{"_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_05fc3cf7774ce51c1160d3e7bbe36af5a693e9755bc20098a654301ea1224998","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_05fc3cf7774ce51c1160d3e7bbe36af5a693e9755bc20098a654301ea1224998","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"18120ce334c9a7faa21c229b18215a39f63de32ad58f322fabfab88ffbace3e3","published":"Tue, 19 May 2026 00:00:00 -0400","receipt_hash":"18120ce334c9a7faa21c229b18215a39f63de32ad58f322fabfab88ffbace3e3","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":"18120ce334c9a7faa21c229b18215a39f63de32ad58f322fabfab88ffbace3e3","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:2603.04737v4 Announce Type: replace \nAbstract: Existing reasoning evaluation paradigms suffer from different limitations: fixed benchmarks are increasingly saturated and vulnerable to contamination, while preference-based evaluations rely on subjective judgments. We argue that a core aspect of intelligence is the ability to decide what information to acquire and how to use it effectively. We propose Interactive Benchmarks, a unified evaluation paradigm that assesses a model's reasoning ability through budgeted multi-turn interaction. We evaluate models under this framework in two settings: Interactive Proofs, where models interact with a judge to solve Logic, UI2Html, and Mathematics tasks under objective feedback; and Interactive Games, where models reason strategically to maximize long-horizon utilities. Our results show that interactive benchmarks provide a more robust assessment of this dimension of model intelligence, revealing substantial room for improvement in interactive","title":"Interactive Benchmarks","url":"https://arxiv.org/abs/2603.04737","vendor":"arxiv_cs_ai"},"summary":"arXiv:2603.04737v4 Announce Type: replace \nAbstract: Existing reasoning evaluation paradigms suffer from different limitations: fixed benchmarks are increasingly saturated and vulnerable to contamination, while preference-based evaluations rely on subjective judgments. We argue that a core aspect of intelligence is the ability to decide what information to acquire and how to use it effectively. We propose Interactive Benchmarks, a unified evaluation paradigm that assesses a model's reasoning ability through budgeted multi-turn interaction. We evaluate models under this framework in two settings: Interactive Proofs, where models interact with a judge to solve Logic, UI2Html, and Mathematics tasks under objective feedback; and Interactive Games, where models reason strategically to maximize long-horizon utilities. Our results show that interactive benchmarks provide a more robust assessment of this dimension of model intelligence, revealing substantial room for improvement in interactive","title":"Interactive Benchmarks","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/2603.04737"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:92955a44f1fe1ddf8675326adc0b4566c1e65b77b7194ddc91954d4dc02777a84899c413edcc84f0bc15e4e65e3c0561b9329fd26b062361495f783a4f497508","signer":"crovia.substrate","subject":{"observed_at":"2026-05-19T04:43:36Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2603.04737"},"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":"709d25b671952a595788d4eeeca6377e8b9bb8f73f4084d8b8e0927fe281b1a3","leaf_index":142971,"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":"4113f77c2356b22dd680fed1be7c5109ed81029b532701cd5eb129b247e36483","side":"left"},{"sibling":"c5ccbf548ca9b5f0974d7f689c55cdfc9ba0726c48f951283c66d73a0916ddea","side":"left"},{"sibling":"56030ea9e7d2a481dcb5053299dd20097840dd1c49e27e6ff3b46dc1de578f7f","side":"right"},{"sibling":"379a1b1d961fdc322d34e9fc5ebf0a09151bed41b4ece298eb295296abac39a2","side":"left"},{"sibling":"ddaacd9c90cab459721d12246ec0ad294daa10209c41ad656cb6729d96fa1fac","side":"left"},{"sibling":"3f9a5345017ea65e5d058e222a647991f120e8ad55377a6ea03ee8db431d977d","side":"left"},{"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_05fc3cf7774ce51c1160d3e7bbe36af5a693e9755bc20098a654301ea1224998"}}