{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6QMW5RN7SHVCFSOVZG36Z3NLUC","short_pith_number":"pith:6QMW5RN7","canonical_record":{"source":{"id":"2101.08452","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-21T05:38:52Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4a7b8d95b814104d62bf221357700ff50c18d91b81e4814c18fa19fc6d629bff","abstract_canon_sha256":"da2f18d06930f2e117bd3e0147f0e8d04d9b04c795851c22ad461408baa066c8"},"schema_version":"1.0"},"canonical_sha256":"f4196ec5bf91ea22c9d5c9b7ecedaba082bda489c63153b8778b1fe2e14b9c4c","source":{"kind":"arxiv","id":"2101.08452","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.08452","created_at":"2026-07-05T02:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"2101.08452v1","created_at":"2026-07-05T02:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08452","created_at":"2026-07-05T02:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"6QMW5RN7SHVC","created_at":"2026-07-05T02:08:35Z"},{"alias_kind":"pith_short_16","alias_value":"6QMW5RN7SHVCFSOV","created_at":"2026-07-05T02:08:35Z"},{"alias_kind":"pith_short_8","alias_value":"6QMW5RN7","created_at":"2026-07-05T02:08:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6QMW5RN7SHVCFSOVZG36Z3NLUC","target":"record","payload":{"canonical_record":{"source":{"id":"2101.08452","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-21T05:38:52Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4a7b8d95b814104d62bf221357700ff50c18d91b81e4814c18fa19fc6d629bff","abstract_canon_sha256":"da2f18d06930f2e117bd3e0147f0e8d04d9b04c795851c22ad461408baa066c8"},"schema_version":"1.0"},"canonical_sha256":"f4196ec5bf91ea22c9d5c9b7ecedaba082bda489c63153b8778b1fe2e14b9c4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:35.428150Z","signature_b64":"F6WLKjE5IncpIELwKjEcaBsX1z+QBK4ROzs9GeTdcThng0/+EDtxM4ej9TkNbo2RpcPFvYJVWpE+C2/S4fu5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4196ec5bf91ea22c9d5c9b7ecedaba082bda489c63153b8778b1fe2e14b9c4c","last_reissued_at":"2026-07-05T02:08:35.427716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:35.427716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.08452","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":"2026-07-05T02:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ItUAMCKFxihI0HJrZ6gnAsQUuPSD0sWifbMgoESoquBBTMiToqDuBLflMbVwIiGxkB7gktQ35/sWa279cjXeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:51:08.840844Z"},"content_sha256":"09a8acabc90a91203a25c39477068d0d0870a647dc2a52cf1e5c0b2667a34e09","schema_version":"1.0","event_id":"sha256:09a8acabc90a91203a25c39477068d0d0870a647dc2a52cf1e5c0b2667a34e09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6QMW5RN7SHVCFSOVZG36Z3NLUC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, Duane Boning, Hongge Chen, Huan Zhang","submitted_at":"2021-01-21T05:38:52Z","abstract_excerpt":"We study the robustness of reinforcement learning (RL) with adversarially perturbed state observations, which aligns with the setting of many adversarial attacks to deep reinforcement learning (DRL) and is also important for rolling out real-world RL agent under unpredictable sensing noise. With a fixed agent policy, we demonstrate that an optimal adversary to perturb state observations can be found, which is guaranteed to obtain the worst case agent reward. For DRL settings, this leads to a novel empirical adversarial attack to RL agents via a learned adversary that is much stronger than prev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08452","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/2101.08452/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":"2026-07-05T02:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n7C33uZYGpgVzaHotVV+CkGaU6Lfa0xxLtvyZ1BrkYFo0WNtPcA8YEEfeziEntIbZm4u5mtNz7mCWi67jjkPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:51:08.841357Z"},"content_sha256":"2ce626cc7d1935e1035f64985e691774802c510bf2639ec1acac201c18d863d9","schema_version":"1.0","event_id":"sha256:2ce626cc7d1935e1035f64985e691774802c510bf2639ec1acac201c18d863d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6QMW5RN7SHVCFSOVZG36Z3NLUC/bundle.json","state_url":"https://pith.science/pith/6QMW5RN7SHVCFSOVZG36Z3NLUC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6QMW5RN7SHVCFSOVZG36Z3NLUC/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":"2026-08-08T16:51:08Z","links":{"resolver":"https://pith.science/pith/6QMW5RN7SHVCFSOVZG36Z3NLUC","bundle":"https://pith.science/pith/6QMW5RN7SHVCFSOVZG36Z3NLUC/bundle.json","state":"https://pith.science/pith/6QMW5RN7SHVCFSOVZG36Z3NLUC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6QMW5RN7SHVCFSOVZG36Z3NLUC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6QMW5RN7SHVCFSOVZG36Z3NLUC","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":"da2f18d06930f2e117bd3e0147f0e8d04d9b04c795851c22ad461408baa066c8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-21T05:38:52Z","title_canon_sha256":"4a7b8d95b814104d62bf221357700ff50c18d91b81e4814c18fa19fc6d629bff"},"schema_version":"1.0","source":{"id":"2101.08452","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.08452","created_at":"2026-07-05T02:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"2101.08452v1","created_at":"2026-07-05T02:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08452","created_at":"2026-07-05T02:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"6QMW5RN7SHVC","created_at":"2026-07-05T02:08:35Z"},{"alias_kind":"pith_short_16","alias_value":"6QMW5RN7SHVCFSOV","created_at":"2026-07-05T02:08:35Z"},{"alias_kind":"pith_short_8","alias_value":"6QMW5RN7","created_at":"2026-07-05T02:08:35Z"}],"graph_snapshots":[{"event_id":"sha256:2ce626cc7d1935e1035f64985e691774802c510bf2639ec1acac201c18d863d9","target":"graph","created_at":"2026-07-05T02:08:35Z","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/2101.08452/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the robustness of reinforcement learning (RL) with adversarially perturbed state observations, which aligns with the setting of many adversarial attacks to deep reinforcement learning (DRL) and is also important for rolling out real-world RL agent under unpredictable sensing noise. With a fixed agent policy, we demonstrate that an optimal adversary to perturb state observations can be found, which is guaranteed to obtain the worst case agent reward. For DRL settings, this leads to a novel empirical adversarial attack to RL agents via a learned adversary that is much stronger than prev","authors_text":"Cho-Jui Hsieh, Duane Boning, Hongge Chen, Huan Zhang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-21T05:38:52Z","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08452","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":"sha256:09a8acabc90a91203a25c39477068d0d0870a647dc2a52cf1e5c0b2667a34e09","target":"record","created_at":"2026-07-05T02:08:35Z","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":"da2f18d06930f2e117bd3e0147f0e8d04d9b04c795851c22ad461408baa066c8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-21T05:38:52Z","title_canon_sha256":"4a7b8d95b814104d62bf221357700ff50c18d91b81e4814c18fa19fc6d629bff"},"schema_version":"1.0","source":{"id":"2101.08452","kind":"arxiv","version":1}},"canonical_sha256":"f4196ec5bf91ea22c9d5c9b7ecedaba082bda489c63153b8778b1fe2e14b9c4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4196ec5bf91ea22c9d5c9b7ecedaba082bda489c63153b8778b1fe2e14b9c4c","first_computed_at":"2026-07-05T02:08:35.427716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:08:35.427716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F6WLKjE5IncpIELwKjEcaBsX1z+QBK4ROzs9GeTdcThng0/+EDtxM4ej9TkNbo2RpcPFvYJVWpE+C2/S4fu5Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:08:35.428150Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.08452","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09a8acabc90a91203a25c39477068d0d0870a647dc2a52cf1e5c0b2667a34e09","sha256:2ce626cc7d1935e1035f64985e691774802c510bf2639ec1acac201c18d863d9"],"state_sha256":"777f755f99ec3dfd7c13b7fd6780c0ba3a243a23db8eb431b83187b7a4595b14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PrEZpfvqZVj82cC3BSafVv3hmBklwZL1EbDmdW99+3lF23X05OdKYOJFT7ydWrS8wfBjRMWPNrBY5vGlUyMUDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:51:08.847143Z","bundle_sha256":"95cefcd8f6f8bcb2df7c83c7d778fc81844aa02f61633a969630097f1f11a3d2"}}