{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EC2GIAS43TSC3TTLPN6YEY245X","short_pith_number":"pith:EC2GIAS4","canonical_record":{"source":{"id":"1812.10576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-26T23:48:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b70409b28b834293d254572db6f664d64fa1d192a6687c6453920dc0b95d6512","abstract_canon_sha256":"476c4e025bc1cc5fd9c7bcc0d2f6c71e203b7b5707dbfed6a4d12fc70b4d548c"},"schema_version":"1.0"},"canonical_sha256":"20b464025cdce42dce6b7b7d82635cedca746fe4548dbf38fbd957e168bdac74","source":{"kind":"arxiv","id":"1812.10576","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.10576","created_at":"2026-05-17T23:57:20Z"},{"alias_kind":"arxiv_version","alias_value":"1812.10576v1","created_at":"2026-05-17T23:57:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10576","created_at":"2026-05-17T23:57:20Z"},{"alias_kind":"pith_short_12","alias_value":"EC2GIAS43TSC","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EC2GIAS43TSC3TTL","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EC2GIAS4","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EC2GIAS43TSC3TTLPN6YEY245X","target":"record","payload":{"canonical_record":{"source":{"id":"1812.10576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-26T23:48:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b70409b28b834293d254572db6f664d64fa1d192a6687c6453920dc0b95d6512","abstract_canon_sha256":"476c4e025bc1cc5fd9c7bcc0d2f6c71e203b7b5707dbfed6a4d12fc70b4d548c"},"schema_version":"1.0"},"canonical_sha256":"20b464025cdce42dce6b7b7d82635cedca746fe4548dbf38fbd957e168bdac74","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:20.618244Z","signature_b64":"/QPFxwoaKH7WuzW7fkhlXcFUZWnifpm+BZP/BO59Z6UJmGU/eKZBIR+h+2IBNhVXisBM3RO3CXdY0ntXZPWNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20b464025cdce42dce6b7b7d82635cedca746fe4548dbf38fbd957e168bdac74","last_reissued_at":"2026-05-17T23:57:20.617635Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:20.617635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.10576","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":"2026-05-17T23:57:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NCFaYJ1bmYr6Hh9COa414OsEFW3LdL/Wevb1vOdCnOy8UPSqfyJseO3OYlvqiUdTGH0Z9U9InOg1YZgo8KYMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T05:41:53.873179Z"},"content_sha256":"75b834f5b0d664d7ece3d400275898e4506d684041e11f61156afbc3261f02aa","schema_version":"1.0","event_id":"sha256:75b834f5b0d664d7ece3d400275898e4506d684041e11f61156afbc3261f02aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EC2GIAS43TSC3TTLPN6YEY245X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deconfounding Reinforcement Learning in Observational Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernhard Sch\\\"olkopf, Chaochao Lu, Jos\\'e Miguel Hern\\'andez-Lobato","submitted_at":"2018-12-26T23:48:51Z","abstract_excerpt":"We propose a general formulation for addressing reinforcement learning (RL) problems in settings with observational data. That is, we consider the problem of learning good policies solely from historical data in which unobserved factors (confounders) affect both observed actions and rewards. Our formulation allows us to extend a representative RL algorithm, the Actor-Critic method, to its deconfounding variant, with the methodology for this extension being easily applied to other RL algorithms. In addition to this, we develop a new benchmark for evaluating deconfounding RL algorithms by modify"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10576","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":""},"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":"2026-05-17T23:57:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i0YnknU9rDRSxcw3y18AkXL2NbI8jbONaZi2A2x7uL2ZWvoBl2T9nMcxppGba7fcBtPW4GI9IpXaUnDTan+4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T05:41:53.873558Z"},"content_sha256":"2f86faef182c2730d473b8d42bff577a98eb624ac81cd814eed3d8fa914e316a","schema_version":"1.0","event_id":"sha256:2f86faef182c2730d473b8d42bff577a98eb624ac81cd814eed3d8fa914e316a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EC2GIAS43TSC3TTLPN6YEY245X/bundle.json","state_url":"https://pith.science/pith/EC2GIAS43TSC3TTLPN6YEY245X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EC2GIAS43TSC3TTLPN6YEY245X/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":"2026-05-28T05:41:53Z","links":{"resolver":"https://pith.science/pith/EC2GIAS43TSC3TTLPN6YEY245X","bundle":"https://pith.science/pith/EC2GIAS43TSC3TTLPN6YEY245X/bundle.json","state":"https://pith.science/pith/EC2GIAS43TSC3TTLPN6YEY245X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EC2GIAS43TSC3TTLPN6YEY245X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EC2GIAS43TSC3TTLPN6YEY245X","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":"476c4e025bc1cc5fd9c7bcc0d2f6c71e203b7b5707dbfed6a4d12fc70b4d548c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-26T23:48:51Z","title_canon_sha256":"b70409b28b834293d254572db6f664d64fa1d192a6687c6453920dc0b95d6512"},"schema_version":"1.0","source":{"id":"1812.10576","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.10576","created_at":"2026-05-17T23:57:20Z"},{"alias_kind":"arxiv_version","alias_value":"1812.10576v1","created_at":"2026-05-17T23:57:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10576","created_at":"2026-05-17T23:57:20Z"},{"alias_kind":"pith_short_12","alias_value":"EC2GIAS43TSC","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EC2GIAS43TSC3TTL","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EC2GIAS4","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:2f86faef182c2730d473b8d42bff577a98eb624ac81cd814eed3d8fa914e316a","target":"graph","created_at":"2026-05-17T23:57:20Z","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 propose a general formulation for addressing reinforcement learning (RL) problems in settings with observational data. That is, we consider the problem of learning good policies solely from historical data in which unobserved factors (confounders) affect both observed actions and rewards. Our formulation allows us to extend a representative RL algorithm, the Actor-Critic method, to its deconfounding variant, with the methodology for this extension being easily applied to other RL algorithms. In addition to this, we develop a new benchmark for evaluating deconfounding RL algorithms by modify","authors_text":"Bernhard Sch\\\"olkopf, Chaochao Lu, Jos\\'e Miguel Hern\\'andez-Lobato","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-26T23:48:51Z","title":"Deconfounding Reinforcement Learning in Observational Settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10576","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":"sha256:75b834f5b0d664d7ece3d400275898e4506d684041e11f61156afbc3261f02aa","target":"record","created_at":"2026-05-17T23:57:20Z","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":"476c4e025bc1cc5fd9c7bcc0d2f6c71e203b7b5707dbfed6a4d12fc70b4d548c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-26T23:48:51Z","title_canon_sha256":"b70409b28b834293d254572db6f664d64fa1d192a6687c6453920dc0b95d6512"},"schema_version":"1.0","source":{"id":"1812.10576","kind":"arxiv","version":1}},"canonical_sha256":"20b464025cdce42dce6b7b7d82635cedca746fe4548dbf38fbd957e168bdac74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20b464025cdce42dce6b7b7d82635cedca746fe4548dbf38fbd957e168bdac74","first_computed_at":"2026-05-17T23:57:20.617635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:20.617635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/QPFxwoaKH7WuzW7fkhlXcFUZWnifpm+BZP/BO59Z6UJmGU/eKZBIR+h+2IBNhVXisBM3RO3CXdY0ntXZPWNCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:20.618244Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.10576","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75b834f5b0d664d7ece3d400275898e4506d684041e11f61156afbc3261f02aa","sha256:2f86faef182c2730d473b8d42bff577a98eb624ac81cd814eed3d8fa914e316a"],"state_sha256":"306d841d21951d9df14b8c4ad47ec772c7c8e6d6e7345a7ef92a446b647fa095"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"df4K9zRpvgHVZ6CN5O7Ryv/WONgVdw0BRnJCnPAgnBIDrt55GcP86GXeeAxyYEz2dEbvMID0QqUElaWxWnT1Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T05:41:53.875590Z","bundle_sha256":"d298659c216a61e0e0cc1456cc94a971a336f089784fcff2735bdc0ef4766041"}}