{"_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_5a5379039beabc6b5c846d8df34f1e75d1cf8f3d68b2c0dbbbf201979d636fa1","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_5a5379039beabc6b5c846d8df34f1e75d1cf8f3d68b2c0dbbbf201979d636fa1","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"fe32d33e66c54b0dff9f67744b65d4eec8de2c48354e1fcdb0f101baafa7621a","published":"Thu, 16 Jul 2026 00:00:00 -0400","receipt_hash":"fe32d33e66c54b0dff9f67744b65d4eec8de2c48354e1fcdb0f101baafa7621a","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":"fe32d33e66c54b0dff9f67744b65d4eec8de2c48354e1fcdb0f101baafa7621a","observed_at":"2026-07-16T04:44:04.234592Z","parent_run_hash":"392cd8ef881a5a54dbb7fbd0e0c490e4811d7ed32379244b3196bd5cb9c5d632","published":"Thu, 16 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:2604.11996v4 Announce Type: replace-cross \nAbstract: Should we trust Large Language Models (LLMs) with high accuracy? LLMs achieve high accuracy on reasoning benchmarks, but correctness alone does not reveal the quality of the reasoning used to produce it. This highlights a fundamental limitation of outcome-based evaluation: models may arrive at correct answers through flawed reasoning, and models with substantially different reasoning capabilities can nevertheless exhibit similar benchmark accuracy, for example due to memorization or over-optimization. In this paper, we ask: given existing benchmarks, can we move beyond outcome-based evaluation to assess the quality of reasoning itself? We seek metrics that (1) differentiate models with similar accuracy and (2) are robust to variations in input prompts and generation configurations. To this end, we propose a reasoning score that evaluates reasoning traces along dimensions such as faithfulness, coherence, utility, and factuality.","title":"Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces","url":"https://arxiv.org/abs/2604.11996","vendor":"arxiv_cs_ai"},"summary":"arXiv:2604.11996v4 Announce Type: replace-cross \nAbstract: Should we trust Large Language Models (LLMs) with high accuracy? LLMs achieve high accuracy on reasoning benchmarks, but correctness alone does not reveal the quality of the reasoning used to produce it. This highlights a fundamental limitation of outcome-based evaluation: models may arrive at correct answers through flawed reasoning, and models with substantially different reasoning capabilities can nevertheless exhibit similar benchmark accuracy, for example due to memorization or over-optimization. In this paper, we ask: given existing benchmarks, can we move beyond outcome-based evaluation to assess the quality of reasoning itself? We seek metrics that (1) differentiate models with similar accuracy and (2) are robust to variations in input prompts and generation configurations. To this end, we propose a reasoning score that evaluates reasoning traces along dimensions such as faithfulness, coherence, utility, and factuality.","title":"Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-16T04:44:04Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2604.11996"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:309f72e064a9c25557378bb2fcafef545a63ccd9d09707043f4654bed84cac4195e96fed709c99038394d9541e601c4b4a9215610df8b47ba25eee62d0954c02","signer":"crovia.substrate","subject":{"observed_at":"2026-07-16T04:44:04Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2604.11996"},"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":"b5305857adde931f9b3827aed793eef7f61ceb44ab41e4f8ab6c76d34f27ea1d","leaf_index":319928,"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":"0da3ede5e16bc1f57b201bbcff758b6caf6611fd4ab13eef51d4f39e982a5aaf","side":"right"},{"sibling":"ea5079041ecb010e49073d7c2c6ccad17436fa6838eeb9945de1bd6dd0947478","side":"right"},{"sibling":"b0951b53e2ba5a8aba50e27aa0451c54054d9e7674ee56c1159393ed588ae53c","side":"right"},{"sibling":"72d7e5da6a36f9422814a95c2a0b9583069c7d6bb7223a8db45599ed4b68818f","side":"left"},{"sibling":"cef8f54590a18a61e37a43b26b1ba6372c594eb3034d971bc89c453ef45cb0d5","side":"left"},{"sibling":"0a406d5b6dcdb2557f337fa4e7fc00a16c274018328cfa5d047964d9b7bd24a7","side":"left"},{"sibling":"ee301003f62e32cb8340b9b36c3b96d6f2fbb9843fae27ab12f5db78a700fd40","side":"right"},{"sibling":"07cc977fce7e64af6ef759252372209956d49c5a495213666eef01b40c0f6d6f","side":"left"},{"sibling":"929619d7bb5abd9d4c015f749565f8d43a371ed382bafe122457d67edb9b8323","side":"left"},{"sibling":"1290775fa2a1fe2079ed83a9c60b8cb479714b6312967daa62f6a91dbbe1cac9","side":"right"},{"sibling":"95977bf2fb44d423026e874e6c275f78b1cf48666d2c472c5e4603d16f4faf7f","side":"right"},{"sibling":"6b83879fdb76b5b7270071f1edfe4d1a059fa9b92653e70fc8c8893214b8f237","side":"right"},{"sibling":"ff49c1d8749b258f58cc33cfaf20d723098ed6860fb62a6779db960d6250915b","side":"right"},{"sibling":"34d85f6ad6cc7dfa79d90e2b9ff99a561bcdc75b0301bbbd3e83861f54535c1e","side":"left"},{"sibling":"f302542c38ba7c3aab7c9280dd60259ecec777dca6e6f71b6f0729b0b8791b72","side":"left"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"3ee6ab8db1878db0b324dd807ca233edd472899b8e90d2c5e018848ea5d12d99","side":"right"},{"sibling":"73a8d1605c15a74de720f0c54b5b4567e3eb8b5999bd8812dc66eedc461540fa","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":320080,"merkle_root":"1e159bceacfdb1f3c930dae410f8759ddc4c762abcfa4a257b150d6f44ab16e0","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260716T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-16T05:38:31Z","sig_algorithm":"ed25519","signature":"c1cd1fc5704d4fec4dee47b29a0e9877f8cfb41eb61dcfd783d82344a15f6e44d80d6cd5128849547b62fe9d9724fc71433319ab6030445b4ac1c9e6bf8a3709","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_5a5379039beabc6b5c846d8df34f1e75d1cf8f3d68b2c0dbbbf201979d636fa1"}}