{"_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_0dad67666cf3b6eae728c0fe51d022ecad74d8057b6ce3d5a87c5c0869402a15","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_0dad67666cf3b6eae728c0fe51d022ecad74d8057b6ce3d5a87c5c0869402a15","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"baf1182202c7daa0c4128629ffd7118c6e104604f8ce5896fd7def20c4e5af5d","published":"Fri, 26 Jun 2026 00:00:00 -0400","receipt_hash":"baf1182202c7daa0c4128629ffd7118c6e104604f8ce5896fd7def20c4e5af5d","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":"baf1182202c7daa0c4128629ffd7118c6e104604f8ce5896fd7def20c4e5af5d","observed_at":"2026-06-26T04:43:58.168958Z","parent_run_hash":"9459505a803125e4b968df08c74ed0054a2aafd44e4e1a036e3b0709a8a65cb4","published":"Fri, 26 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:2606.27047v1 Announce Type: cross \nAbstract: Large language models (LLMs) have demonstrated strong performance across a wide range of tasks, but ensuring their reliability in highly technical domains remains a significant challenge. In nuclear engineering, problem solving often requires not only factual knowledge but also quantitative reasoning and conceptual understanding. To address the need for systematic evaluation in this domain, we introduce NuclearQAv2, a benchmark for assessing LLMs on nuclear engineering knowledge. The benchmark comprises approximately 1,240 question-answer pairs spanning three categories: boolean, numeric, and verbal. NuclearQAv2 is constructed using a hybrid pipeline that combines expert-authored questions, existing datasets, and LLM-assisted generation from domain-specific technical corpora. By leveraging structured prompting for both automated question generation and response evaluation, the proposed framework enables scalable benchmark construction ","title":"NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models","url":"https://arxiv.org/abs/2606.27047","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.27047v1 Announce Type: cross \nAbstract: Large language models (LLMs) have demonstrated strong performance across a wide range of tasks, but ensuring their reliability in highly technical domains remains a significant challenge. In nuclear engineering, problem solving often requires not only factual knowledge but also quantitative reasoning and conceptual understanding. To address the need for systematic evaluation in this domain, we introduce NuclearQAv2, a benchmark for assessing LLMs on nuclear engineering knowledge. The benchmark comprises approximately 1,240 question-answer pairs spanning three categories: boolean, numeric, and verbal. NuclearQAv2 is constructed using a hybrid pipeline that combines expert-authored questions, existing datasets, and LLM-assisted generation from domain-specific technical corpora. By leveraging structured prompting for both automated question generation and response evaluation, the proposed framework enables scalable benchmark construction ","title":"NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-26T04:43:58Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.27047"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:eadabe5b2f71fdb08da063c247372437d2f7d8b7bb889e1f49ec875102831a3e5ea8dc91dc242adba10209cff4aabec8f48365bc481f315e5662ed26ae466606","signer":"crovia.substrate","subject":{"observed_at":"2026-06-26T04:43:58Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.27047"},"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":"f081b52d2937232d4b7b83f44aa304939cd9733eae9584791af1ee1aa408e094","leaf_index":251172,"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":"1c15e8477532a1fa39eac0255127b66392a12ff43455dbec1cbc6fb5633086dd","side":"right"},{"sibling":"be943471b25282b924147a57d6458a535a4fcd8d6601702c34d34bbc1ed137d8","side":"right"},{"sibling":"51a405cee65caffd9463263a78f7f30313e4bc07185db055e99e023fa5edd656","side":"left"},{"sibling":"b4738d5c444bab2543b70e4a23efe33110b5c436ad9bbb529f5ea3f3064a7f2b","side":"right"},{"sibling":"1a56d0acee1139e79b9cb7a452db735657dc8dbcbe5baa415a46d2aa9bd396b6","side":"right"},{"sibling":"560f6bfbc80c60f9cd8b6d1801c24aad7b45471335f3a4eacdc44dcad4f9129a","side":"left"},{"sibling":"2f14dad8e0a8f8bab0ca581ed1b54b6a2b4cc27363a36e17359b2be932eb3fb9","side":"right"},{"sibling":"846fe23f5401fbe8ae1dd175eade4cb955db0a1adde862418a9a781a48f6283c","side":"right"},{"sibling":"d097e1d1d25acb37e74792d46ad69ba853039e2f2b33a092c9ea32a837aeed84","side":"left"},{"sibling":"b6709caadc8510310ee2ec0b66d1058fcad31c91c65cc2bad6f46a693d553580","side":"right"},{"sibling":"a72c3b8804a37d1a9d18e02e6fdb048bc8ea6b0746909cd2de10bdbabc793737","side":"left"},{"sibling":"803703dc2c50a646fa77b57c0056e9a5126611ba4bcde0d6013ccd6b2d44bdbf","side":"right"},{"sibling":"e78f244b1b8df6d5e3fdc6dd76b5c27d4e6fe3b93b8cd61355497b63d7e4cfe8","side":"left"},{"sibling":"6167cb552ed6871fbf0afcf3db01d1017af7d472b136fcbe5404d1df09f41cc1","side":"right"},{"sibling":"f29798d8bb6aa9900eab878992d9ff0c53266debd87472f31ab26a6a3fb55880","side":"left"},{"sibling":"a04392fb9f2a3a620840e3b3fecd93d12e6d224e481c162389d8ae64e7194599","side":"left"},{"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":251380,"merkle_root":"e042805d07cd8dc777d49695ad78b8d4ec9721df271ff0245d7706773c30b4a5","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260626T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-26T05:37:59Z","sig_algorithm":"ed25519","signature":"c68a6e827804771acd244208495c5e35c6f417307db3c76192f038dedaa5b5f86e019074a3bea353357ff7457924c4f7907832638bb9a4d3d18e7a7f50c6a10b","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_0dad67666cf3b6eae728c0fe51d022ecad74d8057b6ce3d5a87c5c0869402a15"}}