{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:RZQUBSIFHWDRXJPCDKXF3A6ZDN","short_pith_number":"pith:RZQUBSIF","canonical_record":{"source":{"id":"1511.03722","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-11T22:59:51Z","cross_cats_sorted":["cs.AI","cs.SY","stat.ME","stat.ML"],"title_canon_sha256":"d0b0112698d747e1f33b2aa59e3e13d1f435881f673725b2fff3a3372580bb18","abstract_canon_sha256":"c8a7f9267bf6dbf5f54265a1e4befc524fb0eef666e254c24214dc3ff16d2a12"},"schema_version":"1.0"},"canonical_sha256":"8e6140c9053d871ba5e21aae5d83d91b5a00017638ac4c939c8df41be9280d0a","source":{"kind":"arxiv","id":"1511.03722","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.03722","created_at":"2026-05-18T01:13:37Z"},{"alias_kind":"arxiv_version","alias_value":"1511.03722v3","created_at":"2026-05-18T01:13:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.03722","created_at":"2026-05-18T01:13:37Z"},{"alias_kind":"pith_short_12","alias_value":"RZQUBSIFHWDR","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"RZQUBSIFHWDRXJPC","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"RZQUBSIF","created_at":"2026-05-18T12:29:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:RZQUBSIFHWDRXJPCDKXF3A6ZDN","target":"record","payload":{"canonical_record":{"source":{"id":"1511.03722","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-11T22:59:51Z","cross_cats_sorted":["cs.AI","cs.SY","stat.ME","stat.ML"],"title_canon_sha256":"d0b0112698d747e1f33b2aa59e3e13d1f435881f673725b2fff3a3372580bb18","abstract_canon_sha256":"c8a7f9267bf6dbf5f54265a1e4befc524fb0eef666e254c24214dc3ff16d2a12"},"schema_version":"1.0"},"canonical_sha256":"8e6140c9053d871ba5e21aae5d83d91b5a00017638ac4c939c8df41be9280d0a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:37.920601Z","signature_b64":"qU3mg5Whxsg+fhQrLCpNdOMuwS1RWGNdhgFtqnsbQuQquS2uEkyeWEO5vFZOfOuk2PkVgAD6o33tm1uIHXyXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e6140c9053d871ba5e21aae5d83d91b5a00017638ac4c939c8df41be9280d0a","last_reissued_at":"2026-05-18T01:13:37.920013Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:37.920013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.03722","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:13:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TwbiQs0J+Qzr1XbVjjryvLS80YHXDOnVzA33T906+TDxjbS8rH/bBQWeeMCu46of6G53i9UO3/CKIcW3ZkmUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T10:44:21.016475Z"},"content_sha256":"2bf23ea71597b770ec17f3158b81d25f9e2c1d5cd9bcc6c63adb45abbb525941","schema_version":"1.0","event_id":"sha256:2bf23ea71597b770ec17f3158b81d25f9e2c1d5cd9bcc6c63adb45abbb525941"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:RZQUBSIFHWDRXJPCDKXF3A6ZDN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lihong Li, Nan Jiang","submitted_at":"2015-11-11T22:59:51Z","abstract_excerpt":"We study the problem of off-policy value evaluation in reinforcement learning (RL), where one aims to estimate the value of a new policy based on data collected by a different policy. This problem is often a critical step when applying RL in real-world problems. Despite its importance, existing general methods either have uncontrolled bias or suffer high variance. In this work, we extend the doubly robust estimator for bandits to sequential decision-making problems, which gets the best of both worlds: it is guaranteed to be unbiased and can have a much lower variance than the popular importanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.03722","kind":"arxiv","version":3},"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":"2026-05-18T01:13:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qr3cf8AHMRokERUti/F2/32nfk5INibowq3FBcPmmjjG2hAG2DbrcwdzDFve/Qylne0+hd1EstFiUJkfFwTvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T10:44:21.017012Z"},"content_sha256":"c42c3eb3cceb0febefca3c89932b926598df4195eab57893452e2f4a00490f4d","schema_version":"1.0","event_id":"sha256:c42c3eb3cceb0febefca3c89932b926598df4195eab57893452e2f4a00490f4d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZQUBSIFHWDRXJPCDKXF3A6ZDN/bundle.json","state_url":"https://pith.science/pith/RZQUBSIFHWDRXJPCDKXF3A6ZDN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZQUBSIFHWDRXJPCDKXF3A6ZDN/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":"2026-05-30T10:44:21Z","links":{"resolver":"https://pith.science/pith/RZQUBSIFHWDRXJPCDKXF3A6ZDN","bundle":"https://pith.science/pith/RZQUBSIFHWDRXJPCDKXF3A6ZDN/bundle.json","state":"https://pith.science/pith/RZQUBSIFHWDRXJPCDKXF3A6ZDN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZQUBSIFHWDRXJPCDKXF3A6ZDN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:RZQUBSIFHWDRXJPCDKXF3A6ZDN","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":"c8a7f9267bf6dbf5f54265a1e4befc524fb0eef666e254c24214dc3ff16d2a12","cross_cats_sorted":["cs.AI","cs.SY","stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-11T22:59:51Z","title_canon_sha256":"d0b0112698d747e1f33b2aa59e3e13d1f435881f673725b2fff3a3372580bb18"},"schema_version":"1.0","source":{"id":"1511.03722","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.03722","created_at":"2026-05-18T01:13:37Z"},{"alias_kind":"arxiv_version","alias_value":"1511.03722v3","created_at":"2026-05-18T01:13:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.03722","created_at":"2026-05-18T01:13:37Z"},{"alias_kind":"pith_short_12","alias_value":"RZQUBSIFHWDR","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"RZQUBSIFHWDRXJPC","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"RZQUBSIF","created_at":"2026-05-18T12:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:c42c3eb3cceb0febefca3c89932b926598df4195eab57893452e2f4a00490f4d","target":"graph","created_at":"2026-05-18T01:13:37Z","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 value evaluation in reinforcement learning (RL), where one aims to estimate the value of a new policy based on data collected by a different policy. This problem is often a critical step when applying RL in real-world problems. Despite its importance, existing general methods either have uncontrolled bias or suffer high variance. In this work, we extend the doubly robust estimator for bandits to sequential decision-making problems, which gets the best of both worlds: it is guaranteed to be unbiased and can have a much lower variance than the popular importanc","authors_text":"Lihong Li, Nan Jiang","cross_cats":["cs.AI","cs.SY","stat.ME","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-11T22:59:51Z","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.03722","kind":"arxiv","version":3},"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":"sha256:2bf23ea71597b770ec17f3158b81d25f9e2c1d5cd9bcc6c63adb45abbb525941","target":"record","created_at":"2026-05-18T01:13:37Z","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":"c8a7f9267bf6dbf5f54265a1e4befc524fb0eef666e254c24214dc3ff16d2a12","cross_cats_sorted":["cs.AI","cs.SY","stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-11T22:59:51Z","title_canon_sha256":"d0b0112698d747e1f33b2aa59e3e13d1f435881f673725b2fff3a3372580bb18"},"schema_version":"1.0","source":{"id":"1511.03722","kind":"arxiv","version":3}},"canonical_sha256":"8e6140c9053d871ba5e21aae5d83d91b5a00017638ac4c939c8df41be9280d0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e6140c9053d871ba5e21aae5d83d91b5a00017638ac4c939c8df41be9280d0a","first_computed_at":"2026-05-18T01:13:37.920013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:13:37.920013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qU3mg5Whxsg+fhQrLCpNdOMuwS1RWGNdhgFtqnsbQuQquS2uEkyeWEO5vFZOfOuk2PkVgAD6o33tm1uIHXyXAA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:13:37.920601Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.03722","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bf23ea71597b770ec17f3158b81d25f9e2c1d5cd9bcc6c63adb45abbb525941","sha256:c42c3eb3cceb0febefca3c89932b926598df4195eab57893452e2f4a00490f4d"],"state_sha256":"7385acce6029540ca799c80463929c26e3d418ad57fb65cb988c6201638fb0a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PGW6dkqQWz8LZimwz3q7/JZLWz7kcjt0OYlfXfUF8XL3n0ApF2y/0Magbo4C3ps9wPsEoOYpK8b0dTZU547lDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T10:44:21.021013Z","bundle_sha256":"4792354d5b7d926b1e5c88340f80e0231af1e9abd70d2bd06482d9352e57e92a"}}