{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:G7QVK74S3BDCR46RZOY77CU34E","short_pith_number":"pith:G7QVK74S","canonical_record":{"source":{"id":"2607.03168","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-03T10:09:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f9d27ce2bc4f48e9eca54cd9452deda506eaa384477c4d9ff5e5792fd6edac6b","abstract_canon_sha256":"7f723b0216db9e985b115b28382f955f0ff824b535e6766bd3865fe462bb2bb9"},"schema_version":"1.0"},"canonical_sha256":"37e1557f92d84628f3d1cbb1ff8a9be1151b825731c4c391226f9c579dd1bc1c","source":{"kind":"arxiv","id":"2607.03168","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03168","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03168v1","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03168","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"pith_short_12","alias_value":"G7QVK74S3BDC","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"pith_short_16","alias_value":"G7QVK74S3BDCR46R","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"pith_short_8","alias_value":"G7QVK74S","created_at":"2026-07-07T01:16:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:G7QVK74S3BDCR46RZOY77CU34E","target":"record","payload":{"canonical_record":{"source":{"id":"2607.03168","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-03T10:09:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f9d27ce2bc4f48e9eca54cd9452deda506eaa384477c4d9ff5e5792fd6edac6b","abstract_canon_sha256":"7f723b0216db9e985b115b28382f955f0ff824b535e6766bd3865fe462bb2bb9"},"schema_version":"1.0"},"canonical_sha256":"37e1557f92d84628f3d1cbb1ff8a9be1151b825731c4c391226f9c579dd1bc1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:45.458027Z","signature_b64":"+p5wvQX17hD2mnkZ7wKbj1CGgSKQNMVd2Tdv2oJYYyRasmKqKwiI5ZLKhnHqL0wN7mkjpyrHczShiedxf9EFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37e1557f92d84628f3d1cbb1ff8a9be1151b825731c4c391226f9c579dd1bc1c","last_reissued_at":"2026-07-07T01:16:45.457617Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:45.457617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.03168","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":"2026-07-07T01:16:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cp5Ebk6zUKd55hbmnhrPI3OK8AXt4wcOSnfQCU+5rqO+b+GnPDIHCkH0kMTxicDEeVBnMLy89uq0Do3a5XXdBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:27:23.772542Z"},"content_sha256":"047acee6ce4f1037338c2bd6210c4122caa3a6609fad32543e5f6df14fade1a7","schema_version":"1.0","event_id":"sha256:047acee6ce4f1037338c2bd6210c4122caa3a6609fad32543e5f6df14fade1a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:G7QVK74S3BDCR46RZOY77CU34E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Entropy Regularization Improves Policy Robustness in Continuous-Time Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"David \\v{S}i\\v{s}ka, Fernando Acero, Jialun Cao, Yufei Zhang","submitted_at":"2026-07-03T10:09:39Z","abstract_excerpt":"Entropy regularization is widely used in continuous-time reinforcement learning (RL) to reduce sensitivity to environmental perturbations, yet its robustness benefits lack a rigorous theoretical foundation. This paper establishes the first robustness guarantees for entropy-regularized continuous-time Markov decision processes. We show that maximizing an entropy-regularized objective yields a lower bound on a worst-case robust RL problem with joint reward and transition perturbations. We analytically characterize the induced robust sets and prove that they expand monotonically with the regulari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03168","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/2607.03168/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":"2026-07-07T01:16:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BbbizcKexYwuKFh4HfTSJKBMHQMkf6GDFFvOpvz4djRJRcE1lzuoTsbOS3Q2z5eIcdMtuVvCSVz/hOSebIZwAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:27:23.773113Z"},"content_sha256":"87a2a3a3f0fb3608a8593e6c1066388d9caf3529394bf60b34943c29b4ff9cb6","schema_version":"1.0","event_id":"sha256:87a2a3a3f0fb3608a8593e6c1066388d9caf3529394bf60b34943c29b4ff9cb6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G7QVK74S3BDCR46RZOY77CU34E/bundle.json","state_url":"https://pith.science/pith/G7QVK74S3BDCR46RZOY77CU34E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G7QVK74S3BDCR46RZOY77CU34E/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":"2026-08-14T19:27:23Z","links":{"resolver":"https://pith.science/pith/G7QVK74S3BDCR46RZOY77CU34E","bundle":"https://pith.science/pith/G7QVK74S3BDCR46RZOY77CU34E/bundle.json","state":"https://pith.science/pith/G7QVK74S3BDCR46RZOY77CU34E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G7QVK74S3BDCR46RZOY77CU34E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G7QVK74S3BDCR46RZOY77CU34E","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":"7f723b0216db9e985b115b28382f955f0ff824b535e6766bd3865fe462bb2bb9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-03T10:09:39Z","title_canon_sha256":"f9d27ce2bc4f48e9eca54cd9452deda506eaa384477c4d9ff5e5792fd6edac6b"},"schema_version":"1.0","source":{"id":"2607.03168","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03168","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03168v1","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03168","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"pith_short_12","alias_value":"G7QVK74S3BDC","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"pith_short_16","alias_value":"G7QVK74S3BDCR46R","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"pith_short_8","alias_value":"G7QVK74S","created_at":"2026-07-07T01:16:45Z"}],"graph_snapshots":[{"event_id":"sha256:87a2a3a3f0fb3608a8593e6c1066388d9caf3529394bf60b34943c29b4ff9cb6","target":"graph","created_at":"2026-07-07T01:16:45Z","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/2607.03168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entropy regularization is widely used in continuous-time reinforcement learning (RL) to reduce sensitivity to environmental perturbations, yet its robustness benefits lack a rigorous theoretical foundation. This paper establishes the first robustness guarantees for entropy-regularized continuous-time Markov decision processes. We show that maximizing an entropy-regularized objective yields a lower bound on a worst-case robust RL problem with joint reward and transition perturbations. We analytically characterize the induced robust sets and prove that they expand monotonically with the regulari","authors_text":"David \\v{S}i\\v{s}ka, Fernando Acero, Jialun Cao, Yufei Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-03T10:09:39Z","title":"Entropy Regularization Improves Policy Robustness in Continuous-Time Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03168","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":"sha256:047acee6ce4f1037338c2bd6210c4122caa3a6609fad32543e5f6df14fade1a7","target":"record","created_at":"2026-07-07T01:16:45Z","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":"7f723b0216db9e985b115b28382f955f0ff824b535e6766bd3865fe462bb2bb9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-03T10:09:39Z","title_canon_sha256":"f9d27ce2bc4f48e9eca54cd9452deda506eaa384477c4d9ff5e5792fd6edac6b"},"schema_version":"1.0","source":{"id":"2607.03168","kind":"arxiv","version":1}},"canonical_sha256":"37e1557f92d84628f3d1cbb1ff8a9be1151b825731c4c391226f9c579dd1bc1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37e1557f92d84628f3d1cbb1ff8a9be1151b825731c4c391226f9c579dd1bc1c","first_computed_at":"2026-07-07T01:16:45.457617Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T01:16:45.457617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+p5wvQX17hD2mnkZ7wKbj1CGgSKQNMVd2Tdv2oJYYyRasmKqKwiI5ZLKhnHqL0wN7mkjpyrHczShiedxf9EFAg==","signature_status":"signed_v1","signed_at":"2026-07-07T01:16:45.458027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03168","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:047acee6ce4f1037338c2bd6210c4122caa3a6609fad32543e5f6df14fade1a7","sha256:87a2a3a3f0fb3608a8593e6c1066388d9caf3529394bf60b34943c29b4ff9cb6"],"state_sha256":"96fad8d98c3af5cdfca5053a4c5e650ef8e31a56958766c2cd648937a8fefd1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gR5FgJPjuWcsLd+31hxDE1PSGd0Th5cJaTc+oe73TTwoXHypshRwhez8+j2EARHEZvNjlD09BEXQqzfWAkPHDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:27:23.777129Z","bundle_sha256":"60d38c63409b315b38d7d64cabc1ecb41f8c0eaae7ea22aab5415222410fdad3"}}