{"_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_9df5d66224e4d2ce7931b2c6076bf3f2730b3c2c6baa9991bd2e4b1f6ba0cf02","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_9df5d66224e4d2ce7931b2c6076bf3f2730b3c2c6baa9991bd2e4b1f6ba0cf02","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"aa51fe68c44f8767c5fd629d3a581db7a3ad1306e612950be5574ea6d9ecc7fc","published":"Thu, 04 Jun 2026 00:00:00 -0400","receipt_hash":"aa51fe68c44f8767c5fd629d3a581db7a3ad1306e612950be5574ea6d9ecc7fc","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":"aa51fe68c44f8767c5fd629d3a581db7a3ad1306e612950be5574ea6d9ecc7fc","observed_at":"2026-06-04T04:43:08.243501Z","parent_run_hash":"298818240313a3c9ce3ace3750dbf55845013dc3bc59aeced6331eccefdb61ac","published":"Thu, 04 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:2601.13735v2 Announce Type: replace \nAbstract: Probabilistic confidence metrics are increasingly adopted as proxies for reasoning quality in Best-of-N selection, under the assumption that higher confidence reflects higher reasoning fidelity. In this work, we challenge this assumption by investigating whether these metrics truly capture inter-step causal dependencies necessary for valid reasoning. We introduce three classes of inter-step causality perturbations that systematically disrupt dependencies between reasoning steps while preserving local fluency. Surprisingly, across diverse model families and reasoning benchmarks, we find that selection accuracy degrades only marginally under these disruptions. Even severe interventions, such as applying hard attention masks that directly prevent the model from attending to prior reasoning steps, do not substantially reduce selection performance. These findings provide strong evidence that current probabilistic metrics are largely insen","title":"Reasoning or Fluency? Dissecting Probabilistic Confidence in Best-of-N Selection","url":"https://arxiv.org/abs/2601.13735","vendor":"arxiv_cs_ai"},"summary":"arXiv:2601.13735v2 Announce Type: replace \nAbstract: Probabilistic confidence metrics are increasingly adopted as proxies for reasoning quality in Best-of-N selection, under the assumption that higher confidence reflects higher reasoning fidelity. In this work, we challenge this assumption by investigating whether these metrics truly capture inter-step causal dependencies necessary for valid reasoning. We introduce three classes of inter-step causality perturbations that systematically disrupt dependencies between reasoning steps while preserving local fluency. Surprisingly, across diverse model families and reasoning benchmarks, we find that selection accuracy degrades only marginally under these disruptions. Even severe interventions, such as applying hard attention masks that directly prevent the model from attending to prior reasoning steps, do not substantially reduce selection performance. These findings provide strong evidence that current probabilistic metrics are largely insen","title":"Reasoning or Fluency? Dissecting Probabilistic Confidence in Best-of-N Selection","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-04T04:43:08Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2601.13735"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:413e684a70be6d668d6e1ae0e367938313be5220f7c3dcdd00ff75aa105545c7a4f0376c427eb899500827b337ec27734ef25d81995352959eb8566a75dd8107","signer":"crovia.substrate","subject":{"observed_at":"2026-06-04T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2601.13735"},"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":"4654330050a45b4cd21677f76eacff66b20b30c1ea826621bcc3ef9b817816de","leaf_index":212768,"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":"bee6689736c164704f2e1ce3a680a05a742e8f8160ec5292e509caffdfb27d3c","side":"right"},{"sibling":"ecef8cddd64431b18ad8cfc7d0695583a6d9689c3a8bd7ed4733a7a441245066","side":"right"},{"sibling":"55de06f778369aa675c5729e26c41c695df663c79a1221e410e9f1e38e7576f1","side":"right"},{"sibling":"d7e045b90887b2e3ddf546329c5ca1311a96fafb22be1b7da53c4fee355b1619","side":"right"},{"sibling":"6b9b65fe4213b2d5b3547b308d66c2e09972089c75da2bcba50fbfcd3005a909","side":"right"},{"sibling":"3ee399cbcf943b5b3b1a99d07b62f2717a69bec6f1a25a258555a29c653d7ec7","side":"left"},{"sibling":"9abe7beed823fcb4fca86168a937bdf567afb433b776352858b68322288bbf2a","side":"right"},{"sibling":"5d10c089cc50333cc6f5ec8f5c37b251f9cdd4252a9604bb46ec83ac720abdd9","side":"right"},{"sibling":"b4e8a5af3a9fdc4bb815270cd541ee4baf09fb1d9e2cccd75c7346558e1f1e4c","side":"left"},{"sibling":"cfb460164a914d1f96a36aa17124b45bb5417829d2adbe5ca48375dbd842ec44","side":"left"},{"sibling":"a84ebc8e894a9893ee34d1afc942d15f28243b926f1e5f9d7f10a3de1e795262","side":"left"},{"sibling":"f8f6bd9da448fa097e2115b71146f61691d9f8807aca291c87c633192a7224e9","side":"left"},{"sibling":"2dca509b3eb767a47cf215d4315f230ce9103a76264412008ae23a349b519ef1","side":"left"},{"sibling":"24d1bb4b13e0e46131b27b70a48e65fcf4e2e14b95e3bb83ade821e9df530f6b","side":"left"},{"sibling":"422bcf7e281ca3a607f3726a5e6b8fabdb85e8b32199b4a86356998e260a0b34","side":"right"},{"sibling":"54a99163a4a62374c3ca6fb46294222f1d4b1a9d0b636e27256b0e093e98239a","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":213053,"merkle_root":"19d104b92c4d7299881c447fb8422611fc9cb8615d37a538959e34a2da7ef55f","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260604T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-04T05:37:49Z","sig_algorithm":"ed25519","signature":"630748e88645187aa3b4d4cb8c872cc146180d0301e4c6656f15f99081d7776432715cea2a997b32b7b3a5216f215d19c1b536c0b093100ec843fa0bd65f2101","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_9df5d66224e4d2ce7931b2c6076bf3f2730b3c2c6baa9991bd2e4b1f6ba0cf02"}}