{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RDZC4P7RESY2HU3BT4BXAC6QZO","short_pith_number":"pith:RDZC4P7R","canonical_record":{"source":{"id":"2105.14111","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-28T21:13:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1a63f77323b27191a8e6412fc2560b7f76f9441d0e12fc9524601d969b228bd3","abstract_canon_sha256":"4e4cc62eb6aa9ec66585a7b85786d4ee4dfe410730b9f09d5a5e36c92e7984dc"},"schema_version":"1.0"},"canonical_sha256":"88f22e3ff124b1a3d3619f03700bd0cb82604f055c8e1b1190344b0ac1f17d20","source":{"kind":"arxiv","id":"2105.14111","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.14111","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"arxiv_version","alias_value":"2105.14111v7","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14111","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"pith_short_12","alias_value":"RDZC4P7RESY2","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"RDZC4P7RESY2HU3B","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"RDZC4P7R","created_at":"2026-07-05T05:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RDZC4P7RESY2HU3BT4BXAC6QZO","target":"record","payload":{"canonical_record":{"source":{"id":"2105.14111","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-28T21:13:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1a63f77323b27191a8e6412fc2560b7f76f9441d0e12fc9524601d969b228bd3","abstract_canon_sha256":"4e4cc62eb6aa9ec66585a7b85786d4ee4dfe410730b9f09d5a5e36c92e7984dc"},"schema_version":"1.0"},"canonical_sha256":"88f22e3ff124b1a3d3619f03700bd0cb82604f055c8e1b1190344b0ac1f17d20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:43.134119Z","signature_b64":"cAIzxSBpC7jIHhyYFF6lQQWK8RfxHgD9JplvoibPTQ9/ht+0OYWXo3njB1jpoxGMOLVNOB14dO0O6B5Q6YP+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88f22e3ff124b1a3d3619f03700bd0cb82604f055c8e1b1190344b0ac1f17d20","last_reissued_at":"2026-07-05T05:31:43.133639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:43.133639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.14111","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:31:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XOjdlIKMMsnJVIDHAHX1SFqjEZ2ZmAQeB/TZB6JNc2Y5Ux5UoPKuTg83myB1A46JHGBls3f7IPi+i2JEtDxiDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:30:04.547169Z"},"content_sha256":"3011b20ba9ed78a34b5e26a27a779ad7890822624a69733c204d7e613420bb78","schema_version":"1.0","event_id":"sha256:3011b20ba9ed78a34b5e26a27a779ad7890822624a69733c204d7e613420bb78"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RDZC4P7RESY2HU3BT4BXAC6QZO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Goal Misgeneralization in Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Krueger, Jack Koch, Jacob Pfau, Laurent Orseau, Lauro Langosco, Lee Sharkey","submitted_at":"2021-05-28T21:13:34Z","abstract_excerpt":"We study goal misgeneralization, a type of out-of-distribution generalization failure in reinforcement learning (RL). Goal misgeneralization failures occur when an RL agent retains its capabilities out-of-distribution yet pursues the wrong goal. For instance, an agent might continue to competently avoid obstacles, but navigate to the wrong place. In contrast, previous works have typically focused on capability generalization failures, where an agent fails to do anything sensible at test time. We formalize this distinction between capability and goal generalization, provide the first empirical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14111","kind":"arxiv","version":7},"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/2105.14111/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":"2026-07-05T05:31:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ssaet2YmHoXZtcWYng2qh5VUFQB2RehHehmI8KNT5IeaTO3dqAYXsK0K1ctEav1GIaEF/5Rupvh9+r51f0jEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:30:04.547640Z"},"content_sha256":"a6f8ca92c09b882f7561ebacd9aba6d1576dfa4bf19e9d708349fe690295cf8a","schema_version":"1.0","event_id":"sha256:a6f8ca92c09b882f7561ebacd9aba6d1576dfa4bf19e9d708349fe690295cf8a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RDZC4P7RESY2HU3BT4BXAC6QZO/bundle.json","state_url":"https://pith.science/pith/RDZC4P7RESY2HU3BT4BXAC6QZO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RDZC4P7RESY2HU3BT4BXAC6QZO/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":"2026-08-06T13:30:04Z","links":{"resolver":"https://pith.science/pith/RDZC4P7RESY2HU3BT4BXAC6QZO","bundle":"https://pith.science/pith/RDZC4P7RESY2HU3BT4BXAC6QZO/bundle.json","state":"https://pith.science/pith/RDZC4P7RESY2HU3BT4BXAC6QZO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RDZC4P7RESY2HU3BT4BXAC6QZO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RDZC4P7RESY2HU3BT4BXAC6QZO","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":"4e4cc62eb6aa9ec66585a7b85786d4ee4dfe410730b9f09d5a5e36c92e7984dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-28T21:13:34Z","title_canon_sha256":"1a63f77323b27191a8e6412fc2560b7f76f9441d0e12fc9524601d969b228bd3"},"schema_version":"1.0","source":{"id":"2105.14111","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.14111","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"arxiv_version","alias_value":"2105.14111v7","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14111","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"pith_short_12","alias_value":"RDZC4P7RESY2","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"RDZC4P7RESY2HU3B","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"RDZC4P7R","created_at":"2026-07-05T05:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:a6f8ca92c09b882f7561ebacd9aba6d1576dfa4bf19e9d708349fe690295cf8a","target":"graph","created_at":"2026-07-05T05:31:43Z","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/2105.14111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study goal misgeneralization, a type of out-of-distribution generalization failure in reinforcement learning (RL). Goal misgeneralization failures occur when an RL agent retains its capabilities out-of-distribution yet pursues the wrong goal. For instance, an agent might continue to competently avoid obstacles, but navigate to the wrong place. In contrast, previous works have typically focused on capability generalization failures, where an agent fails to do anything sensible at test time. We formalize this distinction between capability and goal generalization, provide the first empirical ","authors_text":"David Krueger, Jack Koch, Jacob Pfau, Laurent Orseau, Lauro Langosco, Lee Sharkey","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-28T21:13:34Z","title":"Goal Misgeneralization in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14111","kind":"arxiv","version":7},"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":"sha256:3011b20ba9ed78a34b5e26a27a779ad7890822624a69733c204d7e613420bb78","target":"record","created_at":"2026-07-05T05:31:43Z","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":"4e4cc62eb6aa9ec66585a7b85786d4ee4dfe410730b9f09d5a5e36c92e7984dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-28T21:13:34Z","title_canon_sha256":"1a63f77323b27191a8e6412fc2560b7f76f9441d0e12fc9524601d969b228bd3"},"schema_version":"1.0","source":{"id":"2105.14111","kind":"arxiv","version":7}},"canonical_sha256":"88f22e3ff124b1a3d3619f03700bd0cb82604f055c8e1b1190344b0ac1f17d20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88f22e3ff124b1a3d3619f03700bd0cb82604f055c8e1b1190344b0ac1f17d20","first_computed_at":"2026-07-05T05:31:43.133639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:31:43.133639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cAIzxSBpC7jIHhyYFF6lQQWK8RfxHgD9JplvoibPTQ9/ht+0OYWXo3njB1jpoxGMOLVNOB14dO0O6B5Q6YP+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:31:43.134119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.14111","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3011b20ba9ed78a34b5e26a27a779ad7890822624a69733c204d7e613420bb78","sha256:a6f8ca92c09b882f7561ebacd9aba6d1576dfa4bf19e9d708349fe690295cf8a"],"state_sha256":"b25b500cfd85c088c84857e2e9b6a18374d3ce51e9de5619ec23af8ba821fd87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uBbiSMYrIisEKrEt6EisonpF9MA5vmv02HCyzMoTn5yZrKNZdRj31wOIXz3funf7R0QmeHOeXxVcYQHXcgipCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:30:04.550818Z","bundle_sha256":"7ef80fa80ace7e8b5533c2c15e6f548008477810c7b9d6a557aa00eeca51e6c9"}}