{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3N46Y3S6CCSBF7CGZJHGL5ZRPE","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":"94c4388e873a39ad51a169d2066e57112afc20569cefd177b820f41e0f9697d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-03T03:17:26Z","title_canon_sha256":"067be0a5c96163bdbe702273aecef119b5c02ee8475bea3264d9208619937d4f"},"schema_version":"1.0","source":{"id":"2606.04394","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04394","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04394v1","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04394","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"3N46Y3S6CCSB","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"3N46Y3S6CCSBF7CG","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"3N46Y3S6","created_at":"2026-06-04T01:09:06Z"}],"graph_snapshots":[{"event_id":"sha256:ee29600c3934884913d8714da1afe5800ad96d74ac9d735ceade7612c0cd209d","target":"graph","created_at":"2026-06-04T01:09:06Z","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/2606.04394/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model chatbots are increasingly deployed in organizational settings such as healthcare, finance, and public services. Evaluating policy alignment is therefore critical to reliable chatbot deployment. By analyzing real-world user queries, we identify composed-policy violation is prevalent in various chatbots but overlooked by existing benchmarks. This paper present COPAL, an automated tool for evaluating composed-policy alignment in chatbots. COPAL efficiently generates queries that trigger composed-policy failures in chatbots via empirically derived interaction patterns and expl","authors_text":"Xiaoyu Wang, Xuan Wang, Yangfan Zhou, Yilun Li, Yingjie Liu, Yongxiang Hu, Yunlei Wei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-03T03:17:26Z","title":"Beyond Single-Policy: Evaluating Composed Organization-Specific Policy Alignment in LLM Chatbots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04394","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:fb3a352f7b932b721cfc0a792d72daef81bf955ea4df082d4580b608647b0476","target":"record","created_at":"2026-06-04T01:09:06Z","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":"94c4388e873a39ad51a169d2066e57112afc20569cefd177b820f41e0f9697d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-03T03:17:26Z","title_canon_sha256":"067be0a5c96163bdbe702273aecef119b5c02ee8475bea3264d9208619937d4f"},"schema_version":"1.0","source":{"id":"2606.04394","kind":"arxiv","version":1}},"canonical_sha256":"db79ec6e5e10a412fc46ca4e65f7317937a5bced3117f018df3b57624171f23f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db79ec6e5e10a412fc46ca4e65f7317937a5bced3117f018df3b57624171f23f","first_computed_at":"2026-06-04T01:09:06.440026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:06.440026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xWbq55nE9YesXc7Luuo726bGgCjLSx9EKDemvJT4EkOrbWQ6ogQp9jlWslzEVxECIH1KliiVjPUi7yNqfRq3DQ==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:06.440449Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04394","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb3a352f7b932b721cfc0a792d72daef81bf955ea4df082d4580b608647b0476","sha256:ee29600c3934884913d8714da1afe5800ad96d74ac9d735ceade7612c0cd209d"],"state_sha256":"e94b3d6bf7a4f382362e7f9adec1015334a6f140e00c2098f10a2469a1505cc5"}