{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2L7AMY4M6UTBA2EWGJ4X6IS2ET","short_pith_number":"pith:2L7AMY4M","canonical_record":{"source":{"id":"2507.03068","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T17:57:12Z","cross_cats_sorted":[],"title_canon_sha256":"833d11089aa163b45ba4a24fd25f66ce561c57d07b00f72be9c15e20c95af1fe","abstract_canon_sha256":"e27b5ce8d13eabd8f7cb3084ad831d38adc9e84a8a81ae8b4f986093455efe3a"},"schema_version":"1.0"},"canonical_sha256":"d2fe06638cf52610689632797f225a24cef4a41019d08d7659285ce8fd3da2f5","source":{"kind":"arxiv","id":"2507.03068","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03068","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03068v2","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03068","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"2L7AMY4M6UTB","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_16","alias_value":"2L7AMY4M6UTBA2EW","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_8","alias_value":"2L7AMY4M","created_at":"2026-07-05T11:39:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2L7AMY4M6UTBA2EWGJ4X6IS2ET","target":"record","payload":{"canonical_record":{"source":{"id":"2507.03068","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T17:57:12Z","cross_cats_sorted":[],"title_canon_sha256":"833d11089aa163b45ba4a24fd25f66ce561c57d07b00f72be9c15e20c95af1fe","abstract_canon_sha256":"e27b5ce8d13eabd8f7cb3084ad831d38adc9e84a8a81ae8b4f986093455efe3a"},"schema_version":"1.0"},"canonical_sha256":"d2fe06638cf52610689632797f225a24cef4a41019d08d7659285ce8fd3da2f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:12.970660Z","signature_b64":"kpiAxT2p8ehcu0QGCRMq685VTtlAnjrgC5vC2Ab1KJ56JZY+Ywe5ppeivAZKm4JvF8FgjHteh+Ryk1TCQAQJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2fe06638cf52610689632797f225a24cef4a41019d08d7659285ce8fd3da2f5","last_reissued_at":"2026-07-05T11:39:12.970202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:12.970202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.03068","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HbQjTVnPQMVeZc0Y9hsrUOs1FSJPjIzM9C9tcGBSuP0+xZ1cEnQfca0Fdx1ewq9uJqe7BkJ7NVv8XjNrsaD5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T12:16:28.661859Z"},"content_sha256":"ad22bc21a75e6e2e2ec9fe6819c385056f87ab0af3827460e581c2e3492ed3e3","schema_version":"1.0","event_id":"sha256:ad22bc21a75e6e2e2ec9fe6819c385056f87ab0af3827460e581c2e3492ed3e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2L7AMY4M6UTBA2EWGJ4X6IS2ET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mitigating Goal Misgeneralization via Minimax Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christian Schroeder de Witt, David Krueger, Hannah Erlebach, Karim Abdel Sadek, Matthew Farrugia-Roberts, Michael Dennis, Usman Anwar","submitted_at":"2025-07-03T17:57:12Z","abstract_excerpt":"Safe generalization in reinforcement learning requires not only that a learned policy acts capably in new situations, but also that it uses its capabilities towards the pursuit of the designer's intended goal. The latter requirement may fail when a proxy goal incentivizes similar behavior to the intended goal within the training environment, but not in novel deployment environments. This creates the risk that policies will behave as if in pursuit of the proxy goal, rather than the intended goal, in deployment -- a phenomenon known as goal misgeneralization. In this paper, we formalize this pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03068","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.03068/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s9EQvjdBtgycf7R9IYaU8kewE53sJ3+NOj2ec2pZQ0dujDsGda5yfAyXZtQeZIBmi5tNQBKeGrjKZW9IduHlBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T12:16:28.662229Z"},"content_sha256":"cce7af116d2e046b2559180c7e70109564183aecf21dc341f0666696a6878b8d","schema_version":"1.0","event_id":"sha256:cce7af116d2e046b2559180c7e70109564183aecf21dc341f0666696a6878b8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2L7AMY4M6UTBA2EWGJ4X6IS2ET/bundle.json","state_url":"https://pith.science/pith/2L7AMY4M6UTBA2EWGJ4X6IS2ET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2L7AMY4M6UTBA2EWGJ4X6IS2ET/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-11T12:16:28Z","links":{"resolver":"https://pith.science/pith/2L7AMY4M6UTBA2EWGJ4X6IS2ET","bundle":"https://pith.science/pith/2L7AMY4M6UTBA2EWGJ4X6IS2ET/bundle.json","state":"https://pith.science/pith/2L7AMY4M6UTBA2EWGJ4X6IS2ET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2L7AMY4M6UTBA2EWGJ4X6IS2ET/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2L7AMY4M6UTBA2EWGJ4X6IS2ET","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":"e27b5ce8d13eabd8f7cb3084ad831d38adc9e84a8a81ae8b4f986093455efe3a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T17:57:12Z","title_canon_sha256":"833d11089aa163b45ba4a24fd25f66ce561c57d07b00f72be9c15e20c95af1fe"},"schema_version":"1.0","source":{"id":"2507.03068","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03068","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03068v2","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03068","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"2L7AMY4M6UTB","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_16","alias_value":"2L7AMY4M6UTBA2EW","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_8","alias_value":"2L7AMY4M","created_at":"2026-07-05T11:39:12Z"}],"graph_snapshots":[{"event_id":"sha256:cce7af116d2e046b2559180c7e70109564183aecf21dc341f0666696a6878b8d","target":"graph","created_at":"2026-07-05T11:39:12Z","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/2507.03068/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe generalization in reinforcement learning requires not only that a learned policy acts capably in new situations, but also that it uses its capabilities towards the pursuit of the designer's intended goal. The latter requirement may fail when a proxy goal incentivizes similar behavior to the intended goal within the training environment, but not in novel deployment environments. This creates the risk that policies will behave as if in pursuit of the proxy goal, rather than the intended goal, in deployment -- a phenomenon known as goal misgeneralization. In this paper, we formalize this pro","authors_text":"Christian Schroeder de Witt, David Krueger, Hannah Erlebach, Karim Abdel Sadek, Matthew Farrugia-Roberts, Michael Dennis, Usman Anwar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T17:57:12Z","title":"Mitigating Goal Misgeneralization via Minimax Regret"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03068","kind":"arxiv","version":2},"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:ad22bc21a75e6e2e2ec9fe6819c385056f87ab0af3827460e581c2e3492ed3e3","target":"record","created_at":"2026-07-05T11:39:12Z","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":"e27b5ce8d13eabd8f7cb3084ad831d38adc9e84a8a81ae8b4f986093455efe3a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T17:57:12Z","title_canon_sha256":"833d11089aa163b45ba4a24fd25f66ce561c57d07b00f72be9c15e20c95af1fe"},"schema_version":"1.0","source":{"id":"2507.03068","kind":"arxiv","version":2}},"canonical_sha256":"d2fe06638cf52610689632797f225a24cef4a41019d08d7659285ce8fd3da2f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2fe06638cf52610689632797f225a24cef4a41019d08d7659285ce8fd3da2f5","first_computed_at":"2026-07-05T11:39:12.970202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:12.970202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kpiAxT2p8ehcu0QGCRMq685VTtlAnjrgC5vC2Ab1KJ56JZY+Ywe5ppeivAZKm4JvF8FgjHteh+Ryk1TCQAQJCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:12.970660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03068","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad22bc21a75e6e2e2ec9fe6819c385056f87ab0af3827460e581c2e3492ed3e3","sha256:cce7af116d2e046b2559180c7e70109564183aecf21dc341f0666696a6878b8d"],"state_sha256":"c43eb1f6974ad3613ee18a38954979d0459bd54fb18cbece7abc1f9f2cead6d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LVjDVE/Vrvr3FyjaHFG9FJ3zH9f40a9wg0FUDxSdF2f+k6N1E08iXBj+CE8hpEdHrkZuRcrVIRB02h1TCxL7Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T12:16:28.664289Z","bundle_sha256":"8e24a5a3402d3a0cceb51d40b2d85049553ec3d8cffc4f161f3b431cb2443972"}}