{"_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_a99a296c773a94b9e69dcb202e25aea0a53fa9ef34c73fcccd63a518aac5bd84","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_a99a296c773a94b9e69dcb202e25aea0a53fa9ef34c73fcccd63a518aac5bd84","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"ac88fb93bec35a78734684b7f92bc0e01897f225e4c8329ee9bb0724872fdc0f","published":"Tue, 14 Jul 2026 00:00:00 -0400","receipt_hash":"ac88fb93bec35a78734684b7f92bc0e01897f225e4c8329ee9bb0724872fdc0f","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":"ac88fb93bec35a78734684b7f92bc0e01897f225e4c8329ee9bb0724872fdc0f","observed_at":"2026-07-14T04:43:37.834979Z","parent_run_hash":"66b89520a448b8d9fe7d8f602ef38b82b6c95e57f532ce72de51375b41870477","published":"Tue, 14 Jul 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:2607.09789v1 Announce Type: new \nAbstract: We introduce PHITSBench, an execution-scored benchmark for the Monte Carlo Particle and Heavy Ion Transport code System (PHITS). PHITSBench comprises 282 transport-scorable tasks spanning three common workflow categories: parameter editing (Edit), syntax repair (Repair ), and complete simulation generation from natural-language descriptions (Reproduce). Each task is evaluated using a Composite Metric Score that combines execution success with agreement between generated and reference transport observables. Using PHITSBench, we evaluate five GPT-5.4-based configurations ranging from zero-shot prompting to knowledge-augmented and agentic workflows. Without domain-specific knowledge, the model performs well on editing and repair tasks (95% and 70% success, respectively) but fails to generate correct simulations from scratch (0% success on the Reproduce track). A structured, machine-readable PHITS knowledge catalog, supplied alongside the us","title":"PHITSBench: an execution-scored benchmark for AI-assisted PHITS radiation-transport input generation using natural language","url":"https://arxiv.org/abs/2607.09789","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.09789v1 Announce Type: new \nAbstract: We introduce PHITSBench, an execution-scored benchmark for the Monte Carlo Particle and Heavy Ion Transport code System (PHITS). PHITSBench comprises 282 transport-scorable tasks spanning three common workflow categories: parameter editing (Edit), syntax repair (Repair ), and complete simulation generation from natural-language descriptions (Reproduce). Each task is evaluated using a Composite Metric Score that combines execution success with agreement between generated and reference transport observables. Using PHITSBench, we evaluate five GPT-5.4-based configurations ranging from zero-shot prompting to knowledge-augmented and agentic workflows. Without domain-specific knowledge, the model performs well on editing and repair tasks (95% and 70% success, respectively) but fails to generate correct simulations from scratch (0% success on the Reproduce track). A structured, machine-readable PHITS knowledge catalog, supplied alongside the us","title":"PHITSBench: an execution-scored benchmark for AI-assisted PHITS radiation-transport input generation using natural language","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-14T04:43:37Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.09789"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:acae2af85983d232eab8f141d0d833ec0d35dd4d0683f932845c79d1ecbacc9d87669622e4106f310f1eed2bccffc6c491d9774767a487810cce0a42044b2f0d","signer":"crovia.substrate","subject":{"observed_at":"2026-07-14T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.09789"},"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":"81dabf8c6762b3e19005ba67454cb0e7419aca2e7cbc479f99b5f5d07ec20073","leaf_index":312806,"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":"1de4b7de0a8cd9e5d6bbe7cff216cc23927b5c671b29a8ecefc25b885898f4fa","side":"right"},{"sibling":"d9f38c1ded4b866ba69b04e50437969aecdb785125d37e28745e71bdb00f6ca7","side":"left"},{"sibling":"bbaf1ceb1abc9d2c5c2ffd016ec62aabc23f88417d2dec6c80a620cd1956a304","side":"left"},{"sibling":"511d60a81ef6c0c88b55e9b740f61299b66791ef2c9c27d385e3557a487ab72b","side":"right"},{"sibling":"e6b51982312a070a32dee7d04c7978a0c6663fbf33e2d486b1b9a3041200fbba","side":"right"},{"sibling":"bc4721fdcc1f36bedeaba62d3f41fc689ea8d373f9d3d57a988797bbcd8257ae","side":"left"},{"sibling":"e78d0d4e476fa207968b0d1b4de1b6e0b862fa2573890cb17883fbd17c4bee92","side":"left"},{"sibling":"1bf33ad3b3babcd7e3971fa58862cd0ad2723ec6c97ea2f6ab19b733299eb475","side":"left"},{"sibling":"36e58162e2f6481e200fac2cc34bef53d1ba911d1fe07a8ecd0e0a03097469fc","side":"left"},{"sibling":"2b62f9c6ec45961991e3cfb6ed140d70943061d83fb37c4dc886775dd52fcb6a","side":"right"},{"sibling":"1627ce6908965f2e5fbc7c16bc8e247867478c587014561d0de1359dc2dc0afc","side":"left"},{"sibling":"74e1ba9fd48bdd0f52777dd5b56c10706e73f42629013748eca13ef113cd59db","side":"right"},{"sibling":"682fd39539db5bce908d0ab6f180374728fed6b34a9a8c87c7b4eb5a726e30b8","side":"right"},{"sibling":"184927f71d667ac0c6ebeadb33394626973738b9107c6dc3c0c4949b44acf295","side":"right"},{"sibling":"f302542c38ba7c3aab7c9280dd60259ecec777dca6e6f71b6f0729b0b8791b72","side":"left"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"c4c189d79669979b59d9aa976ee249c54a7e065b4a05bf49463459cc7f37428e","side":"right"},{"sibling":"19475e206bdf2698769a286db2c97c4d3f089741319f9b29a139038c6e511975","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","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":313381,"merkle_root":"5f7d48580373d0ab0bc6bdf34f26de442f9a86d130946f7ee45addd1a55cb9f4","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260714T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-14T05:38:23Z","sig_algorithm":"ed25519","signature":"97364224142ed1b2a8925fed1bfba2e0a8a6a15f8ca0999b934846ad83584a78c7f0f5cd09dbc1c938b35383fcc5c8fa4b723118e30916628879d1c5fd3a9908","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_a99a296c773a94b9e69dcb202e25aea0a53fa9ef34c73fcccd63a518aac5bd84"}}