{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:KN63SWW6CDLXHSMJED66XSPH7A","short_pith_number":"pith:KN63SWW6","canonical_record":{"source":{"id":"1805.08122","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T15:30:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d96652281170b6df9d827f0dac5bea28fd375dda05ce624b316ac58bfd253fb8","abstract_canon_sha256":"7d8afc04d5b47162543e59ff3a06438e530c68a242f829da60fe8be6ba55c7b9"},"schema_version":"1.0"},"canonical_sha256":"537db95ade10d773c98920fdebc9e7f81a22857dcb64c6f175fcedb9cacaba79","source":{"kind":"arxiv","id":"1805.08122","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08122","created_at":"2026-05-17T23:44:59Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08122v2","created_at":"2026-05-17T23:44:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08122","created_at":"2026-05-17T23:44:59Z"},{"alias_kind":"pith_short_12","alias_value":"KN63SWW6CDLX","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KN63SWW6CDLXHSMJ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KN63SWW6","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:KN63SWW6CDLXHSMJED66XSPH7A","target":"record","payload":{"canonical_record":{"source":{"id":"1805.08122","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T15:30:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d96652281170b6df9d827f0dac5bea28fd375dda05ce624b316ac58bfd253fb8","abstract_canon_sha256":"7d8afc04d5b47162543e59ff3a06438e530c68a242f829da60fe8be6ba55c7b9"},"schema_version":"1.0"},"canonical_sha256":"537db95ade10d773c98920fdebc9e7f81a22857dcb64c6f175fcedb9cacaba79","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:59.534111Z","signature_b64":"RTEoNUG4oCi6NLKqZRVVx0pT6aQBlFPYaSvlON9WNA07LGQ6MQa8Tk+HmpeDPU6XiZgclQN5qi5TX7V9DCP6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"537db95ade10d773c98920fdebc9e7f81a22857dcb64c6f175fcedb9cacaba79","last_reissued_at":"2026-05-17T23:44:59.533548Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:59.533548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.08122","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yFiIqa/qEgkh6KeP95BSSnZgGSHxZLSK34sXBel4SoBqYqxoFR1sXVzuNB/8gd61E47dNoGhHL72Qlo8iqO7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T15:33:37.780088Z"},"content_sha256":"1eaefd96f295b0af202fb73beef5ba5a885f57d566e5b7906059a6a1100cbe7f","schema_version":"1.0","event_id":"sha256:1eaefd96f295b0af202fb73beef5ba5a885f57d566e5b7906059a6a1100cbe7f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:KN63SWW6CDLXHSMJED66XSPH7A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A General Family of Robust Stochastic Operators for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chai Wah Wu, Mark S. Squillante, Yingdong Lu","submitted_at":"2018-05-21T15:30:54Z","abstract_excerpt":"We consider a new family of operators for reinforcement learning with the goal of alleviating the negative effects and becoming more robust to approximation or estimation errors. Various theoretical results are established, which include showing on a sample path basis that our family of operators preserve optimality and increase the action gap. Our empirical results illustrate the strong benefits of our family of operators, significantly outperforming the classical Bellman operator and recently proposed operators."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08122","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:44:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z4BV28VWg7B26PKAdLUXDrBkv6BUPNVp/ipPSMfJrkLvoMKvOoL8bYGCYEGqmtvnhOdWtm+j9yUIHvHqstQhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T15:33:37.780830Z"},"content_sha256":"1faa492d1a116f773b8bf20b5cb976d171a8645bb54671d242be18754785d8ef","schema_version":"1.0","event_id":"sha256:1faa492d1a116f773b8bf20b5cb976d171a8645bb54671d242be18754785d8ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KN63SWW6CDLXHSMJED66XSPH7A/bundle.json","state_url":"https://pith.science/pith/KN63SWW6CDLXHSMJED66XSPH7A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KN63SWW6CDLXHSMJED66XSPH7A/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":"2026-05-23T15:33:37Z","links":{"resolver":"https://pith.science/pith/KN63SWW6CDLXHSMJED66XSPH7A","bundle":"https://pith.science/pith/KN63SWW6CDLXHSMJED66XSPH7A/bundle.json","state":"https://pith.science/pith/KN63SWW6CDLXHSMJED66XSPH7A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KN63SWW6CDLXHSMJED66XSPH7A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KN63SWW6CDLXHSMJED66XSPH7A","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":"7d8afc04d5b47162543e59ff3a06438e530c68a242f829da60fe8be6ba55c7b9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T15:30:54Z","title_canon_sha256":"d96652281170b6df9d827f0dac5bea28fd375dda05ce624b316ac58bfd253fb8"},"schema_version":"1.0","source":{"id":"1805.08122","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08122","created_at":"2026-05-17T23:44:59Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08122v2","created_at":"2026-05-17T23:44:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08122","created_at":"2026-05-17T23:44:59Z"},{"alias_kind":"pith_short_12","alias_value":"KN63SWW6CDLX","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KN63SWW6CDLXHSMJ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KN63SWW6","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:1faa492d1a116f773b8bf20b5cb976d171a8645bb54671d242be18754785d8ef","target":"graph","created_at":"2026-05-17T23:44:59Z","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"},"paper":{"abstract_excerpt":"We consider a new family of operators for reinforcement learning with the goal of alleviating the negative effects and becoming more robust to approximation or estimation errors. Various theoretical results are established, which include showing on a sample path basis that our family of operators preserve optimality and increase the action gap. Our empirical results illustrate the strong benefits of our family of operators, significantly outperforming the classical Bellman operator and recently proposed operators.","authors_text":"Chai Wah Wu, Mark S. Squillante, Yingdong Lu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T15:30:54Z","title":"A General Family of Robust Stochastic Operators for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08122","kind":"arxiv","version":2},"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":"sha256:1eaefd96f295b0af202fb73beef5ba5a885f57d566e5b7906059a6a1100cbe7f","target":"record","created_at":"2026-05-17T23:44:59Z","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":"7d8afc04d5b47162543e59ff3a06438e530c68a242f829da60fe8be6ba55c7b9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T15:30:54Z","title_canon_sha256":"d96652281170b6df9d827f0dac5bea28fd375dda05ce624b316ac58bfd253fb8"},"schema_version":"1.0","source":{"id":"1805.08122","kind":"arxiv","version":2}},"canonical_sha256":"537db95ade10d773c98920fdebc9e7f81a22857dcb64c6f175fcedb9cacaba79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"537db95ade10d773c98920fdebc9e7f81a22857dcb64c6f175fcedb9cacaba79","first_computed_at":"2026-05-17T23:44:59.533548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:59.533548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RTEoNUG4oCi6NLKqZRVVx0pT6aQBlFPYaSvlON9WNA07LGQ6MQa8Tk+HmpeDPU6XiZgclQN5qi5TX7V9DCP6Bw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:59.534111Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08122","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1eaefd96f295b0af202fb73beef5ba5a885f57d566e5b7906059a6a1100cbe7f","sha256:1faa492d1a116f773b8bf20b5cb976d171a8645bb54671d242be18754785d8ef"],"state_sha256":"9f4bf0129cb0521e2d86f7f28b3113b7e941bf143e64f70739935eb3e28a206d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pWblxMWVm0+xyHOb2hAB0CvVTJepDU9Ii99RhZosFs+8M11vvN3sLTZ1aPQv5BvAcR2OLsqpMHGvsdLccKKQAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T15:33:37.784752Z","bundle_sha256":"3bf30b2a380b0925b4fef16370000e822727acb9d1e53c1aa45249ead960cfa1"}}