{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:P3HND7KT4T7YOORYYRWKRZZ4EZ","short_pith_number":"pith:P3HND7KT","canonical_record":{"source":{"id":"2505.16734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T14:48:00Z","cross_cats_sorted":[],"title_canon_sha256":"aba839bd3de2cc32bf05c4e2a32bd0650363fd9c7be183bc7de0cccae9ec5f48","abstract_canon_sha256":"b68fc171def2cd8957c6fb91eec70506015772d1e1cbc2c9ba8449cdaca7d0c9"},"schema_version":"1.0"},"canonical_sha256":"7eced1fd53e4ff873a38c46ca8e73c2652cc3e5159bc84bcee72d564b306bbd7","source":{"kind":"arxiv","id":"2505.16734","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16734","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16734v1","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16734","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"pith_short_12","alias_value":"P3HND7KT4T7Y","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"pith_short_16","alias_value":"P3HND7KT4T7YOORY","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"pith_short_8","alias_value":"P3HND7KT","created_at":"2026-07-05T11:07:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:P3HND7KT4T7YOORYYRWKRZZ4EZ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T14:48:00Z","cross_cats_sorted":[],"title_canon_sha256":"aba839bd3de2cc32bf05c4e2a32bd0650363fd9c7be183bc7de0cccae9ec5f48","abstract_canon_sha256":"b68fc171def2cd8957c6fb91eec70506015772d1e1cbc2c9ba8449cdaca7d0c9"},"schema_version":"1.0"},"canonical_sha256":"7eced1fd53e4ff873a38c46ca8e73c2652cc3e5159bc84bcee72d564b306bbd7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:39.937086Z","signature_b64":"pntQ2gJOVFh8g7MMmgKWILn3ZJKfrTREK4JePHobFgGyu+hF0h45UNaHD4REPNrrwb+sbbrCj6xA+RdRl8EqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eced1fd53e4ff873a38c46ca8e73c2652cc3e5159bc84bcee72d564b306bbd7","last_reissued_at":"2026-07-05T11:07:39.936531Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:39.936531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16734","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":"2026-07-05T11:07:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rIuJPlzh0l+rUTeVrX5RJVRQ6ByaEZW4WG9JaOXCr9Z1UguM/bOz0eNkf0L5WDEgvwZfxGNpKzA41qOVId4TBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:44:57.139431Z"},"content_sha256":"dc7f793dff7ea2241fcc1ce294bd545f68d0daeb70495e1a3f3e87d5d95cf0a1","schema_version":"1.0","event_id":"sha256:dc7f793dff7ea2241fcc1ce294bd545f68d0daeb70495e1a3f3e87d5d95cf0a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:P3HND7KT4T7YOORYYRWKRZZ4EZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Maximum Total Correlation Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bang You, Huaping Liu, Jan Peters, Oleg Arenz, Puze Liu","submitted_at":"2025-05-22T14:48:00Z","abstract_excerpt":"Simplicity is a powerful inductive bias. In reinforcement learning, regularization is used for simpler policies, data augmentation for simpler representations, and sparse reward functions for simpler objectives, all that, with the underlying motivation to increase generalizability and robustness by focusing on the essentials. Supplementary to these techniques, we investigate how to promote simple behavior throughout the episode. To that end, we introduce a modification of the reinforcement learning problem that additionally maximizes the total correlation within the induced trajectories. We pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16734","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/2505.16734/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":"2026-07-05T11:07:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1wJQbESLtV/NuykWVqohSsoXqORB6Fu5fHIdnsgjo1+lzDnYUfhAOzI+JYxVsmwcQ5gf0FfY9fJvBo1QTXIjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:44:57.139998Z"},"content_sha256":"a3e7c8508c85887df8100f2198a9c26470b8887bc2975b2657ec524898c0b0c3","schema_version":"1.0","event_id":"sha256:a3e7c8508c85887df8100f2198a9c26470b8887bc2975b2657ec524898c0b0c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P3HND7KT4T7YOORYYRWKRZZ4EZ/bundle.json","state_url":"https://pith.science/pith/P3HND7KT4T7YOORYYRWKRZZ4EZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P3HND7KT4T7YOORYYRWKRZZ4EZ/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":"2026-08-19T16:44:57Z","links":{"resolver":"https://pith.science/pith/P3HND7KT4T7YOORYYRWKRZZ4EZ","bundle":"https://pith.science/pith/P3HND7KT4T7YOORYYRWKRZZ4EZ/bundle.json","state":"https://pith.science/pith/P3HND7KT4T7YOORYYRWKRZZ4EZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P3HND7KT4T7YOORYYRWKRZZ4EZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P3HND7KT4T7YOORYYRWKRZZ4EZ","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":"b68fc171def2cd8957c6fb91eec70506015772d1e1cbc2c9ba8449cdaca7d0c9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T14:48:00Z","title_canon_sha256":"aba839bd3de2cc32bf05c4e2a32bd0650363fd9c7be183bc7de0cccae9ec5f48"},"schema_version":"1.0","source":{"id":"2505.16734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16734","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16734v1","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16734","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"pith_short_12","alias_value":"P3HND7KT4T7Y","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"pith_short_16","alias_value":"P3HND7KT4T7YOORY","created_at":"2026-07-05T11:07:39Z"},{"alias_kind":"pith_short_8","alias_value":"P3HND7KT","created_at":"2026-07-05T11:07:39Z"}],"graph_snapshots":[{"event_id":"sha256:a3e7c8508c85887df8100f2198a9c26470b8887bc2975b2657ec524898c0b0c3","target":"graph","created_at":"2026-07-05T11:07:39Z","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/2505.16734/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Simplicity is a powerful inductive bias. In reinforcement learning, regularization is used for simpler policies, data augmentation for simpler representations, and sparse reward functions for simpler objectives, all that, with the underlying motivation to increase generalizability and robustness by focusing on the essentials. Supplementary to these techniques, we investigate how to promote simple behavior throughout the episode. To that end, we introduce a modification of the reinforcement learning problem that additionally maximizes the total correlation within the induced trajectories. We pr","authors_text":"Bang You, Huaping Liu, Jan Peters, Oleg Arenz, Puze Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T14:48:00Z","title":"Maximum Total Correlation Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16734","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:dc7f793dff7ea2241fcc1ce294bd545f68d0daeb70495e1a3f3e87d5d95cf0a1","target":"record","created_at":"2026-07-05T11:07:39Z","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":"b68fc171def2cd8957c6fb91eec70506015772d1e1cbc2c9ba8449cdaca7d0c9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T14:48:00Z","title_canon_sha256":"aba839bd3de2cc32bf05c4e2a32bd0650363fd9c7be183bc7de0cccae9ec5f48"},"schema_version":"1.0","source":{"id":"2505.16734","kind":"arxiv","version":1}},"canonical_sha256":"7eced1fd53e4ff873a38c46ca8e73c2652cc3e5159bc84bcee72d564b306bbd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7eced1fd53e4ff873a38c46ca8e73c2652cc3e5159bc84bcee72d564b306bbd7","first_computed_at":"2026-07-05T11:07:39.936531Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:39.936531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pntQ2gJOVFh8g7MMmgKWILn3ZJKfrTREK4JePHobFgGyu+hF0h45UNaHD4REPNrrwb+sbbrCj6xA+RdRl8EqAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:39.937086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc7f793dff7ea2241fcc1ce294bd545f68d0daeb70495e1a3f3e87d5d95cf0a1","sha256:a3e7c8508c85887df8100f2198a9c26470b8887bc2975b2657ec524898c0b0c3"],"state_sha256":"737c3de84c206cb27386f908d0579a7f3f3a90a00fb6b08de0ae3a028a83b5e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PGTy29BAhbI9LuupRMZA/RASfxqvvLvBY816DNA1hSyth6cDgCdvWpA9aUcVTJDhpgCPNno+4DtOG1TtTkUwAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T16:44:57.144939Z","bundle_sha256":"773e76ccd79bdb99a97750eeaf8071c31236181e1ec22c4d8e721f33a27838c0"}}