{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GXKWPWVTZGNXIB3IBBY7DG76AG","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":"d4d8e21f7a408c7489330cbeb851998df35403dcc78998f3e3aca4be8eee4f83","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2026-06-24T14:47:47Z","title_canon_sha256":"babada62512dd42cbf92649edaf8cfca7640407f1f9276133e79039c0f942c1e"},"schema_version":"1.0","source":{"id":"2606.25899","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25899","created_at":"2026-06-25T01:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25899v1","created_at":"2026-06-25T01:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25899","created_at":"2026-06-25T01:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"GXKWPWVTZGNX","created_at":"2026-06-25T01:18:42Z"},{"alias_kind":"pith_short_16","alias_value":"GXKWPWVTZGNXIB3I","created_at":"2026-06-25T01:18:42Z"},{"alias_kind":"pith_short_8","alias_value":"GXKWPWVT","created_at":"2026-06-25T01:18:42Z"}],"graph_snapshots":[{"event_id":"sha256:b174339c4bca02416e2949ee04f3b85a2eddca6d83e6808c8b0de92a03a02fa7","target":"graph","created_at":"2026-06-25T01:18:42Z","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/2606.25899/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We evaluate manipulative behavior in six frontier language models across six environments, ranging from negotiation tasks to agentic workflows, resulting in 13{,}590 individual scenarios. Manipulation rates are measured across three axes: framing (mandate honesty or permit manipulation), incentive structure (from no incentives to substantial ones), and task difficulty. Existing benchmarks typically vary a single axis within a single environment, an approach our results show is insufficient. We rank models by manipulation rate and find Spearman rank correlations across environments average $\\rh","authors_text":"Adeeb Zaman, Erik Nordby, Fred Heiding","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2026-06-24T14:47:47Z","title":"Manipulation Is Task-Dependent: A Multi-Axis, Multi-Environment Evaluation of Frontier LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25899","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":"sha256:77adff9d2580ae358c1cd70b8a650d82fb6af7461a240d8b577bc8d7040bf3c9","target":"record","created_at":"2026-06-25T01:18:42Z","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":"d4d8e21f7a408c7489330cbeb851998df35403dcc78998f3e3aca4be8eee4f83","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2026-06-24T14:47:47Z","title_canon_sha256":"babada62512dd42cbf92649edaf8cfca7640407f1f9276133e79039c0f942c1e"},"schema_version":"1.0","source":{"id":"2606.25899","kind":"arxiv","version":1}},"canonical_sha256":"35d567dab3c99b7407680871f19bfe01a0b9d9ee02e2e7f9ca8b1cb1554114dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35d567dab3c99b7407680871f19bfe01a0b9d9ee02e2e7f9ca8b1cb1554114dd","first_computed_at":"2026-06-25T01:18:42.674154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:42.674154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2movlxw0GGUaGLs6yN23FOabrBM1OXdtFXYCjgumn9zsDoWS18YKIDazkMXJpzDLbmH0cQljYto7lDjCvxeMBw==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:42.674648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25899","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77adff9d2580ae358c1cd70b8a650d82fb6af7461a240d8b577bc8d7040bf3c9","sha256:b174339c4bca02416e2949ee04f3b85a2eddca6d83e6808c8b0de92a03a02fa7"],"state_sha256":"a4e0bcbf48b9fadd138a2a8e0034eab15ed8699613de4c23748e899613625444"}