{"_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_eefe60f1ed81199201f91b1a64072849bab367ec11d0e464e2392dcc9885413c","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_eefe60f1ed81199201f91b1a64072849bab367ec11d0e464e2392dcc9885413c","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"be9ebcaa4134853fe983d2af66a7a3c8adb03e900ca7100eaca3f53478b7b915","published":"Tue, 19 May 2026 00:00:00 -0400","receipt_hash":"be9ebcaa4134853fe983d2af66a7a3c8adb03e900ca7100eaca3f53478b7b915","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":"be9ebcaa4134853fe983d2af66a7a3c8adb03e900ca7100eaca3f53478b7b915","observed_at":"2026-05-19T04:43:36.782648Z","parent_run_hash":"fefa4c726316a95c5dda9fc1ca07a38a811cf7ffa9825b2f09b365abacd9b32d","published":"Tue, 19 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:2510.26384v2 Announce Type: replace \nAbstract: The prohibitive cost of evaluating large language models (LLMs) on comprehensive benchmarks necessitates the creation of small yet representative data subsets (i.e., tiny benchmarks) that enable efficient assessment while retaining predictive fidelity. Current methods for this task operate under a model-centric paradigm, selecting benchmarking items based on the collective performance of existing models. Such approaches are limited by large upfront costs, an inability to immediately handle new benchmarks (\"cold-start\"), and the fragile assumption that future models will share the failure patterns of their predecessors. In this work, we propose a new item-centric approach to benchmark subset selection, arguing that selection should be based on the intrinsic properties of the task items themselves, rather than on model-specific failure patterns. We instantiate this item-centric efficient benchmarking approach via a novel method, Scales","title":"Scales++: Compute Efficient Evaluation Subset Selection with Cognitive Scales Embeddings","url":"https://arxiv.org/abs/2510.26384","vendor":"arxiv_cs_ai"},"summary":"arXiv:2510.26384v2 Announce Type: replace \nAbstract: The prohibitive cost of evaluating large language models (LLMs) on comprehensive benchmarks necessitates the creation of small yet representative data subsets (i.e., tiny benchmarks) that enable efficient assessment while retaining predictive fidelity. Current methods for this task operate under a model-centric paradigm, selecting benchmarking items based on the collective performance of existing models. Such approaches are limited by large upfront costs, an inability to immediately handle new benchmarks (\"cold-start\"), and the fragile assumption that future models will share the failure patterns of their predecessors. In this work, we propose a new item-centric approach to benchmark subset selection, arguing that selection should be based on the intrinsic properties of the task items themselves, rather than on model-specific failure patterns. We instantiate this item-centric efficient benchmarking approach via a novel method, Scales","title":"Scales++: Compute Efficient Evaluation Subset Selection with Cognitive Scales Embeddings","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-19T04:43:36Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2510.26384"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:e00be6d87acaeaf5cd002936fc85e9018d0cd8d930d0ee752457dfdd33b77bed9188e4a2f7c4d21546038f72021580bb9fb424cb523d24fa0588c7aee327ba04","signer":"crovia.substrate","subject":{"observed_at":"2026-05-19T04:43:36Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2510.26384"},"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":"6a407ec694d52ddf948dc887051fd10593f858df9ec10f225f835d4a18d8d3ad","leaf_index":142940,"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":"f70ae5cc8d0dc744c65b1ed938c91d7b4ab802afb99d3ce6d76f21e64d290b59","side":"right"},{"sibling":"203f289d62ad4a9732cd289ffdfa2b91e5f587edc4b7db3d54237b9c1fa91791","side":"right"},{"sibling":"f5bef39dc4823b49b6710b67ddeb5fc865e9a6cee43accc86cb1555cc0ada0ca","side":"left"},{"sibling":"f5e6beea98855957a21e27288368d09f428b2d74c9e186e58f96a7183bc6c3e0","side":"left"},{"sibling":"f36e6611b68888ffd33c8810d2cf599f4cbe4f7063445fde6b8a9630e596b066","side":"left"},{"sibling":"9dea9c18a1f3e1ca2dd11d844f0399fbd5e56147ad6d60d4ab5391a014482612","side":"right"},{"sibling":"18920e627055779d158c7c223ef853d7d69b12953cbd8e0326b3401e85b3e0a0","side":"left"},{"sibling":"1d2edc28d27d4c312510482f7321ca401bdfe21a8e83916a1ba677f0ea4fcd2b","side":"right"},{"sibling":"78a19962a2f444f055541381645626e3d4e1c8c7c2811bf54eeb89100f89f5b2","side":"right"},{"sibling":"db97141c585f6a1e6bebe92b3ea300ea0f38a2321ca286d85850b11b2dd162a6","side":"left"},{"sibling":"202f1bead178ef3785968d50d3d188264a95192a077654c331612e04a34cbfbe","side":"left"},{"sibling":"72249c8c8b068386e35d16f4bd0bbeb9ba820ca217ef0f0d28396c9fe493f5f0","side":"left"},{"sibling":"ea64599340f7ffdf17ad0cbc1d9401ef8870a347e3847bdc106d06b1673df09c","side":"right"},{"sibling":"8f4c0fbe56b6c010fbb8c782ebcd478079bb3f991d8704e2534209a075d9163c","side":"left"},{"sibling":"4db1f363729507e27a60851cf6ed334d7b9acdef194ed7d419aba4d2bd367a4a","side":"right"},{"sibling":"a86ee18c45e7fcc408b6007eaece05aa75b2d9ae30252e9e878462b4dffbef7b","side":"right"},{"sibling":"1d18e7663d43ccff0122ecc7ee12645bb16afb607b218e81b1ea2408f863cb78","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":143302,"merkle_root":"999156d40a7c61d9ddd52b7338f3cbda3e68f53bace070c7b616ea194e23b123","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260519T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-19T05:37:30Z","sig_algorithm":"ed25519","signature":"b1a252cc66ff32bed1d10dd88a6b2a200e3856d3dbcfcc4ee55e02e00f3d548e854ed9c544704b222bd5d315492c4a935ba2d90d727c585a67899b0ad602fc05","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_eefe60f1ed81199201f91b1a64072849bab367ec11d0e464e2392dcc9885413c"}}