{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ABSOZZU7EVMIDA7DXRBX3RAIKL","short_pith_number":"pith:ABSOZZU7","canonical_record":{"source":{"id":"2306.02419","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-04T17:51:37Z","cross_cats_sorted":[],"title_canon_sha256":"f634f792f2d0aeec6559e113f2debd3639f3792c9d5c0ccaaf3627c414efe89f","abstract_canon_sha256":"4437d15c1169f4e1cc5b93b864b05dfc5f90599c90b1182f4a7bffbeb2c3218e"},"schema_version":"1.0"},"canonical_sha256":"0064ece69f25588183e3bc437dc40852e28df4422702e17c698f6979bb89ce48","source":{"kind":"arxiv","id":"2306.02419","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02419","created_at":"2026-07-05T08:35:35Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02419v2","created_at":"2026-07-05T08:35:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02419","created_at":"2026-07-05T08:35:35Z"},{"alias_kind":"pith_short_12","alias_value":"ABSOZZU7EVMI","created_at":"2026-07-05T08:35:35Z"},{"alias_kind":"pith_short_16","alias_value":"ABSOZZU7EVMIDA7D","created_at":"2026-07-05T08:35:35Z"},{"alias_kind":"pith_short_8","alias_value":"ABSOZZU7","created_at":"2026-07-05T08:35:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ABSOZZU7EVMIDA7DXRBX3RAIKL","target":"record","payload":{"canonical_record":{"source":{"id":"2306.02419","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-04T17:51:37Z","cross_cats_sorted":[],"title_canon_sha256":"f634f792f2d0aeec6559e113f2debd3639f3792c9d5c0ccaaf3627c414efe89f","abstract_canon_sha256":"4437d15c1169f4e1cc5b93b864b05dfc5f90599c90b1182f4a7bffbeb2c3218e"},"schema_version":"1.0"},"canonical_sha256":"0064ece69f25588183e3bc437dc40852e28df4422702e17c698f6979bb89ce48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:35.440851Z","signature_b64":"7vFwwJi2QZJygDylGs33T5Cd2kmeKPqOZRHdt6j/9ckALX4hHL19rWChmpSLFIZES8/7Yy4ClaMoRlkQhjpGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0064ece69f25588183e3bc437dc40852e28df4422702e17c698f6979bb89ce48","last_reissued_at":"2026-07-05T08:35:35.440453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:35.440453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.02419","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":"2026-07-05T08:35:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l3V1LDnOqnN4P4g4y+q7KbjEQurYXorseQYaGzgQtzLWiO+ocfHJNJcUn/issXFrUbBZDRrn5b4traE8UZaYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:02:05.898006Z"},"content_sha256":"33fe050e04252d505824beab6f5ff592d4b7e8d050ad47d369d4f4fb3c350ab8","schema_version":"1.0","event_id":"sha256:33fe050e04252d505824beab6f5ff592d4b7e8d050ad47d369d4f4fb3c350ab8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ABSOZZU7EVMIDA7DXRBX3RAIKL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Frans A. Oliehoek, Matthijs T. J. Spaan, Miguel Suau","submitted_at":"2023-06-04T17:51:37Z","abstract_excerpt":"Reinforcement learning agents tend to develop habits that are effective only under specific policies. Following an initial exploration phase where agents try out different actions, they eventually converge onto a particular policy. As this occurs, the distribution over state-action trajectories becomes narrower, leading agents to repeatedly experience the same transitions. This repetitive exposure fosters spurious correlations between certain observations and rewards. Agents may then pick up on these correlations and develop simplistic habits tailored to the specific set of trajectories dictat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02419","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/2306.02419/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":"2026-07-05T08:35:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lylyaYS/WDoSHAT3xBzUOGl6WpX/14yngX8pbvH+/+UN3Btq6EC4alS0KSfyYUo2unj3MtddUXVW2xocReKOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:02:05.898512Z"},"content_sha256":"3cf604794c9bee92f5ef574f5bf455483d51087f77f886065f2ce8ea1dc4ee70","schema_version":"1.0","event_id":"sha256:3cf604794c9bee92f5ef574f5bf455483d51087f77f886065f2ce8ea1dc4ee70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ABSOZZU7EVMIDA7DXRBX3RAIKL/bundle.json","state_url":"https://pith.science/pith/ABSOZZU7EVMIDA7DXRBX3RAIKL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ABSOZZU7EVMIDA7DXRBX3RAIKL/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":"2026-08-22T08:02:05Z","links":{"resolver":"https://pith.science/pith/ABSOZZU7EVMIDA7DXRBX3RAIKL","bundle":"https://pith.science/pith/ABSOZZU7EVMIDA7DXRBX3RAIKL/bundle.json","state":"https://pith.science/pith/ABSOZZU7EVMIDA7DXRBX3RAIKL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ABSOZZU7EVMIDA7DXRBX3RAIKL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ABSOZZU7EVMIDA7DXRBX3RAIKL","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":"4437d15c1169f4e1cc5b93b864b05dfc5f90599c90b1182f4a7bffbeb2c3218e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-04T17:51:37Z","title_canon_sha256":"f634f792f2d0aeec6559e113f2debd3639f3792c9d5c0ccaaf3627c414efe89f"},"schema_version":"1.0","source":{"id":"2306.02419","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02419","created_at":"2026-07-05T08:35:35Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02419v2","created_at":"2026-07-05T08:35:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02419","created_at":"2026-07-05T08:35:35Z"},{"alias_kind":"pith_short_12","alias_value":"ABSOZZU7EVMI","created_at":"2026-07-05T08:35:35Z"},{"alias_kind":"pith_short_16","alias_value":"ABSOZZU7EVMIDA7D","created_at":"2026-07-05T08:35:35Z"},{"alias_kind":"pith_short_8","alias_value":"ABSOZZU7","created_at":"2026-07-05T08:35:35Z"}],"graph_snapshots":[{"event_id":"sha256:3cf604794c9bee92f5ef574f5bf455483d51087f77f886065f2ce8ea1dc4ee70","target":"graph","created_at":"2026-07-05T08:35:35Z","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/2306.02419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning agents tend to develop habits that are effective only under specific policies. Following an initial exploration phase where agents try out different actions, they eventually converge onto a particular policy. As this occurs, the distribution over state-action trajectories becomes narrower, leading agents to repeatedly experience the same transitions. This repetitive exposure fosters spurious correlations between certain observations and rewards. Agents may then pick up on these correlations and develop simplistic habits tailored to the specific set of trajectories dictat","authors_text":"Frans A. Oliehoek, Matthijs T. J. Spaan, Miguel Suau","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-04T17:51:37Z","title":"Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02419","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":"sha256:33fe050e04252d505824beab6f5ff592d4b7e8d050ad47d369d4f4fb3c350ab8","target":"record","created_at":"2026-07-05T08:35:35Z","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":"4437d15c1169f4e1cc5b93b864b05dfc5f90599c90b1182f4a7bffbeb2c3218e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-04T17:51:37Z","title_canon_sha256":"f634f792f2d0aeec6559e113f2debd3639f3792c9d5c0ccaaf3627c414efe89f"},"schema_version":"1.0","source":{"id":"2306.02419","kind":"arxiv","version":2}},"canonical_sha256":"0064ece69f25588183e3bc437dc40852e28df4422702e17c698f6979bb89ce48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0064ece69f25588183e3bc437dc40852e28df4422702e17c698f6979bb89ce48","first_computed_at":"2026-07-05T08:35:35.440453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:35.440453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7vFwwJi2QZJygDylGs33T5Cd2kmeKPqOZRHdt6j/9ckALX4hHL19rWChmpSLFIZES8/7Yy4ClaMoRlkQhjpGBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:35.440851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02419","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33fe050e04252d505824beab6f5ff592d4b7e8d050ad47d369d4f4fb3c350ab8","sha256:3cf604794c9bee92f5ef574f5bf455483d51087f77f886065f2ce8ea1dc4ee70"],"state_sha256":"f72acaa2ab9e5dd37f0634d129a74d70cd4b5ca3153734e0d451d642b18ae890"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lKRwItJEP1cDjhDWHbHkhQwJ/1w9OqwURTKklDHiOmFBv7c5Cg94ZsLCfwv2ZIRhtJwUhM3W20CUxEQ5UhiVDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T08:02:05.902968Z","bundle_sha256":"f7b1040a7751c3ad26f875a2b3b9b99f2d973fe4037e2f3f777ba42e43fde5e4"}}