{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WLMEZUTZ2CS6TSECOVDRKYW2MU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"963ea6220b853fb39c61b5caa79ea6e259339b458cd462c25e8aa1e9e89299f8","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T03:31:09Z","title_canon_sha256":"95a3b0692310d8fbff3711432ba4d7477318ba82b7adc1a37b3ab909f2f9f1ba"},"schema_version":"1.0","source":{"id":"2607.20491","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20491","created_at":"2026-07-24T00:23:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20491v1","created_at":"2026-07-24T00:23:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20491","created_at":"2026-07-24T00:23:18Z"},{"alias_kind":"pith_short_12","alias_value":"WLMEZUTZ2CS6","created_at":"2026-07-24T00:23:18Z"},{"alias_kind":"pith_short_16","alias_value":"WLMEZUTZ2CS6TSEC","created_at":"2026-07-24T00:23:18Z"},{"alias_kind":"pith_short_8","alias_value":"WLMEZUTZ","created_at":"2026-07-24T00:23:18Z"}],"graph_snapshots":[{"event_id":"sha256:3880b2f02119437cb6ca8f8e7686a558c8416ae9e788c919b48ef396eabd8a2f","target":"graph","created_at":"2026-07-24T00:23:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.20491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"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 ","authors_text":"Raffi Khatchadourian","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T03:31:09Z","title":"DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20491","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8dc6ff87aefc0b601f237cdf6b2e14f2de38c9002d672809204f4ac9cca88cf2","target":"record","created_at":"2026-07-24T00:23:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"963ea6220b853fb39c61b5caa79ea6e259339b458cd462c25e8aa1e9e89299f8","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T03:31:09Z","title_canon_sha256":"95a3b0692310d8fbff3711432ba4d7477318ba82b7adc1a37b3ab909f2f9f1ba"},"schema_version":"1.0","source":{"id":"2607.20491","kind":"arxiv","version":1}},"canonical_sha256":"b2d84cd279d0a5e9c88275471562da651748e3daadc19ffa0a656c5d161e863f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2d84cd279d0a5e9c88275471562da651748e3daadc19ffa0a656c5d161e863f","first_computed_at":"2026-07-24T00:23:18.637968Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T00:23:18.637968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pj4JqY3pqf4Yz99rWuebrZvG0STh3GBtBZqTfQFh8qa+AnokXA3yHgImxEDgHES8wtbZHL37Duw3e/DCMytbBw==","signature_status":"signed_v1","signed_at":"2026-07-24T00:23:18.638811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.20491","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dc6ff87aefc0b601f237cdf6b2e14f2de38c9002d672809204f4ac9cca88cf2","sha256:3880b2f02119437cb6ca8f8e7686a558c8416ae9e788c919b48ef396eabd8a2f"],"state_sha256":"1632ef4976d8823faa3c9a68675e2e6fd8740a15f080f86bf66fee7bdaac466f"}