{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:55TDSEUFROACICSEQKMVESBHB5","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":"00625ead66de3940eb589c22ff3b62da5ffd374589b3a407ab8c3c408b726b5c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-18T10:31:19Z","title_canon_sha256":"428d7b8c0a0dedf95e4b92bbf3a76bf383c81b8f24fc1ffa3a1c254bd4cfb6e8"},"schema_version":"1.0","source":{"id":"2602.16346","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.16346","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"arxiv_version","alias_value":"2602.16346v3","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.16346","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"pith_short_12","alias_value":"55TDSEUFROAC","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"pith_short_16","alias_value":"55TDSEUFROACICSE","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"pith_short_8","alias_value":"55TDSEUF","created_at":"2026-05-20T00:02:09Z"}],"graph_snapshots":[{"event_id":"sha256:f330bf8e4a0eb56f805b8aeb83d08b126e530812e0a03bb06c883aea65f179b9","target":"graph","created_at":"2026-05-20T00:02:09Z","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/2602.16346/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test single-prompt instructions, leaving a gap in measuring how agents end up helping with harmful or illegal tasks over multiple turns. We introduce STING (Sequential Testing of Illicit N-step Goal execution), an automated red-teaming framework that constructs a step-by-step illicit plan grounded in a benign persona and iteratively probes a target agent with adaptive follow","authors_text":"Antoine Bosselut, Ayush K Tarun, Maksym Andriushchenko, Murari Mandal, Nivya Talokar","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-18T10:31:19Z","title":"Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.16346","kind":"arxiv","version":3},"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":"sha256:395f1678cfc91a535bc1f6b535f76feda9ad24c96c17df120002d9fef770a109","target":"record","created_at":"2026-05-20T00:02:09Z","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":"00625ead66de3940eb589c22ff3b62da5ffd374589b3a407ab8c3c408b726b5c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-18T10:31:19Z","title_canon_sha256":"428d7b8c0a0dedf95e4b92bbf3a76bf383c81b8f24fc1ffa3a1c254bd4cfb6e8"},"schema_version":"1.0","source":{"id":"2602.16346","kind":"arxiv","version":3}},"canonical_sha256":"ef663912858b80240a4482995248270f579752b49f40b3d56d77076b84c464b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef663912858b80240a4482995248270f579752b49f40b3d56d77076b84c464b3","first_computed_at":"2026-05-20T00:02:09.792419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:09.792419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cwLKfVB1WrI/auVxWfrvY3ZjbdpSaxkdVexafhXfnMPfWQnlLmxDnm+Xi39hrlZdQWm3xhBvpDmcwNX7qT5DDw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:09.793188Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.16346","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:395f1678cfc91a535bc1f6b535f76feda9ad24c96c17df120002d9fef770a109","sha256:f330bf8e4a0eb56f805b8aeb83d08b126e530812e0a03bb06c883aea65f179b9"],"state_sha256":"40cc9ed183177820f37f1339bd571a82853a8d4cd58cf1b7c7af5a4aaf6163f4"}