{"_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_caac2fa176d45d226e4ee31f128eb2ae9f9621c5733a99f9abd0ba20c3ef6c91","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_caac2fa176d45d226e4ee31f128eb2ae9f9621c5733a99f9abd0ba20c3ef6c91","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"0806494bf42a9d2784bf858ccc8c9b79b7c2b6486ba659336dcdac0fc9dd4ec6","published":"Tue, 02 Jun 2026 00:00:00 -0400","receipt_hash":"0806494bf42a9d2784bf858ccc8c9b79b7c2b6486ba659336dcdac0fc9dd4ec6","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":"0806494bf42a9d2784bf858ccc8c9b79b7c2b6486ba659336dcdac0fc9dd4ec6","observed_at":"2026-06-02T04:43:38.825628Z","parent_run_hash":"c2a9665c814770d56765bb764e6a6c7e4fa7d4e9708e157ca0f7440c89927d54","published":"Tue, 02 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:2510.10541v2 Announce Type: replace-cross \nAbstract: Current benchmarks are inadequate for evaluating progress in reinforcement learning (RL) for large language models (LLMs).Despite recent benchmark gains reported for RL, we find that training on these benchmarks' training sets achieves nearly the same performance as training directly on the test sets, suggesting that the benchmarks cannot reliably separate further progress.To study this phenomenon, we introduce a diagnostic suite and the Oracle Performance Gap (OPG) metric that quantifies the performance difference between training on the train split versus the test split of a benchmark. We further analyze this phenomenon with stress tests and find that, despite strong benchmark scores, existing RL methods struggle to generalize across distribution shifts, varying levels of difficulty, and counterfactual scenarios: shortcomings that current benchmarks fail to reveal.We conclude that current benchmarks are insufficient for evalu","title":"Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods?","url":"https://arxiv.org/abs/2510.10541","vendor":"arxiv_cs_ai"},"summary":"arXiv:2510.10541v2 Announce Type: replace-cross \nAbstract: Current benchmarks are inadequate for evaluating progress in reinforcement learning (RL) for large language models (LLMs).Despite recent benchmark gains reported for RL, we find that training on these benchmarks' training sets achieves nearly the same performance as training directly on the test sets, suggesting that the benchmarks cannot reliably separate further progress.To study this phenomenon, we introduce a diagnostic suite and the Oracle Performance Gap (OPG) metric that quantifies the performance difference between training on the train split versus the test split of a benchmark. We further analyze this phenomenon with stress tests and find that, despite strong benchmark scores, existing RL methods struggle to generalize across distribution shifts, varying levels of difficulty, and counterfactual scenarios: shortcomings that current benchmarks fail to reveal.We conclude that current benchmarks are insufficient for evalu","title":"Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods?","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-02T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2510.10541"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:ee716789bc391dd25483276d8a894ac216d88556359a15e4073ccca8bb8cd789c037ed80cf960f6fdcd6bf25a94c8357efafa440e76585fff045f42a1ecee50f","signer":"crovia.substrate","subject":{"observed_at":"2026-06-02T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2510.10541"},"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":"8a8fede7491522cdc49c93b08875ceeb4858b08b2500967cfbd6c313ec7a39f0","leaf_index":205889,"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":"5d92009f091ec1036a923a96513c8a3f93c8a2a98794d892fd6a521ce7fb0c81","side":"left"},{"sibling":"0dfa30eab1fe42469177358849450a858fd1d79765584d3ae37dce24346b30b3","side":"right"},{"sibling":"3ed69b9d593f4fa2e44cb4e0c05d4384ad70e933b6acc4acbc1d621a3f31ef67","side":"right"},{"sibling":"7b134163d36be8ae41c5faaddb0273de50eabf75324240c039c96348f7613da3","side":"right"},{"sibling":"d4b4d4d9defa9aaeeeb546cdadb19e89c0db090bd2b9cf154e14eb03e1f3b771","side":"right"},{"sibling":"e92b8ea42f6bc163f81eddcf5a1f43bf23f994c592c5c1fa0ab7ca7ac0791b22","side":"right"},{"sibling":"e3079b690878ce30b8ca3786d84b9c0a1891426d146e638fe7ca9df8dcb74e02","side":"left"},{"sibling":"a5c0411da65d36a27f4e797deeace23f77314552708425e4e91c3ebf671bc23b","side":"right"},{"sibling":"6ac554ede1f78dc3a28ebe5e1155c2b9c258b71805fdd7ad2ec992697f3ccd0c","side":"right"},{"sibling":"5e1949edfad76bc6a73d008dc8be8a0c6fe4a7fb64c8beaf70e5023ca11d35e0","side":"right"},{"sibling":"e4bd1aaaf3f336d9b072b4d1fc234246fc3cf2874ca873b7741c03eaf97911f2","side":"left"},{"sibling":"e6adead8216db4cae92f0a036d53baebf30eed95a99c0d10758aa75bb7780f2f","side":"right"},{"sibling":"1acc2b7ff453ffd8c97b80ae4db5358780f0c6796874fd75403791dbe99f8cd7","side":"right"},{"sibling":"24d1bb4b13e0e46131b27b70a48e65fcf4e2e14b95e3bb83ade821e9df530f6b","side":"left"},{"sibling":"5f86f58c28b1a86ae06dfff4666bb9fba8866021a81fd4f1d200aa9af4722dfb","side":"right"},{"sibling":"f6cc6f94f6944ae21390afc65ac9e91dc31f84ee6e060681bba5ae08058294bd","side":"right"},{"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":206226,"merkle_root":"d2a6d32b13cbf343fb143b21a756d0533864ae6577a376ee84ba867b949207ec","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260602T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-02T05:37:46Z","sig_algorithm":"ed25519","signature":"abd9956cfb19dd1fb8142c46a220bac2514848c6abb0e79b8b0940206cc3ebb00894d4daaf9f786427f82a7cc12482e7fda79054ebb06bceaa9b4b97e23fb30e","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_caac2fa176d45d226e4ee31f128eb2ae9f9621c5733a99f9abd0ba20c3ef6c91"}}