{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NHW6WUC67VMTQ4AALUDVMDTRBJ","short_pith_number":"pith:NHW6WUC6","canonical_record":{"source":{"id":"2506.05615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T22:03:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4ade1576e8674c4579547e633d5bd3c0d418986b4cd487ca62c58dcaece502d5","abstract_canon_sha256":"4a1cd0c878f46d4c79886d30788b7e13e6271fa827688f989663ec6d470bb22a"},"schema_version":"1.0"},"canonical_sha256":"69edeb505efd593870005d07560e710a4df7a2a2695d6c51652b04fc018a60b7","source":{"kind":"arxiv","id":"2506.05615","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05615","created_at":"2026-07-05T11:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05615v1","created_at":"2026-07-05T11:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05615","created_at":"2026-07-05T11:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"NHW6WUC67VMT","created_at":"2026-07-05T11:20:13Z"},{"alias_kind":"pith_short_16","alias_value":"NHW6WUC67VMTQ4AA","created_at":"2026-07-05T11:20:13Z"},{"alias_kind":"pith_short_8","alias_value":"NHW6WUC6","created_at":"2026-07-05T11:20:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NHW6WUC67VMTQ4AALUDVMDTRBJ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.05615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T22:03:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4ade1576e8674c4579547e633d5bd3c0d418986b4cd487ca62c58dcaece502d5","abstract_canon_sha256":"4a1cd0c878f46d4c79886d30788b7e13e6271fa827688f989663ec6d470bb22a"},"schema_version":"1.0"},"canonical_sha256":"69edeb505efd593870005d07560e710a4df7a2a2695d6c51652b04fc018a60b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:13.203241Z","signature_b64":"POT1o3uJXjGJA7J+GLkACnn0nn0tOfG/lKP1ImNaDMcPQkT6TR+O6g+FJ7Zs86USCzYcfGWD5g5sMdVC0eP5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69edeb505efd593870005d07560e710a4df7a2a2695d6c51652b04fc018a60b7","last_reissued_at":"2026-07-05T11:20:13.202737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:13.202737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.05615","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":"2026-07-05T11:20:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I/akS7wL+p506DNCB4D1zEjo4+JR2rSh3GSI4xiFcwwMUBtTqAy6hAmiz0h0rX44hww32ZaE29erPF8KchRyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:11:23.658210Z"},"content_sha256":"02de5e067e3cff761671e27faac34e6efad7cad542ab0cc5ae068f0922b674d1","schema_version":"1.0","event_id":"sha256:02de5e067e3cff761671e27faac34e6efad7cad542ab0cc5ae068f0922b674d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NHW6WUC67VMTQ4AALUDVMDTRBJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Maximum Entropy Misleads Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ruipeng Zhang, Sicun Gao, Ya-Chien Chang","submitted_at":"2025-06-05T22:03:38Z","abstract_excerpt":"The Maximum Entropy Reinforcement Learning (MaxEnt RL) framework is a leading approach for achieving efficient learning and robust performance across many RL tasks. However, MaxEnt methods have also been shown to struggle with performance-critical control problems in practice, where non-MaxEnt algorithms can successfully learn. In this work, we analyze how the trade-off between robustness and optimality affects the performance of MaxEnt algorithms in complex control tasks: while entropy maximization enhances exploration and robustness, it can also mislead policy optimization, leading to failur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05615","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/2506.05615/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":"2026-07-05T11:20:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JsWl9RVhC8jIHuES22Vu3t3J/DiCh365M6dxEe56sYPxHsYt4Cs+iuAbMEy0rdm4kvIsdUfvGFvJVhRmOrqwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:11:23.658584Z"},"content_sha256":"48deddb4704d6bc09d976b2a9cb194d7cc8434b61ca00dd39500c61c7431fd1a","schema_version":"1.0","event_id":"sha256:48deddb4704d6bc09d976b2a9cb194d7cc8434b61ca00dd39500c61c7431fd1a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NHW6WUC67VMTQ4AALUDVMDTRBJ/bundle.json","state_url":"https://pith.science/pith/NHW6WUC67VMTQ4AALUDVMDTRBJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NHW6WUC67VMTQ4AALUDVMDTRBJ/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":"2026-08-06T14:11:23Z","links":{"resolver":"https://pith.science/pith/NHW6WUC67VMTQ4AALUDVMDTRBJ","bundle":"https://pith.science/pith/NHW6WUC67VMTQ4AALUDVMDTRBJ/bundle.json","state":"https://pith.science/pith/NHW6WUC67VMTQ4AALUDVMDTRBJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NHW6WUC67VMTQ4AALUDVMDTRBJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NHW6WUC67VMTQ4AALUDVMDTRBJ","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":"4a1cd0c878f46d4c79886d30788b7e13e6271fa827688f989663ec6d470bb22a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T22:03:38Z","title_canon_sha256":"4ade1576e8674c4579547e633d5bd3c0d418986b4cd487ca62c58dcaece502d5"},"schema_version":"1.0","source":{"id":"2506.05615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05615","created_at":"2026-07-05T11:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05615v1","created_at":"2026-07-05T11:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05615","created_at":"2026-07-05T11:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"NHW6WUC67VMT","created_at":"2026-07-05T11:20:13Z"},{"alias_kind":"pith_short_16","alias_value":"NHW6WUC67VMTQ4AA","created_at":"2026-07-05T11:20:13Z"},{"alias_kind":"pith_short_8","alias_value":"NHW6WUC6","created_at":"2026-07-05T11:20:13Z"}],"graph_snapshots":[{"event_id":"sha256:48deddb4704d6bc09d976b2a9cb194d7cc8434b61ca00dd39500c61c7431fd1a","target":"graph","created_at":"2026-07-05T11:20:13Z","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/2506.05615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Maximum Entropy Reinforcement Learning (MaxEnt RL) framework is a leading approach for achieving efficient learning and robust performance across many RL tasks. However, MaxEnt methods have also been shown to struggle with performance-critical control problems in practice, where non-MaxEnt algorithms can successfully learn. In this work, we analyze how the trade-off between robustness and optimality affects the performance of MaxEnt algorithms in complex control tasks: while entropy maximization enhances exploration and robustness, it can also mislead policy optimization, leading to failur","authors_text":"Ruipeng Zhang, Sicun Gao, Ya-Chien Chang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T22:03:38Z","title":"When Maximum Entropy Misleads Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05615","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":"sha256:02de5e067e3cff761671e27faac34e6efad7cad542ab0cc5ae068f0922b674d1","target":"record","created_at":"2026-07-05T11:20:13Z","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":"4a1cd0c878f46d4c79886d30788b7e13e6271fa827688f989663ec6d470bb22a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T22:03:38Z","title_canon_sha256":"4ade1576e8674c4579547e633d5bd3c0d418986b4cd487ca62c58dcaece502d5"},"schema_version":"1.0","source":{"id":"2506.05615","kind":"arxiv","version":1}},"canonical_sha256":"69edeb505efd593870005d07560e710a4df7a2a2695d6c51652b04fc018a60b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69edeb505efd593870005d07560e710a4df7a2a2695d6c51652b04fc018a60b7","first_computed_at":"2026-07-05T11:20:13.202737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:13.202737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"POT1o3uJXjGJA7J+GLkACnn0nn0tOfG/lKP1ImNaDMcPQkT6TR+O6g+FJ7Zs86USCzYcfGWD5g5sMdVC0eP5DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:13.203241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02de5e067e3cff761671e27faac34e6efad7cad542ab0cc5ae068f0922b674d1","sha256:48deddb4704d6bc09d976b2a9cb194d7cc8434b61ca00dd39500c61c7431fd1a"],"state_sha256":"9ab286b6ee2663292e1e9146e1d4011937b995336471632083c20e6da1072dbf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"swd3vWPtX7Q1J1POoHARU5wQA6ke9pwutWomBDBqvvh7flY5x2Lfd5CnpaW8ifWURGBD7lBlRNpnqM/4LcTCDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:11:23.662943Z","bundle_sha256":"9e0f5550a03894180a846362848251c6e2b30a4a41abe5d9108b78f77eebb1ea"}}