{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CJ4XQUPA6L5K523B5XDBBADCRY","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":"5f3f6727e08093bd67d104a76fa7d71b7576cfcd96c5b73a3c514b11ad5b9da9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T17:18:17Z","title_canon_sha256":"f45d26508d651a16ac03b17f7c741a1c979214999e3f7a434ea8186d21175bb5"},"schema_version":"1.0","source":{"id":"2410.06213","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06213","created_at":"2026-07-05T09:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06213v1","created_at":"2026-07-05T09:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06213","created_at":"2026-07-05T09:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"CJ4XQUPA6L5K","created_at":"2026-07-05T09:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"CJ4XQUPA6L5K523B","created_at":"2026-07-05T09:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"CJ4XQUPA","created_at":"2026-07-05T09:17:57Z"}],"graph_snapshots":[{"event_id":"sha256:11708e3e81054a3f4a0095fe7f464596ec301a9504cbb1bcf953c896e47bf707","target":"graph","created_at":"2026-07-05T09:17:57Z","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/2410.06213/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning, if the agent's reward differs from the designers' true utility, even only rarely, the state distribution resulting from the agent's policy can be very bad, in theory and in practice. When RL policies would devolve into undesired behavior, a common countermeasure is KL regularization to a trusted policy (\"Don't do anything I wouldn't do\"). All current cutting-edge language models are RL agents that are KL-regularized to a \"base policy\" that is purely predictive. Unfortunately, we demonstrate that when this base policy is a Bayesian predictive model of a trusted policy","authors_text":"Marcus Hutter, Michael K. Cohen, Stuart Russell, Yoshua Bengio","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T17:18:17Z","title":"RL, but don't do anything I wouldn't do"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06213","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":"sha256:3b40739215e5b9d867ae031a8077852468af91924040e0432bd121971a8f34a3","target":"record","created_at":"2026-07-05T09:17:57Z","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":"5f3f6727e08093bd67d104a76fa7d71b7576cfcd96c5b73a3c514b11ad5b9da9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T17:18:17Z","title_canon_sha256":"f45d26508d651a16ac03b17f7c741a1c979214999e3f7a434ea8186d21175bb5"},"schema_version":"1.0","source":{"id":"2410.06213","kind":"arxiv","version":1}},"canonical_sha256":"12797851e0f2faaeeb61edc61080628e31c89dd52eb6e884b0660bdb95329c8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12797851e0f2faaeeb61edc61080628e31c89dd52eb6e884b0660bdb95329c8b","first_computed_at":"2026-07-05T09:17:57.711978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:57.711978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KMKxwT6gAekXxKkQ2kFWHA+vZImhYVWQGsKDed7+HgdYZDh+hAmimuaVvwXudnG51BXkmsasZvLR2naqBTmVAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:57.712423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06213","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b40739215e5b9d867ae031a8077852468af91924040e0432bd121971a8f34a3","sha256:11708e3e81054a3f4a0095fe7f464596ec301a9504cbb1bcf953c896e47bf707"],"state_sha256":"cb7d8e4d1da30c138f3e1458623703c3a9c717191c565667725d89b682b7d609"}