{"_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_ecc5af626db0c066332a16fefe9217ef122a6b7aff47a33eed8a1f9db1500140","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_ecc5af626db0c066332a16fefe9217ef122a6b7aff47a33eed8a1f9db1500140","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"bddc6ed5dae9105cc0466275ab452ae9f4a05f170505222560259a977ea78c8a","published":"Fri, 24 Jul 2026 00:00:00 -0400","receipt_hash":"bddc6ed5dae9105cc0466275ab452ae9f4a05f170505222560259a977ea78c8a","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":"bddc6ed5dae9105cc0466275ab452ae9f4a05f170505222560259a977ea78c8a","observed_at":"2026-07-24T04:43:08.456021Z","parent_run_hash":"b018378f86139a28e6209ec008b31c1282cd1b5c1632dbd43b054c17aa88ab96","published":"Fri, 24 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:2607.20491v1 Announce Type: new \nAbstract: Standard evaluation benchmarks measure what a tool-using agent decides, not whether it arrives at that decision through the same process each time. We introduce DFAH-Bench, a replay benchmark that measures observable behavioral instability in financial agent decision-making across three channels -- tool-call trajectories, evidence contacts, and decision concentration -- none of which require access to hidden reasoning text. Across 8,127 replay episodes spanning 10 models and 3 financial tasks, we find that outcome agreement alone is an incomplete stability signal: frontier models can agree on decisions 95% of the time while following the same tool path only 77% of the time -- an 18-percentage-point gap (95% CI: [0.14, 0.22]) that outcome-only evaluation misses entirely. Among frontier-model case groups with high decision agreement, over 55% exhibit meaningful trajectory divergence. We identify three behavioral profiles: pattern matchers ","title":"DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making","url":"https://arxiv.org/abs/2607.20491","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.20491v1 Announce Type: new \nAbstract: Standard evaluation benchmarks measure what a tool-using agent decides, not whether it arrives at that decision through the same process each time. We introduce DFAH-Bench, a replay benchmark that measures observable behavioral instability in financial agent decision-making across three channels -- tool-call trajectories, evidence contacts, and decision concentration -- none of which require access to hidden reasoning text. Across 8,127 replay episodes spanning 10 models and 3 financial tasks, we find that outcome agreement alone is an incomplete stability signal: frontier models can agree on decisions 95% of the time while following the same tool path only 77% of the time -- an 18-percentage-point gap (95% CI: [0.14, 0.22]) that outcome-only evaluation misses entirely. Among frontier-model case groups with high decision agreement, over 55% exhibit meaningful trajectory divergence. We identify three behavioral profiles: pattern matchers ","title":"DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-24T04:43:08Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.20491"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:ead18e823ed7c37fafbd721c7a51bc4756bac3d73c7f1f29110b26f15766a546555dfc73b8efca477a2886f72ebfa1e0fe95e1feba93f51f3f5d6a5dfebade0f","signer":"crovia.substrate","subject":{"observed_at":"2026-07-24T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.20491"},"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":"8459d26ec54760b81f33c60a98089cf2ad381f0d60ae150d94773107b008e312","leaf_index":346973,"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":"939b60686339a74694cb6f4532d7033967aa861f36b9643911ece1d12e958732","side":"left"},{"sibling":"7440cd0613c158e039e0bd795388f1a86dc3becdd9b022f0f358de1e7e60b1ce","side":"right"},{"sibling":"84bc8f61e7b574b4037d0472e15f5b269f885d0776d2631a9681a3d6d1597bab","side":"left"},{"sibling":"551cb781053af41a3e87eed21be2ededbc92b0379894eda6b90d3ecd9863d807","side":"left"},{"sibling":"04b123a4ab505420518864d060b9f3ea347535cc26ddeb7cf516d35bf34272ab","side":"left"},{"sibling":"f54f8ad11bbf8705675ecd11d73d406ebd6373eea9d33b8d2969150ce62b83d1","side":"right"},{"sibling":"6149df3d1da13abe8a81da069f7bd406a0badf8b62cfc2d62ba645f403037400","side":"left"},{"sibling":"ffd3a55995db3d94b2e5c6432ae18b8c5c13fa05a460ebe646d97e4cfd4c196c","side":"right"},{"sibling":"c212fcc83c532c0321804b72fe72b546946bb055d3d482aab19c43f5bebfbf3f","side":"left"},{"sibling":"da189c159d0789c2229cf3731890cc753832dab1aa83e4bbf0fac01955c22cd8","side":"left"},{"sibling":"3a02ed8ea41a09957282e4e27db74ed88cd675156461abb02acb28e2cd257e63","side":"right"},{"sibling":"d3139af8c5ce235438e1c69e4b7afa44ba09129fd86674968434f23e546f423e","side":"left"},{"sibling":"cb89775a838ee16d10fc8da3213420c2012b4d96e8d55cd49939b0887a4b92d3","side":"right"},{"sibling":"252d30ea8052c3bb6b40bc5cc29fc9b9725343d212f84c08fbbae4215a125b00","side":"right"},{"sibling":"f3e45bceed774d2402fa45d41ff5190f295823bd2f216eb90157884150034693","side":"left"},{"sibling":"3cfa2102c0224815c6f3bf73e6710e24103f43f7bf5da1ca2abad1416d9c0890","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"e871fd7edf9b2ad89bce1609a028f5225eea4d14372169bac242420830f86530","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":347413,"merkle_root":"9efe042c5dd6583dfd3b6a58fbfc289807f60bcf2bd2927f10488a54a8ba11fc","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260724T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-24T05:38:42Z","sig_algorithm":"ed25519","signature":"8633c55f558d42994850505218b2862c6134bad2b1c80d4b80736c2fd3ea7a19690ca3498727a8adbdc47791176128a8d64bef0883b888db809f0477355bd00c","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_ecc5af626db0c066332a16fefe9217ef122a6b7aff47a33eed8a1f9db1500140"}}