{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TU5VGOVTAFKYPSGAETRU5ZAVU7","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":"ac40fd8e0e8f1a7bed2123f13cb94d3660ee962254061c2aa5e793d1ee9392d3","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-06T17:59:03Z","title_canon_sha256":"b42b0c60ea6bea2f6df4781087a313e03304e6aeef6a7b4c712deb0133528885"},"schema_version":"1.0","source":{"id":"2304.03279","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03279","created_at":"2026-07-05T06:19:57Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03279v4","created_at":"2026-07-05T06:19:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03279","created_at":"2026-07-05T06:19:57Z"},{"alias_kind":"pith_short_12","alias_value":"TU5VGOVTAFKY","created_at":"2026-07-05T06:19:57Z"},{"alias_kind":"pith_short_16","alias_value":"TU5VGOVTAFKYPSGA","created_at":"2026-07-05T06:19:57Z"},{"alias_kind":"pith_short_8","alias_value":"TU5VGOVT","created_at":"2026-07-05T06:19:57Z"}],"graph_snapshots":[{"event_id":"sha256:2b281283f75603698b68077b753931484f192df995c819c713090fc0c3f61c38","target":"graph","created_at":"2026-07-05T06:19:57Z","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/2304.03279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Artificial agents have traditionally been trained to maximize reward, which may incentivize power-seeking and deception, analogous to how next-token prediction in language models (LMs) may incentivize toxicity. So do agents naturally learn to be Machiavellian? And how do we measure these behaviors in general-purpose models such as GPT-4? Towards answering these questions, we introduce MACHIAVELLI, a benchmark of 134 Choose-Your-Own-Adventure games containing over half a million rich, diverse scenarios that center on social decision-making. Scenario labeling is automated with LMs, which are mor","authors_text":"Alexander Pan, Andy Zou, Dan Hendrycks, Hanlin Zhang, Jonathan Ng, Jun Shern Chan, Nathaniel Li, Scott Emmons, Steven Basart, Thomas Woodside","cross_cats":["cs.AI","cs.CL","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-06T17:59:03Z","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03279","kind":"arxiv","version":4},"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:acd531fa61d52bf3bd8d807b34e0fd40f7111f0613edd0f5570a50340119de13","target":"record","created_at":"2026-07-05T06:19:57Z","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":"ac40fd8e0e8f1a7bed2123f13cb94d3660ee962254061c2aa5e793d1ee9392d3","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-06T17:59:03Z","title_canon_sha256":"b42b0c60ea6bea2f6df4781087a313e03304e6aeef6a7b4c712deb0133528885"},"schema_version":"1.0","source":{"id":"2304.03279","kind":"arxiv","version":4}},"canonical_sha256":"9d3b533ab3015587c8c024e34ee415a7c1cb9fb8502563e5cb778e738d5eab63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d3b533ab3015587c8c024e34ee415a7c1cb9fb8502563e5cb778e738d5eab63","first_computed_at":"2026-07-05T06:19:57.579047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:57.579047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4q6PxD9Si2FN4nVtVLZSOvvev5Ay3N6XyiLd0vz2BqFkc6tqm2EL69TP4s8bjKK9qXLvFRUpF5MpGkOwrWudCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:57.579574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.03279","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acd531fa61d52bf3bd8d807b34e0fd40f7111f0613edd0f5570a50340119de13","sha256:2b281283f75603698b68077b753931484f192df995c819c713090fc0c3f61c38"],"state_sha256":"d788ee5c298c1d8fc583b2ede381860c13fad5c64422fed70fd7ddb78ce72918"}