{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SFZWMYZ62ZWI22HV2KTRSBJGX2","short_pith_number":"pith:SFZWMYZ6","canonical_record":{"source":{"id":"2312.08751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T08:57:22Z","cross_cats_sorted":[],"title_canon_sha256":"cf83931757d13d409fc8c7be453d2ff2238e514b5e9a3909d2e1bac022279426","abstract_canon_sha256":"6c98ba5fb8057f6ac97c04720ae096ee7a3abb040220b990609918569fcb5039"},"schema_version":"1.0"},"canonical_sha256":"917366633ed66c8d68f5d2a7190526beb0a3fd63e5d18a7c1a28b81e32561a6d","source":{"kind":"arxiv","id":"2312.08751","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08751","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08751v1","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08751","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_12","alias_value":"SFZWMYZ62ZWI","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_16","alias_value":"SFZWMYZ62ZWI22HV","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_8","alias_value":"SFZWMYZ6","created_at":"2026-07-05T07:24:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SFZWMYZ62ZWI22HV2KTRSBJGX2","target":"record","payload":{"canonical_record":{"source":{"id":"2312.08751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T08:57:22Z","cross_cats_sorted":[],"title_canon_sha256":"cf83931757d13d409fc8c7be453d2ff2238e514b5e9a3909d2e1bac022279426","abstract_canon_sha256":"6c98ba5fb8057f6ac97c04720ae096ee7a3abb040220b990609918569fcb5039"},"schema_version":"1.0"},"canonical_sha256":"917366633ed66c8d68f5d2a7190526beb0a3fd63e5d18a7c1a28b81e32561a6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:08.998104Z","signature_b64":"LLiOERBKoX48tVVOcnxqkBuZijPx3VlAqlFeWpYvNxbJVHLauEIKFux9pM9Q+ok926bEPIGEme8DYUJS5iPWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"917366633ed66c8d68f5d2a7190526beb0a3fd63e5d18a7c1a28b81e32561a6d","last_reissued_at":"2026-07-05T07:24:08.997707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:08.997707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.08751","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":"2026-07-05T07:24:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UuvANa6ExQMcCk5KwPF3uGlVrTzAsYo0fWaXr5xdX+Ncc8HMCxOr9y54gg/VbdCgAgYkU6fa+exEEv+LFBIuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:59:23.188398Z"},"content_sha256":"dc2ad9d251feb6034b8f319bf5b583c1e777c9fe6dc198357ba799e9733e9f36","schema_version":"1.0","event_id":"sha256:dc2ad9d251feb6034b8f319bf5b583c1e777c9fe6dc198357ba799e9733e9f36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SFZWMYZ62ZWI22HV2KTRSBJGX2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improve Robustness of Reinforcement Learning against Observation Perturbations via $l_\\infty$ Lipschitz Policy Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Buqing Nie, Jingtian Ji, Yangqing Fu, Yue Gao","submitted_at":"2023-12-14T08:57:22Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) has achieved remarkable advances in sequential decision tasks. However, recent works have revealed that DRL agents are susceptible to slight perturbations in observations. This vulnerability raises concerns regarding the effectiveness and robustness of deploying such agents in real-world applications. In this work, we propose a novel robust reinforcement learning method called SortRL, which improves the robustness of DRL policies against observation perturbations from the perspective of the network architecture. We employ a novel architecture for the policy ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08751","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/2312.08751/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":"2026-07-05T07:24:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n8C82VsZpZQ89K2bjfAHaWQpBF7qCJufgf3uiMEPgx98RZz8OpevdtznIRluXZzgp0mXfkAlZqSKrKNh1QMkDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:59:23.188906Z"},"content_sha256":"e7e747a9ca47e0cacac7c992d025cd5ad3cc288799a0a251f120e04a3ecee04d","schema_version":"1.0","event_id":"sha256:e7e747a9ca47e0cacac7c992d025cd5ad3cc288799a0a251f120e04a3ecee04d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SFZWMYZ62ZWI22HV2KTRSBJGX2/bundle.json","state_url":"https://pith.science/pith/SFZWMYZ62ZWI22HV2KTRSBJGX2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SFZWMYZ62ZWI22HV2KTRSBJGX2/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":"2026-08-08T14:59:23Z","links":{"resolver":"https://pith.science/pith/SFZWMYZ62ZWI22HV2KTRSBJGX2","bundle":"https://pith.science/pith/SFZWMYZ62ZWI22HV2KTRSBJGX2/bundle.json","state":"https://pith.science/pith/SFZWMYZ62ZWI22HV2KTRSBJGX2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SFZWMYZ62ZWI22HV2KTRSBJGX2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SFZWMYZ62ZWI22HV2KTRSBJGX2","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":"6c98ba5fb8057f6ac97c04720ae096ee7a3abb040220b990609918569fcb5039","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T08:57:22Z","title_canon_sha256":"cf83931757d13d409fc8c7be453d2ff2238e514b5e9a3909d2e1bac022279426"},"schema_version":"1.0","source":{"id":"2312.08751","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08751","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08751v1","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08751","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_12","alias_value":"SFZWMYZ62ZWI","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_16","alias_value":"SFZWMYZ62ZWI22HV","created_at":"2026-07-05T07:24:08Z"},{"alias_kind":"pith_short_8","alias_value":"SFZWMYZ6","created_at":"2026-07-05T07:24:08Z"}],"graph_snapshots":[{"event_id":"sha256:e7e747a9ca47e0cacac7c992d025cd5ad3cc288799a0a251f120e04a3ecee04d","target":"graph","created_at":"2026-07-05T07:24:08Z","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/2312.08751/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Reinforcement Learning (DRL) has achieved remarkable advances in sequential decision tasks. However, recent works have revealed that DRL agents are susceptible to slight perturbations in observations. This vulnerability raises concerns regarding the effectiveness and robustness of deploying such agents in real-world applications. In this work, we propose a novel robust reinforcement learning method called SortRL, which improves the robustness of DRL policies against observation perturbations from the perspective of the network architecture. We employ a novel architecture for the policy ne","authors_text":"Buqing Nie, Jingtian Ji, Yangqing Fu, Yue Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T08:57:22Z","title":"Improve Robustness of Reinforcement Learning against Observation Perturbations via $l_\\infty$ Lipschitz Policy Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08751","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:dc2ad9d251feb6034b8f319bf5b583c1e777c9fe6dc198357ba799e9733e9f36","target":"record","created_at":"2026-07-05T07:24:08Z","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":"6c98ba5fb8057f6ac97c04720ae096ee7a3abb040220b990609918569fcb5039","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T08:57:22Z","title_canon_sha256":"cf83931757d13d409fc8c7be453d2ff2238e514b5e9a3909d2e1bac022279426"},"schema_version":"1.0","source":{"id":"2312.08751","kind":"arxiv","version":1}},"canonical_sha256":"917366633ed66c8d68f5d2a7190526beb0a3fd63e5d18a7c1a28b81e32561a6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"917366633ed66c8d68f5d2a7190526beb0a3fd63e5d18a7c1a28b81e32561a6d","first_computed_at":"2026-07-05T07:24:08.997707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:08.997707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LLiOERBKoX48tVVOcnxqkBuZijPx3VlAqlFeWpYvNxbJVHLauEIKFux9pM9Q+ok926bEPIGEme8DYUJS5iPWCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:08.998104Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.08751","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc2ad9d251feb6034b8f319bf5b583c1e777c9fe6dc198357ba799e9733e9f36","sha256:e7e747a9ca47e0cacac7c992d025cd5ad3cc288799a0a251f120e04a3ecee04d"],"state_sha256":"3c0b405707a1f11c70958761e362fa48ad1fb63a4927ebecdcdc2948a54e4c89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h/exHA3HuwPGm0xkI+kr2TW02g+ZQ5Ghyr6pHr6nOJhTr+W8s1YvB1AEZhKjlVrMZWnaKGQBk6KCAnKbSHIHAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:59:23.193409Z","bundle_sha256":"3aeafe751f2b9a3f3fb45e63489c858ec8d11388d1843c0b3fb8149beb07f00d"}}