{"_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_8eef98ed91153679c107b98457babba058254733dc8af1b3242051918fb6c9ac","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_8eef98ed91153679c107b98457babba058254733dc8af1b3242051918fb6c9ac","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"b9745bca106945bbd202bdca28b8dd99e91f269cf068ab8f18e6e17762f8d900","published":"Wed, 15 Jul 2026 00:00:00 -0400","receipt_hash":"b9745bca106945bbd202bdca28b8dd99e91f269cf068ab8f18e6e17762f8d900","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":"b9745bca106945bbd202bdca28b8dd99e91f269cf068ab8f18e6e17762f8d900","observed_at":"2026-07-15T04:44:03.592429Z","parent_run_hash":"d49a6cf532e74153266f377b7760fc948d950d80ed41fc3e3eb82b58f5597ead","published":"Wed, 15 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:2511.04689v3 Announce Type: replace-cross \nAbstract: Evaluating large language models (LLMs) typically requires thousands of benchmark items, making the process expensive, slow, and increasingly impractical at scale. Existing evaluation protocols rely on average accuracy over fixed item sets, treating all items as equally informative despite substantial variation in difficulty and discrimination. We introduce ATLAS, an adaptive testing framework based on Item Response Theory (IRT) that estimates model ability using Fisher information-guided item selection. ATLAS reduces the number of required items by up to 90% while maintaining measurement precision. For instance, it matches whole-bank ability estimates using only 41 items (0.157 MAE) on HellaSwag (5,600 items). We further reconstruct accuracy from ATLAS's ability estimates and find that reconstructed accuracies closely match raw accuracies across all five benchmarks, indicating that ability ${\\theta}$ preserves the global perfo","title":"Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static Benchmarks","url":"https://arxiv.org/abs/2511.04689","vendor":"arxiv_cs_ai"},"summary":"arXiv:2511.04689v3 Announce Type: replace-cross \nAbstract: Evaluating large language models (LLMs) typically requires thousands of benchmark items, making the process expensive, slow, and increasingly impractical at scale. Existing evaluation protocols rely on average accuracy over fixed item sets, treating all items as equally informative despite substantial variation in difficulty and discrimination. We introduce ATLAS, an adaptive testing framework based on Item Response Theory (IRT) that estimates model ability using Fisher information-guided item selection. ATLAS reduces the number of required items by up to 90% while maintaining measurement precision. For instance, it matches whole-bank ability estimates using only 41 items (0.157 MAE) on HellaSwag (5,600 items). We further reconstruct accuracy from ATLAS's ability estimates and find that reconstructed accuracies closely match raw accuracies across all five benchmarks, indicating that ability ${\\theta}$ preserves the global perfo","title":"Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static Benchmarks","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-15T04:44:03Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2511.04689"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:6a320941f61d69e86fb7c83ff7ff042ee8131b33c3bebcd7935937cd2a98544c78bc5420981c0f709091e6efda0449d517a0dcaa1b0024f26abd9eaee8caf90a","signer":"crovia.substrate","subject":{"observed_at":"2026-07-15T04:44:03Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2511.04689"},"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":"1f4fb25f618bbdb095f851d3e9a66cdcf469de32bdce1c450e1bb4335da4b9ef","leaf_index":316556,"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":"75e18826024582003cbdffc39cbe76ac3b3d2fc6f38e6c75df73baee75fe345a","side":"right"},{"sibling":"87494a2d91226c86aae552fca55f3cf2ec2a1e975d7d30e4c44d7efc7898df64","side":"right"},{"sibling":"d3dacd3058e6b468cfd3b7106770bd0e69c65c8af0b6848573047934711ad4b4","side":"left"},{"sibling":"464a00854e69f181f1f33f794cb1b4a1ae132f44c5ca549c8745730c63d767f5","side":"left"},{"sibling":"c97c1916cedd4681a23ca2cbdc36a5d7e6c927e09489be3fb5259b3f12d4a014","side":"right"},{"sibling":"55c1bf3af00ff2daa2b7e7846baaad9e76454cd8203e4764d9fe225883b81168","side":"right"},{"sibling":"33661ca420513ca9092e711309245c4602733fe2714484fedf48cb9c8664fd0e","side":"right"},{"sibling":"af39fefe9ccf50e1288b21fab97d8bc62d8495b7dbe9a55a9ffa363740e34285","side":"left"},{"sibling":"1c7f1bf97993e3a126824f8350788b168c4c13264fb03a73b3ede312035d3527","side":"right"},{"sibling":"84a7590e6b24dd07ed46597f19deb75d9ad247b4227b17f30857ec7cc0fc5c21","side":"right"},{"sibling":"c8d3d8cb0183b912107f9781ad2a1b6c0c9424906c5907c09deeb5bea9d7b571","side":"left"},{"sibling":"0cb62c0ada57a2406a6bcb100889d3e8b29a15efeed07adaff5bb90a5e80612a","side":"right"},{"sibling":"0b69289b25462ddd6166f6f49004cfc8ada0ab4f10adafe188347817bdd46e37","side":"left"},{"sibling":"1418b281cd985b5ed411ef25f2017a1826cc14919b6fad3934e6ceeec693699b","side":"right"},{"sibling":"f302542c38ba7c3aab7c9280dd60259ecec777dca6e6f71b6f0729b0b8791b72","side":"left"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"abe4a8c706e530484d1e96a8988cb09eab85928b2050985500ab289753fe3eec","side":"right"},{"sibling":"f436dccf82aa2c1eb7bfa3eb84316e116aaf64dc55cd9592597118f6cb0648f6","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":316730,"merkle_root":"a8e6e5be81ea6f5b5f2227422459bf39455fe9f0b6602b4d1ce6977dbfd78bc7","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260715T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-15T05:38:24Z","sig_algorithm":"ed25519","signature":"df1678d268b5a07413e2ca6e748c3f40b6cfedea930a18d843489a4ab513da791bf0a886caab1b918d0989f8ebaaf3d0035ca2aa777913b1ad29979f1deb9a0c","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_8eef98ed91153679c107b98457babba058254733dc8af1b3242051918fb6c9ac"}}