{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:GMSGTN6K5PGOFB26AQDXE7W6PY","short_pith_number":"pith:GMSGTN6K","canonical_record":{"source":{"id":"1604.00923","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-04T15:56:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2709d3c4c242f0ca0fd5bf5b32c55feaf8ee5feb0158baea80cdc1e4793ba580","abstract_canon_sha256":"9f8a1982bb1e482f59c99a737be072a38cf9e6e7e52472416e61e2f4ea2e402b"},"schema_version":"1.0"},"canonical_sha256":"332469b7caebcce2875e0407727ede7e3498fd9af586a4882ff25a7b53443d99","source":{"kind":"arxiv","id":"1604.00923","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.00923","created_at":"2026-05-18T01:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"1604.00923v1","created_at":"2026-05-18T01:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.00923","created_at":"2026-05-18T01:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"GMSGTN6K5PGO","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"GMSGTN6K5PGOFB26","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"GMSGTN6K","created_at":"2026-05-18T12:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:GMSGTN6K5PGOFB26AQDXE7W6PY","target":"record","payload":{"canonical_record":{"source":{"id":"1604.00923","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-04T15:56:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2709d3c4c242f0ca0fd5bf5b32c55feaf8ee5feb0158baea80cdc1e4793ba580","abstract_canon_sha256":"9f8a1982bb1e482f59c99a737be072a38cf9e6e7e52472416e61e2f4ea2e402b"},"schema_version":"1.0"},"canonical_sha256":"332469b7caebcce2875e0407727ede7e3498fd9af586a4882ff25a7b53443d99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:47.785128Z","signature_b64":"OXRXNHxw9I27ePeZ2anOTS7vjQ4BHvxzaSbtuWWmRAabRo+eevcClNpqvzJ2bAcOpla2XFGBBmZgMd+MsYxHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"332469b7caebcce2875e0407727ede7e3498fd9af586a4882ff25a7b53443d99","last_reissued_at":"2026-05-18T01:17:47.784325Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:47.784325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1604.00923","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":"2026-05-18T01:17:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2wuIw/JOlnOLJnzpkp9XbjCkAD+RnxbiU3OTPMadKb0QTK7tdjoghgp9Ot0h+iKbsMyRqKicfOonKkW0o7/EDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T06:46:34.306077Z"},"content_sha256":"c989627183b5a7e0b1821da90f95aea6876f602238119bc31a5196f597ff4234","schema_version":"1.0","event_id":"sha256:c989627183b5a7e0b1821da90f95aea6876f602238119bc31a5196f597ff4234"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:GMSGTN6K5PGOFB26AQDXE7W6PY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Emma Brunskill, Philip S. Thomas","submitted_at":"2016-04-04T15:56:52Z","abstract_excerpt":"In this paper we present a new way of predicting the performance of a reinforcement learning policy given historical data that may have been generated by a different policy. The ability to evaluate a policy from historical data is important for applications where the deployment of a bad policy can be dangerous or costly. We show empirically that our algorithm produces estimates that often have orders of magnitude lower mean squared error than existing methods---it makes more efficient use of the available data. Our new estimator is based on two advances: an extension of the doubly robust estim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.00923","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":"2026-05-18T01:17:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yqddmS8VaLvLWXTQHM3vAUCOqoxitjYHBIsKnXqR3kfFFDvd7rq5KH3V0aG1qfvp7fWN/R+5TuexcsnBf4hHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T06:46:34.306758Z"},"content_sha256":"93c95d162140a0314d165d11e5cc7caf08bc2cf021bdcaa1dfb647a451233728","schema_version":"1.0","event_id":"sha256:93c95d162140a0314d165d11e5cc7caf08bc2cf021bdcaa1dfb647a451233728"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GMSGTN6K5PGOFB26AQDXE7W6PY/bundle.json","state_url":"https://pith.science/pith/GMSGTN6K5PGOFB26AQDXE7W6PY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GMSGTN6K5PGOFB26AQDXE7W6PY/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":"2026-06-06T06:46:34Z","links":{"resolver":"https://pith.science/pith/GMSGTN6K5PGOFB26AQDXE7W6PY","bundle":"https://pith.science/pith/GMSGTN6K5PGOFB26AQDXE7W6PY/bundle.json","state":"https://pith.science/pith/GMSGTN6K5PGOFB26AQDXE7W6PY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GMSGTN6K5PGOFB26AQDXE7W6PY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:GMSGTN6K5PGOFB26AQDXE7W6PY","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":"9f8a1982bb1e482f59c99a737be072a38cf9e6e7e52472416e61e2f4ea2e402b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-04T15:56:52Z","title_canon_sha256":"2709d3c4c242f0ca0fd5bf5b32c55feaf8ee5feb0158baea80cdc1e4793ba580"},"schema_version":"1.0","source":{"id":"1604.00923","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.00923","created_at":"2026-05-18T01:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"1604.00923v1","created_at":"2026-05-18T01:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.00923","created_at":"2026-05-18T01:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"GMSGTN6K5PGO","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"GMSGTN6K5PGOFB26","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"GMSGTN6K","created_at":"2026-05-18T12:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:93c95d162140a0314d165d11e5cc7caf08bc2cf021bdcaa1dfb647a451233728","target":"graph","created_at":"2026-05-18T01:17:47Z","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":"In this paper we present a new way of predicting the performance of a reinforcement learning policy given historical data that may have been generated by a different policy. The ability to evaluate a policy from historical data is important for applications where the deployment of a bad policy can be dangerous or costly. We show empirically that our algorithm produces estimates that often have orders of magnitude lower mean squared error than existing methods---it makes more efficient use of the available data. Our new estimator is based on two advances: an extension of the doubly robust estim","authors_text":"Emma Brunskill, Philip S. Thomas","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-04T15:56:52Z","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.00923","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:c989627183b5a7e0b1821da90f95aea6876f602238119bc31a5196f597ff4234","target":"record","created_at":"2026-05-18T01:17:47Z","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":"9f8a1982bb1e482f59c99a737be072a38cf9e6e7e52472416e61e2f4ea2e402b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-04T15:56:52Z","title_canon_sha256":"2709d3c4c242f0ca0fd5bf5b32c55feaf8ee5feb0158baea80cdc1e4793ba580"},"schema_version":"1.0","source":{"id":"1604.00923","kind":"arxiv","version":1}},"canonical_sha256":"332469b7caebcce2875e0407727ede7e3498fd9af586a4882ff25a7b53443d99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"332469b7caebcce2875e0407727ede7e3498fd9af586a4882ff25a7b53443d99","first_computed_at":"2026-05-18T01:17:47.784325Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:47.784325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OXRXNHxw9I27ePeZ2anOTS7vjQ4BHvxzaSbtuWWmRAabRo+eevcClNpqvzJ2bAcOpla2XFGBBmZgMd+MsYxHDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:47.785128Z","signed_message":"canonical_sha256_bytes"},"source_id":"1604.00923","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c989627183b5a7e0b1821da90f95aea6876f602238119bc31a5196f597ff4234","sha256:93c95d162140a0314d165d11e5cc7caf08bc2cf021bdcaa1dfb647a451233728"],"state_sha256":"875d2723ef5eb9980925cd450f604ba798bafa755b1724af9cd75d806282ad91"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U0EBi2/NhqybU2XH18xtcCILbY5Fkcm9iCORSgZCdTBi4dfpNZrEnzMU4d2Kvm61n3LvaVptJYFm0LVCYH9NDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T06:46:34.310501Z","bundle_sha256":"3b503491792ae9dc08d9bbd9a9b1a361a5ab0f644311eab052a662ae60165a2d"}}