{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3EGUN5OUPCUFLOYANJKCIDYHOA","short_pith_number":"pith:3EGUN5OU","canonical_record":{"source":{"id":"2312.03762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-05T19:00:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1edbc22495ecbb382dcee55c50f1ec77f5e390dcf27a0d1f84139eb63594c7ae","abstract_canon_sha256":"e03fd9ce7e7d35c850e59d129ddfe9259f82891b974f2adcb10773ea128cf827"},"schema_version":"1.0"},"canonical_sha256":"d90d46f5d478a855bb006a54240f077011a2853bf9e581487b06335a67d4459e","source":{"kind":"arxiv","id":"2312.03762","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.03762","created_at":"2026-07-05T07:21:14Z"},{"alias_kind":"arxiv_version","alias_value":"2312.03762v1","created_at":"2026-07-05T07:21:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03762","created_at":"2026-07-05T07:21:14Z"},{"alias_kind":"pith_short_12","alias_value":"3EGUN5OUPCUF","created_at":"2026-07-05T07:21:14Z"},{"alias_kind":"pith_short_16","alias_value":"3EGUN5OUPCUFLOYA","created_at":"2026-07-05T07:21:14Z"},{"alias_kind":"pith_short_8","alias_value":"3EGUN5OU","created_at":"2026-07-05T07:21:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3EGUN5OUPCUFLOYANJKCIDYHOA","target":"record","payload":{"canonical_record":{"source":{"id":"2312.03762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-05T19:00:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1edbc22495ecbb382dcee55c50f1ec77f5e390dcf27a0d1f84139eb63594c7ae","abstract_canon_sha256":"e03fd9ce7e7d35c850e59d129ddfe9259f82891b974f2adcb10773ea128cf827"},"schema_version":"1.0"},"canonical_sha256":"d90d46f5d478a855bb006a54240f077011a2853bf9e581487b06335a67d4459e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:14.563864Z","signature_b64":"tHTw4qV1SSF1UKO10AQwDgKV4Dxe9/BwlIcQKq95QuI08HzXJd+dyyF/hRDrATW9r7PomM/wZ6/i4/b6hwTkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d90d46f5d478a855bb006a54240f077011a2853bf9e581487b06335a67d4459e","last_reissued_at":"2026-07-05T07:21:14.563319Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:14.563319Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.03762","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:21:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LCtqcA76/8ebPe8TLZUC+7GiEgxtj9q0j0xc7mi07Yxv37lziqU5u9EDYhEsNjrvIlFf3zXdB5Gld2UNNUWZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:18:46.261880Z"},"content_sha256":"9316573a5889911355548cc2c9d7054ebf852e20bf43a5ae3996b32f0c62cf5d","schema_version":"1.0","event_id":"sha256:9316573a5889911355548cc2c9d7054ebf852e20bf43a5ae3996b32f0c62cf5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3EGUN5OUPCUFLOYANJKCIDYHOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Colour versus Shape Goal Misgeneralization in Reinforcement Learning: A Case Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Karolis Ramanauskas, \\\"Ozg\\\"ur \\c{S}im\\c{s}ek","submitted_at":"2023-12-05T19:00:46Z","abstract_excerpt":"We explore colour versus shape goal misgeneralization originally demonstrated by Di Langosco et al. (2022) in the Procgen Maze environment, where, given an ambiguous choice, the agents seem to prefer generalization based on colour rather than shape. After training over 1,000 agents in a simplified version of the environment and evaluating them on over 10 million episodes, we conclude that the behaviour can be attributed to the agents learning to detect the goal object through a specific colour channel. This choice is arbitrary. Additionally, we show how, due to underspecification, the preferen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03762","kind":"arxiv","version":1},"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/2312.03762/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":"2026-07-05T07:21:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SO/KuYJMUSMqziKtREIFHSQoIn/BHO7gxwfDBx7jaeFM4Wa9YFFqomVEfy54i/CoeVmxs+BjBcdWKxq1QCTaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:18:46.262250Z"},"content_sha256":"e12b63cef38aa6a53833afb43e5bd231ebd6411ba0f5f7b428acd26a0d6d4ee5","schema_version":"1.0","event_id":"sha256:e12b63cef38aa6a53833afb43e5bd231ebd6411ba0f5f7b428acd26a0d6d4ee5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3EGUN5OUPCUFLOYANJKCIDYHOA/bundle.json","state_url":"https://pith.science/pith/3EGUN5OUPCUFLOYANJKCIDYHOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3EGUN5OUPCUFLOYANJKCIDYHOA/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":"2026-07-06T16:18:46Z","links":{"resolver":"https://pith.science/pith/3EGUN5OUPCUFLOYANJKCIDYHOA","bundle":"https://pith.science/pith/3EGUN5OUPCUFLOYANJKCIDYHOA/bundle.json","state":"https://pith.science/pith/3EGUN5OUPCUFLOYANJKCIDYHOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3EGUN5OUPCUFLOYANJKCIDYHOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3EGUN5OUPCUFLOYANJKCIDYHOA","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":"e03fd9ce7e7d35c850e59d129ddfe9259f82891b974f2adcb10773ea128cf827","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-05T19:00:46Z","title_canon_sha256":"1edbc22495ecbb382dcee55c50f1ec77f5e390dcf27a0d1f84139eb63594c7ae"},"schema_version":"1.0","source":{"id":"2312.03762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.03762","created_at":"2026-07-05T07:21:14Z"},{"alias_kind":"arxiv_version","alias_value":"2312.03762v1","created_at":"2026-07-05T07:21:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03762","created_at":"2026-07-05T07:21:14Z"},{"alias_kind":"pith_short_12","alias_value":"3EGUN5OUPCUF","created_at":"2026-07-05T07:21:14Z"},{"alias_kind":"pith_short_16","alias_value":"3EGUN5OUPCUFLOYA","created_at":"2026-07-05T07:21:14Z"},{"alias_kind":"pith_short_8","alias_value":"3EGUN5OU","created_at":"2026-07-05T07:21:14Z"}],"graph_snapshots":[{"event_id":"sha256:e12b63cef38aa6a53833afb43e5bd231ebd6411ba0f5f7b428acd26a0d6d4ee5","target":"graph","created_at":"2026-07-05T07:21:14Z","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/2312.03762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore colour versus shape goal misgeneralization originally demonstrated by Di Langosco et al. (2022) in the Procgen Maze environment, where, given an ambiguous choice, the agents seem to prefer generalization based on colour rather than shape. After training over 1,000 agents in a simplified version of the environment and evaluating them on over 10 million episodes, we conclude that the behaviour can be attributed to the agents learning to detect the goal object through a specific colour channel. This choice is arbitrary. Additionally, we show how, due to underspecification, the preferen","authors_text":"Karolis Ramanauskas, \\\"Ozg\\\"ur \\c{S}im\\c{s}ek","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-05T19:00:46Z","title":"Colour versus Shape Goal Misgeneralization in Reinforcement Learning: A Case Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03762","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":"sha256:9316573a5889911355548cc2c9d7054ebf852e20bf43a5ae3996b32f0c62cf5d","target":"record","created_at":"2026-07-05T07:21:14Z","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":"e03fd9ce7e7d35c850e59d129ddfe9259f82891b974f2adcb10773ea128cf827","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-05T19:00:46Z","title_canon_sha256":"1edbc22495ecbb382dcee55c50f1ec77f5e390dcf27a0d1f84139eb63594c7ae"},"schema_version":"1.0","source":{"id":"2312.03762","kind":"arxiv","version":1}},"canonical_sha256":"d90d46f5d478a855bb006a54240f077011a2853bf9e581487b06335a67d4459e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d90d46f5d478a855bb006a54240f077011a2853bf9e581487b06335a67d4459e","first_computed_at":"2026-07-05T07:21:14.563319Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:21:14.563319Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tHTw4qV1SSF1UKO10AQwDgKV4Dxe9/BwlIcQKq95QuI08HzXJd+dyyF/hRDrATW9r7PomM/wZ6/i4/b6hwTkDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:21:14.563864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.03762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9316573a5889911355548cc2c9d7054ebf852e20bf43a5ae3996b32f0c62cf5d","sha256:e12b63cef38aa6a53833afb43e5bd231ebd6411ba0f5f7b428acd26a0d6d4ee5"],"state_sha256":"abf6c8dc3585403029abcf0f1b8cef37409b5be1f5e8841a564d17f43ad2fa51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VzD5PtCzOnagv1Hpctpw8thZc0BcXJX1VfyPRbPFidQyNzasOa4+soQg2GrfE+rxBlcQQvo1zbaO6611tpEoDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:18:46.264256Z","bundle_sha256":"46cef15178c99435a70e29e01806c2da334e4166ca4808d2c2ddfb0ae657f129"}}