{"_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_4b46d444edb96f8585984eb624e2d8c899bd93cee383709e9c40826f62f752aa","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_4b46d444edb96f8585984eb624e2d8c899bd93cee383709e9c40826f62f752aa","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"b52e272b66268a5d12cf2252b14f70af158b52494bda592ab6826af93d3ebb7b","published":"Mon, 15 Jun 2026 00:00:00 -0400","receipt_hash":"b52e272b66268a5d12cf2252b14f70af158b52494bda592ab6826af93d3ebb7b","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":"b52e272b66268a5d12cf2252b14f70af158b52494bda592ab6826af93d3ebb7b","observed_at":"2026-06-15T04:43:09.998079Z","parent_run_hash":"ded7a5fa7968821af82d6d8d24b2c1f7e7d776433180609016edbdee95e78c1a","published":"Mon, 15 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:2603.05167v2 Announce Type: replace-cross \nAbstract: Large language models (LLMs) are increasingly used as judges of chain-of-thought (CoT) reasoning, yet it remains unclear whether they can reliably assess process faithfulness rather than merely answer plausibility. We introduce C2-Faith, a benchmark built from PRM800K that explicitly decomposes faithfulness into two complementary dimensions: causality (whether each step logically follows from prior context) and coverage (whether essential intermediate inferences are present). Using controlled perturbations, we construct examples with known causal error positions by replacing a single step with a logically inconsistent variant, and with controlled coverage deletions at varying rates, enabling direct measurement against reference labels. We evaluate three frontier LLM judges across three tasks: binary causal detection, causal step localization, and coverage scoring. Our results reveal that judge reliability is highly task-depende","title":"C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning","url":"https://arxiv.org/abs/2603.05167","vendor":"arxiv_cs_ai"},"summary":"arXiv:2603.05167v2 Announce Type: replace-cross \nAbstract: Large language models (LLMs) are increasingly used as judges of chain-of-thought (CoT) reasoning, yet it remains unclear whether they can reliably assess process faithfulness rather than merely answer plausibility. We introduce C2-Faith, a benchmark built from PRM800K that explicitly decomposes faithfulness into two complementary dimensions: causality (whether each step logically follows from prior context) and coverage (whether essential intermediate inferences are present). Using controlled perturbations, we construct examples with known causal error positions by replacing a single step with a logically inconsistent variant, and with controlled coverage deletions at varying rates, enabling direct measurement against reference labels. We evaluate three frontier LLM judges across three tasks: binary causal detection, causal step localization, and coverage scoring. Our results reveal that judge reliability is highly task-depende","title":"C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-15T04:43:09Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2603.05167"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:73c891ee705db159fa25219dd8c31e6fde423227a01f1f14953de9692b2d6b83a50d382da18db040127bc0887d111c2d573ee38089f051362a7f1970b1c9180e","signer":"crovia.substrate","subject":{"observed_at":"2026-06-15T04:43:09Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2603.05167"},"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":"12d8ea2cf8db2b2546c7fc14d33d6764efa07e47c4283575820fdebc8e787c3c","leaf_index":230145,"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":"a9e5245973909ef91ba346ca30bb396e12e3888befa6e7e4ba06e2f92a467d20","side":"left"},{"sibling":"ccc8a8803d5408032b81d61b15ac5d74c6b81da3b7c1b44a5998134f869bd82c","side":"right"},{"sibling":"b01853bd26c6f47a96e5955b6105a6e19dfe25f1fa285ccaad05e142fc2b59b2","side":"right"},{"sibling":"aaaf142875dda58e31a54377fbd33fd682eb39a25fe382cda58e83bd4415bb50","side":"right"},{"sibling":"05c407a8412443954bb52311d95a1e3651bbd3dfa524ca4796585dec94df6a2f","side":"right"},{"sibling":"430e8ffbeeb70eaf2485dfbe508fd2bd77e31b8b2a5c813d940490016761d859","side":"right"},{"sibling":"a614bf836a660bcfb12080603c3b0e05178718e35625a1678b12d5a40d44e0f7","side":"right"},{"sibling":"0d60a870c104823e0ebbac1aad5395bcb88f28b6928636cce19a16b0cfa21564","side":"right"},{"sibling":"03ebe4791d56166247160f6ee7788c15745bdd7e274c62ec21b2438669941587","side":"left"},{"sibling":"74897e850164dddc689c3c65b33f9bae0268ab0bf429867a4e193d9b9b685040","side":"left"},{"sibling":"bde25d7e94e64717e426a97f6fcb4907e92b5c61fc89d92d7e0947a2249c3f6b","side":"right"},{"sibling":"d10d772a4984cae00e65ab24af21d1d260e475bbaae3f17871859eb705bd3999","side":"right"},{"sibling":"e79159853f2f35ddae8e3247d515e433c534277b287d65bbd77ae989aa4992fa","side":"right"},{"sibling":"3054319f1840cce0eaaf0bc4b1ae38e5bf8b6210927d924a750775cc7d77cca6","side":"right"},{"sibling":"0fd8b5059f279c4a4a6688de2472fdbc25543fee183df19b21dacca880354cff","side":"right"},{"sibling":"a04392fb9f2a3a620840e3b3fecd93d12e6d224e481c162389d8ae64e7194599","side":"left"},{"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":232015,"merkle_root":"62bfb7809bb55667ad7eeebdb48267b9b2c1ee89bb808ea1e6d3a814a15aa402","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260617T133701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-17T13:39:59Z","sig_algorithm":"ed25519","signature":"930a3563c643cc7518d048b12a1f5392a96a5edce49533ba0a56f11b6cc69319bb1c800aacc46b52a6941c4d05dae255a45cac757d6093c971b96852c24f140e","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_4b46d444edb96f8585984eb624e2d8c899bd93cee383709e9c40826f62f752aa"}}