{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RGFVDXUQ6A2YQJGLH5IPFPE6VF","short_pith_number":"pith:RGFVDXUQ","canonical_record":{"source":{"id":"1805.09044","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T10:43:16Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"eb6fe6ae354669d858a0f35053d87d061c5f364c66b950ad105ea2a14540115c","abstract_canon_sha256":"96bccdd9f13b73866126274d97dbff9115f561f070937e6433b18bf2c17f6b63"},"schema_version":"1.0"},"canonical_sha256":"898b51de90f0358824cb3f50f2bc9ea943ffb1f9adffac6b75ebdee01eb93922","source":{"kind":"arxiv","id":"1805.09044","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09044","created_at":"2026-05-17T23:48:17Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09044v4","created_at":"2026-05-17T23:48:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09044","created_at":"2026-05-17T23:48:17Z"},{"alias_kind":"pith_short_12","alias_value":"RGFVDXUQ6A2Y","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RGFVDXUQ6A2YQJGL","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RGFVDXUQ","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RGFVDXUQ6A2YQJGLH5IPFPE6VF","target":"record","payload":{"canonical_record":{"source":{"id":"1805.09044","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T10:43:16Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"eb6fe6ae354669d858a0f35053d87d061c5f364c66b950ad105ea2a14540115c","abstract_canon_sha256":"96bccdd9f13b73866126274d97dbff9115f561f070937e6433b18bf2c17f6b63"},"schema_version":"1.0"},"canonical_sha256":"898b51de90f0358824cb3f50f2bc9ea943ffb1f9adffac6b75ebdee01eb93922","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:17.352784Z","signature_b64":"CZz5pZAwEUiEQWDR9JUhuCi3OqgHvfhzReucfjk3oJlmI0aTn+ytv981BCMEaQiAprgLO6fkM20ct2A+i/xoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"898b51de90f0358824cb3f50f2bc9ea943ffb1f9adffac6b75ebdee01eb93922","last_reissued_at":"2026-05-17T23:48:17.352093Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:17.352093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.09044","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o17VvoTQpGWuJ2MLiYzYH5TCfKjfwC26knsDXiMVkUlrwdzd+rr3RbdNdSLCKPA3A/iwmd8y/9xPfJgWdb8YDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T09:44:37.134460Z"},"content_sha256":"639b0846d1c685a3ae6068aa6a2e7f5bd4f596588cbdcdc72dfd67cf9c60791e","schema_version":"1.0","event_id":"sha256:639b0846d1c685a3ae6068aa6a2e7f5bd4f596588cbdcdc72dfd67cf9c60791e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RGFVDXUQ6A2YQJGLH5IPFPE6VF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Representation Balancing MDPs for Off-Policy Policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Faisal, Aniruddh Raghu, Emma Brunskill, Finale Doshi-Velez, Matthieu Komorowski, Omer Gottesman, Yao Liu","submitted_at":"2018-05-23T10:43:16Z","abstract_excerpt":"We study the problem of off-policy policy evaluation (OPPE) in RL. In contrast to prior work, we consider how to estimate both the individual policy value and average policy value accurately. We draw inspiration from recent work in causal reasoning, and propose a new finite sample generalization error bound for value estimates from MDP models. Using this upper bound as an objective, we develop a learning algorithm of an MDP model with a balanced representation, and show that our approach can yield substantially lower MSE in common synthetic benchmarks and a HIV treatment simulation domain."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09044","kind":"arxiv","version":4},"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":"2026-05-17T23:48:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oJKrjKhOQC9WwYeUGwNWlHyXX2ATABk1xWGOHOOYflvAgx7bNCqoneytoFqmAyRHRvPYNVenwigdZtwgUx9/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T09:44:37.135171Z"},"content_sha256":"19c5c73bff0a6fadce2116cef9cba0c5ae557f1952119cfadb5bb3a5901429e8","schema_version":"1.0","event_id":"sha256:19c5c73bff0a6fadce2116cef9cba0c5ae557f1952119cfadb5bb3a5901429e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RGFVDXUQ6A2YQJGLH5IPFPE6VF/bundle.json","state_url":"https://pith.science/pith/RGFVDXUQ6A2YQJGLH5IPFPE6VF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RGFVDXUQ6A2YQJGLH5IPFPE6VF/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":"2026-05-25T09:44:37Z","links":{"resolver":"https://pith.science/pith/RGFVDXUQ6A2YQJGLH5IPFPE6VF","bundle":"https://pith.science/pith/RGFVDXUQ6A2YQJGLH5IPFPE6VF/bundle.json","state":"https://pith.science/pith/RGFVDXUQ6A2YQJGLH5IPFPE6VF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RGFVDXUQ6A2YQJGLH5IPFPE6VF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RGFVDXUQ6A2YQJGLH5IPFPE6VF","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":"96bccdd9f13b73866126274d97dbff9115f561f070937e6433b18bf2c17f6b63","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T10:43:16Z","title_canon_sha256":"eb6fe6ae354669d858a0f35053d87d061c5f364c66b950ad105ea2a14540115c"},"schema_version":"1.0","source":{"id":"1805.09044","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09044","created_at":"2026-05-17T23:48:17Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09044v4","created_at":"2026-05-17T23:48:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09044","created_at":"2026-05-17T23:48:17Z"},{"alias_kind":"pith_short_12","alias_value":"RGFVDXUQ6A2Y","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RGFVDXUQ6A2YQJGL","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RGFVDXUQ","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:19c5c73bff0a6fadce2116cef9cba0c5ae557f1952119cfadb5bb3a5901429e8","target":"graph","created_at":"2026-05-17T23:48:17Z","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 study the problem of off-policy policy evaluation (OPPE) in RL. In contrast to prior work, we consider how to estimate both the individual policy value and average policy value accurately. We draw inspiration from recent work in causal reasoning, and propose a new finite sample generalization error bound for value estimates from MDP models. Using this upper bound as an objective, we develop a learning algorithm of an MDP model with a balanced representation, and show that our approach can yield substantially lower MSE in common synthetic benchmarks and a HIV treatment simulation domain.","authors_text":"Aldo Faisal, Aniruddh Raghu, Emma Brunskill, Finale Doshi-Velez, Matthieu Komorowski, Omer Gottesman, Yao Liu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T10:43:16Z","title":"Representation Balancing MDPs for Off-Policy Policy Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09044","kind":"arxiv","version":4},"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":"sha256:639b0846d1c685a3ae6068aa6a2e7f5bd4f596588cbdcdc72dfd67cf9c60791e","target":"record","created_at":"2026-05-17T23:48:17Z","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":"96bccdd9f13b73866126274d97dbff9115f561f070937e6433b18bf2c17f6b63","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T10:43:16Z","title_canon_sha256":"eb6fe6ae354669d858a0f35053d87d061c5f364c66b950ad105ea2a14540115c"},"schema_version":"1.0","source":{"id":"1805.09044","kind":"arxiv","version":4}},"canonical_sha256":"898b51de90f0358824cb3f50f2bc9ea943ffb1f9adffac6b75ebdee01eb93922","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"898b51de90f0358824cb3f50f2bc9ea943ffb1f9adffac6b75ebdee01eb93922","first_computed_at":"2026-05-17T23:48:17.352093Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:17.352093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CZz5pZAwEUiEQWDR9JUhuCi3OqgHvfhzReucfjk3oJlmI0aTn+ytv981BCMEaQiAprgLO6fkM20ct2A+i/xoAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:17.352784Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.09044","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:639b0846d1c685a3ae6068aa6a2e7f5bd4f596588cbdcdc72dfd67cf9c60791e","sha256:19c5c73bff0a6fadce2116cef9cba0c5ae557f1952119cfadb5bb3a5901429e8"],"state_sha256":"2d5f298216fd82b22609efc4f9dd98d67bcd1c70a82f3098e5c258bd8b6791e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PmuKLOD4ZY3aaM7KusJV8WpdXUZ1+uP7NSpPgJxhes18qLvTGzRS+B0RLpxWnPciH/JQslEJ3y3pJOVlwqEiAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T09:44:37.138931Z","bundle_sha256":"a4508fa06d7e71bfe031be367cf21ee0d3a96b8d58b245d745525754df5e0c6c"}}