{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RGHVBN5U7ILXN54VE6LQA6BKOE","short_pith_number":"pith:RGHVBN5U","canonical_record":{"source":{"id":"2405.11432","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-19T03:27:31Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"7ddc5f486d23b6579000ddd52356c562e05dc50130b79b326df7057ecb9698d1","abstract_canon_sha256":"3a2ebc415ee03a96d505b52d165925f0bd70f09e5ebb431db3b37fe6d17435da"},"schema_version":"1.0"},"canonical_sha256":"898f50b7b4fa1776f795279700782a7131d53712b7d9ab8ca163723d6d3d0a22","source":{"kind":"arxiv","id":"2405.11432","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11432","created_at":"2026-07-05T10:10:07Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11432v3","created_at":"2026-07-05T10:10:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11432","created_at":"2026-07-05T10:10:07Z"},{"alias_kind":"pith_short_12","alias_value":"RGHVBN5U7ILX","created_at":"2026-07-05T10:10:07Z"},{"alias_kind":"pith_short_16","alias_value":"RGHVBN5U7ILXN54V","created_at":"2026-07-05T10:10:07Z"},{"alias_kind":"pith_short_8","alias_value":"RGHVBN5U","created_at":"2026-07-05T10:10:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RGHVBN5U7ILXN54VE6LQA6BKOE","target":"record","payload":{"canonical_record":{"source":{"id":"2405.11432","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-19T03:27:31Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"7ddc5f486d23b6579000ddd52356c562e05dc50130b79b326df7057ecb9698d1","abstract_canon_sha256":"3a2ebc415ee03a96d505b52d165925f0bd70f09e5ebb431db3b37fe6d17435da"},"schema_version":"1.0"},"canonical_sha256":"898f50b7b4fa1776f795279700782a7131d53712b7d9ab8ca163723d6d3d0a22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:07.570879Z","signature_b64":"lsT2GwUZPY4/fkskrPpNHsBFoBEC/KooY9Zbq2PEIMac2B+ohzT3nz1/uISbEdYMxxzztQb0BpXgx1wGa5soAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"898f50b7b4fa1776f795279700782a7131d53712b7d9ab8ca163723d6d3d0a22","last_reissued_at":"2026-07-05T10:10:07.570402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:07.570402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.11432","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:10:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eu/W8NWK/AKsk7Rn8+Mi2bD7+iN1oFNLGbKmiXnLq1eXDFjH9i5KqFzDeZQfWnnEDAZbNHLhwrxihrHHJ5RUDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:49:42.045858Z"},"content_sha256":"18f6c06dc662dc748e65f20b03a5acce82aa9d2898b04786341e4b07856bb610","schema_version":"1.0","event_id":"sha256:18f6c06dc662dc748e65f20b03a5acce82aa9d2898b04786341e4b07856bb610"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RGHVBN5U7ILXN54VE6LQA6BKOE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Robust Reinforcement Learning with Lipschitz-Bounded Policy Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ian R. Manchester, Nicholas H. Barbara, Ruigang Wang","submitted_at":"2024-05-19T03:27:31Z","abstract_excerpt":"This paper presents a study of robust policy networks in deep reinforcement learning. We investigate the benefits of policy parameterizations that naturally satisfy constraints on their Lipschitz bound, analyzing their empirical performance and robustness on two representative problems: pendulum swing-up and Atari Pong. We illustrate that policy networks with smaller Lipschitz bounds are more robust to disturbances, random noise, and targeted adversarial attacks than unconstrained policies composed of vanilla multi-layer perceptrons or convolutional neural networks. However, the structure of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11432","kind":"arxiv","version":3},"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/2405.11432/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":"2026-07-05T10:10:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YQZO2bIeDfmJwUnEMQY5Jg4ZAe5Ubz1fh83uyi9lPeUS46C+xkfMt7gGsd1+BjIUN7V+ghF1+6m2e+e1rLkfBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:49:42.046528Z"},"content_sha256":"0aee9c54570cff2adb60b083855d2fd44dea74a024bc22c36bc51f138bcbcf2c","schema_version":"1.0","event_id":"sha256:0aee9c54570cff2adb60b083855d2fd44dea74a024bc22c36bc51f138bcbcf2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RGHVBN5U7ILXN54VE6LQA6BKOE/bundle.json","state_url":"https://pith.science/pith/RGHVBN5U7ILXN54VE6LQA6BKOE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RGHVBN5U7ILXN54VE6LQA6BKOE/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":"2026-08-20T20:49:42Z","links":{"resolver":"https://pith.science/pith/RGHVBN5U7ILXN54VE6LQA6BKOE","bundle":"https://pith.science/pith/RGHVBN5U7ILXN54VE6LQA6BKOE/bundle.json","state":"https://pith.science/pith/RGHVBN5U7ILXN54VE6LQA6BKOE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RGHVBN5U7ILXN54VE6LQA6BKOE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RGHVBN5U7ILXN54VE6LQA6BKOE","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":"3a2ebc415ee03a96d505b52d165925f0bd70f09e5ebb431db3b37fe6d17435da","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-19T03:27:31Z","title_canon_sha256":"7ddc5f486d23b6579000ddd52356c562e05dc50130b79b326df7057ecb9698d1"},"schema_version":"1.0","source":{"id":"2405.11432","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11432","created_at":"2026-07-05T10:10:07Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11432v3","created_at":"2026-07-05T10:10:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11432","created_at":"2026-07-05T10:10:07Z"},{"alias_kind":"pith_short_12","alias_value":"RGHVBN5U7ILX","created_at":"2026-07-05T10:10:07Z"},{"alias_kind":"pith_short_16","alias_value":"RGHVBN5U7ILXN54V","created_at":"2026-07-05T10:10:07Z"},{"alias_kind":"pith_short_8","alias_value":"RGHVBN5U","created_at":"2026-07-05T10:10:07Z"}],"graph_snapshots":[{"event_id":"sha256:0aee9c54570cff2adb60b083855d2fd44dea74a024bc22c36bc51f138bcbcf2c","target":"graph","created_at":"2026-07-05T10:10:07Z","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/2405.11432/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a study of robust policy networks in deep reinforcement learning. We investigate the benefits of policy parameterizations that naturally satisfy constraints on their Lipschitz bound, analyzing their empirical performance and robustness on two representative problems: pendulum swing-up and Atari Pong. We illustrate that policy networks with smaller Lipschitz bounds are more robust to disturbances, random noise, and targeted adversarial attacks than unconstrained policies composed of vanilla multi-layer perceptrons or convolutional neural networks. However, the structure of t","authors_text":"Ian R. Manchester, Nicholas H. Barbara, Ruigang Wang","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-19T03:27:31Z","title":"On Robust Reinforcement Learning with Lipschitz-Bounded Policy Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11432","kind":"arxiv","version":3},"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":"sha256:18f6c06dc662dc748e65f20b03a5acce82aa9d2898b04786341e4b07856bb610","target":"record","created_at":"2026-07-05T10:10:07Z","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":"3a2ebc415ee03a96d505b52d165925f0bd70f09e5ebb431db3b37fe6d17435da","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-19T03:27:31Z","title_canon_sha256":"7ddc5f486d23b6579000ddd52356c562e05dc50130b79b326df7057ecb9698d1"},"schema_version":"1.0","source":{"id":"2405.11432","kind":"arxiv","version":3}},"canonical_sha256":"898f50b7b4fa1776f795279700782a7131d53712b7d9ab8ca163723d6d3d0a22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"898f50b7b4fa1776f795279700782a7131d53712b7d9ab8ca163723d6d3d0a22","first_computed_at":"2026-07-05T10:10:07.570402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:07.570402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lsT2GwUZPY4/fkskrPpNHsBFoBEC/KooY9Zbq2PEIMac2B+ohzT3nz1/uISbEdYMxxzztQb0BpXgx1wGa5soAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:07.570879Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11432","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18f6c06dc662dc748e65f20b03a5acce82aa9d2898b04786341e4b07856bb610","sha256:0aee9c54570cff2adb60b083855d2fd44dea74a024bc22c36bc51f138bcbcf2c"],"state_sha256":"948b72e3887253919c0125ff04b66872e60edd4fe09a81b9a79db16b30a043c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lw2zP6uy7B8i4yJpBU1PrIhqLKMjZN7bb2/0L3ap0/GpMQD2s3B4wJLhgG9TecbMLdO3lA3/1ytGsXul/M1iDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T20:49:42.052819Z","bundle_sha256":"3206ab63db6beaed429b44c1bd33f9ecf2bb824b70d64ab3c6ce5dd46153e55b"}}