{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N4OHBJPZUY3YQXWDKELNP7KX64","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":"9fa00dd8f47d808de6661c1d6c84f7cc691db1e577e588a0baf658927b06f677","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T14:08:33Z","title_canon_sha256":"463cd73e4f41213d55cb9207b0f40840340b94c91c36ffade5317772de819aa3"},"schema_version":"1.0","source":{"id":"2605.21214","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21214","created_at":"2026-05-21T01:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21214v1","created_at":"2026-05-21T01:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21214","created_at":"2026-05-21T01:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"N4OHBJPZUY3Y","created_at":"2026-05-21T01:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"N4OHBJPZUY3YQXWD","created_at":"2026-05-21T01:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"N4OHBJPZ","created_at":"2026-05-21T01:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:53b2131077d885e5b0418e1384946135a63310f0adc35997baf304c146ca8edc","target":"graph","created_at":"2026-05-21T01:05:43Z","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/2605.21214/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) often exhibits high variance across training runs, leading to unreliable performance and posing a major challenge to deployment in real-world domains. In this work, we address the challenge of cross-run policy divergence by formalizing the problem of behavior-consistent RL, where the objective is to obtain policies that are both high-performing and distributionally similar across training runs. Our key observation is that maximum-entropy RL provides a direct mechanism for controlling behavioral divergence by anchoring runs to a common (uniform) prior. We prove that,","authors_text":"Benjamin Eysenbach, Claas Voelcker, Eric Eaton, Liv G. d'Aliberti, Marcel Hussing","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T14:08:33Z","title":"Behavior-Consistent Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21214","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":"sha256:65e18006f9a29cac6626154e33e081614eaa34cc558b8ad18fabe87373131e1c","target":"record","created_at":"2026-05-21T01:05:43Z","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":"9fa00dd8f47d808de6661c1d6c84f7cc691db1e577e588a0baf658927b06f677","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T14:08:33Z","title_canon_sha256":"463cd73e4f41213d55cb9207b0f40840340b94c91c36ffade5317772de819aa3"},"schema_version":"1.0","source":{"id":"2605.21214","kind":"arxiv","version":1}},"canonical_sha256":"6f1c70a5f9a637885ec35116d7fd57f72bc82804ddf5fdcf984d500605c97683","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f1c70a5f9a637885ec35116d7fd57f72bc82804ddf5fdcf984d500605c97683","first_computed_at":"2026-05-21T01:05:43.882271Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:43.882271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/hNWy6p7niAR0ectSIYEIlyH4Sd2g7bNjcBz8PebBSpARbuWQ0xJ6HJcmDD0yhbnMdPEzLH2nrDQVnhbSkCHCA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:43.882914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21214","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65e18006f9a29cac6626154e33e081614eaa34cc558b8ad18fabe87373131e1c","sha256:53b2131077d885e5b0418e1384946135a63310f0adc35997baf304c146ca8edc"],"state_sha256":"7ab34b0f3e739a02705d72e0ef6d03d6463168306c9e5e890960b47f761bf0d5"}