{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W3IGHSTK5G7TLKHY3CWKXU3PLE","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":"52178b6897ea7c39e7ab39800bbfb6a1cfc656195451ce6ef06712e6b6212261","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-08T00:11:41Z","title_canon_sha256":"e1d124b3b831ab317204899c5429b6a8d118c22d046fe834b08a79b15453ce77"},"schema_version":"1.0","source":{"id":"2607.06873","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06873","created_at":"2026-07-09T00:19:38Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06873v1","created_at":"2026-07-09T00:19:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06873","created_at":"2026-07-09T00:19:38Z"},{"alias_kind":"pith_short_12","alias_value":"W3IGHSTK5G7T","created_at":"2026-07-09T00:19:38Z"},{"alias_kind":"pith_short_16","alias_value":"W3IGHSTK5G7TLKHY","created_at":"2026-07-09T00:19:38Z"},{"alias_kind":"pith_short_8","alias_value":"W3IGHSTK","created_at":"2026-07-09T00:19:38Z"}],"graph_snapshots":[{"event_id":"sha256:4aa19feea08ffc73b0217ad0e1c3ec634741da266de2a7f0cf20253267ca1e10","target":"graph","created_at":"2026-07-09T00:19:38Z","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/2607.06873/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conversational LLM agents can cause real-world harm when their internal workflows fail, such as completing a transaction without confirmation. Testing these state-dependent failures is difficult because critical boundaries, such as identity checks and confirmation gates, are hidden behind multi-turn conversational prerequisites, rendering them inaccessible to standard tests. We present AgentEval, a black-box testing framework that discovers and stresses these stateful boundaries. AgentEval interacts with an agent to mine a \\emph{conversational workflow graph}, a model of its behavior. Instead ","authors_text":"Boxi Yu, David-Paul Niland, Emir Mu\\~noz, Lionel Briand, Liting Lin, Yuzhong Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-08T00:11:41Z","title":"Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06873","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:ac5cd2e529b557aa31450795c63dbcbb9bc6a216d721103fc43cb35ec93565db","target":"record","created_at":"2026-07-09T00:19:38Z","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":"52178b6897ea7c39e7ab39800bbfb6a1cfc656195451ce6ef06712e6b6212261","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-08T00:11:41Z","title_canon_sha256":"e1d124b3b831ab317204899c5429b6a8d118c22d046fe834b08a79b15453ce77"},"schema_version":"1.0","source":{"id":"2607.06873","kind":"arxiv","version":1}},"canonical_sha256":"b6d063ca6ae9bf35a8f8d8acabd36f5935e939f3aa8ba6ab8dde4879b28c3813","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6d063ca6ae9bf35a8f8d8acabd36f5935e939f3aa8ba6ab8dde4879b28c3813","first_computed_at":"2026-07-09T00:19:38.286081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T00:19:38.286081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EVnHM1mzJue1yz8rSGwLN/ngT8S5GNUNE7AFUOvKwn9g1kbwQ9Wcg9xlpNmUt2y2Ns5/jb1+cQ5rrzv/pFtqBA==","signature_status":"signed_v1","signed_at":"2026-07-09T00:19:38.286826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.06873","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac5cd2e529b557aa31450795c63dbcbb9bc6a216d721103fc43cb35ec93565db","sha256:4aa19feea08ffc73b0217ad0e1c3ec634741da266de2a7f0cf20253267ca1e10"],"state_sha256":"42cd044e4913329e268b413f33a5262d38a1df0f836451c54f7f345dcd11b537"}