT was the most robust method, with an accuracy drop of 1.3 percentage points and 1.8% of problems break","title":"Reasoning, Code, or Both? How Large Language Models Handle Variations in Math Questions","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-27T04:43:18Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.26414"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:f37eef55754e80a528bc8bd16cce18ed11f189e9cd4611e7f36459efc28869af686569a506653cc5dfadb16979ed575cd4583fed6b25fa884baac692cd83110f","signer":"crovia.substrate","subject":{"observed_at":"2026-05-27T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.26414"},"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":"45453bd98dfbae4838725cbfc3636a10ec7920442a5250342a4b257f565cf18a","leaf_index":153570,"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":"d17b75f134e55ae354f94c2e2269f8247996a9162ced626e078b08bc683caa90","side":"right"},{"sibling":"0329a4346307f5f089ebd068d0bee04000fa1f13153e9380a69c1ed553caa1be","side":"left"},{"sibling":"84dbfef2692753044c9e7bd18ea4ceca72bbe09ef0011f26e738a4e4a2a8ae02","side":"right"},{"sibling":"559abe33476a024a4b836b69856ef69b0fad8aa982ad4dd29fd970689c40be6d","side":"right"},{"sibling":"e0584e2c758537fb92a0cd145f904dec9f64c6a5ee549236c2ca404a042bcb48","side":"right"},{"sibling":"31d6424910a8cf4c515fbc6a09bdc25637640c854094c78ee9441c26e20f3e7b","side":"left"},{"sibling":"7e29d20bc58bb43ef3f6cdd944eb9f9025decb57a8f63cc2a0d59200f1d77bef","side":"left"},{"sibling":"dcc303c972d90ed3630aef0a6c2a3edd8c5b29cb2cc61805abaf9ddf885832e7","side":"left"},{"sibling":"94a845c78066cc7024ea52be995e0288a46b35a3430ba66fe7b939b2ddeb255c","side":"left"},{"sibling":"083e753237e7e2c337ddece20acebeca13943581cb5f796fe3e86bdba2ead0ed","side":"left"},{"sibling":"b1f51950a0c51a4dd0cca928c048f5b59153bd52927ad638066a0cf61b44365d","side":"left"},{"sibling":"64f0cee43abfb8301986ce9f1637f992794ecd7ee43659e68b16aea49363c2d0","side":"right"},{"sibling":"d415e6939aee710631f5062799379b547d2c3e3d9a68f263bbb5a693285ab2ca","side":"left"},{"sibling":"374c02d15fb12bd356c179c94766043a982052c6132af8bfc15361b431ffa9f7","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"990705096edf483cc877217308f731dc42d6f6d99f82880167bbdbbfef32560a","side":"right"},{"sibling":"dd265753d95fa2e2fb4f5768e37fab6f691ccff09ad60d0910ff7dc23bac9226","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":154065,"merkle_root":"4993cfdc172e7880b60667f16789dc2e831ff000f81bb1ecba248e73f1510eca","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260527T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-27T05:37:36Z","sig_algorithm":"ed25519","signature":"76ecf118011540405e96506e6219752df04a2850632f2903dc6f10e08b98bc5a42c8d9e1cb5b7c5bf714479806a403df5f34399afa40c23fbb71493a1f77bd0c","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_6289b86eb4b84faba1c3b6e69502e158e33a3bd3a51e7e5f3da9c31cfba112ec"}}