{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZBQKZPOR6BOWT7NMX3RVH4ES3B","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":"71c37d2af93238e6339d22d7cfca88eb5748f9f0d0644eec8ad287f81cddd8a8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-09-11T17:48:00Z","title_canon_sha256":"7a10b3b24b80a35eabccd29a939e90e7ff2d43cfe1219430b1a79d39f081d1b8"},"schema_version":"1.0","source":{"id":"1909.05236","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.05236","created_at":"2026-07-05T02:02:51Z"},{"alias_kind":"arxiv_version","alias_value":"1909.05236v2","created_at":"2026-07-05T02:02:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.05236","created_at":"2026-07-05T02:02:51Z"},{"alias_kind":"pith_short_12","alias_value":"ZBQKZPOR6BOW","created_at":"2026-07-05T02:02:51Z"},{"alias_kind":"pith_short_16","alias_value":"ZBQKZPOR6BOWT7NM","created_at":"2026-07-05T02:02:51Z"},{"alias_kind":"pith_short_8","alias_value":"ZBQKZPOR","created_at":"2026-07-05T02:02:51Z"}],"graph_snapshots":[{"event_id":"sha256:2798e324092691ddda63fe6d5236ef5ab7b22e666c4d3ebe7e98ea76a2360786","target":"graph","created_at":"2026-07-05T02:02:51Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.05236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous work has shown the unreliability of existing algorithms in the batch Reinforcement Learning setting, and proposed the theoretically-grounded Safe Policy Improvement with Baseline Bootstrapping (SPIBB) fix: reproduce the baseline policy in the uncertain state-action pairs, in order to control the variance on the trained policy performance. However, in many real-world applications such as dialogue systems, pharmaceutical tests or crop management, data is collected under human supervision and the baseline remains unknown. In this paper, we apply SPIBB algorithms with a baseline estimate ","authors_text":"R\\'emi Tachet des Combes, Romain Laroche, Thiago D. Sim\\~ao","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-09-11T17:48:00Z","title":"Safe Policy Improvement with an Estimated Baseline Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.05236","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":"sha256:6a7e8c68ebbcbae5f3fee5b8003315ac8105b31c1078b207cb99a66d82fa7ed0","target":"record","created_at":"2026-07-05T02:02:51Z","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":"71c37d2af93238e6339d22d7cfca88eb5748f9f0d0644eec8ad287f81cddd8a8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-09-11T17:48:00Z","title_canon_sha256":"7a10b3b24b80a35eabccd29a939e90e7ff2d43cfe1219430b1a79d39f081d1b8"},"schema_version":"1.0","source":{"id":"1909.05236","kind":"arxiv","version":2}},"canonical_sha256":"c860acbdd1f05d69fdacbee353f092d867728f6f1937561f0bf5bb1365296520","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c860acbdd1f05d69fdacbee353f092d867728f6f1937561f0bf5bb1365296520","first_computed_at":"2026-07-05T02:02:51.040506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:02:51.040506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zt8vZzid9h6wSR5c2n+DPoUU0Y00rREu1LBq2LJ1SX32tYaYhPwpSOJR8WaJ/E12bKptjomHmAvuaQuOC2kFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:02:51.040914Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.05236","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a7e8c68ebbcbae5f3fee5b8003315ac8105b31c1078b207cb99a66d82fa7ed0","sha256:2798e324092691ddda63fe6d5236ef5ab7b22e666c4d3ebe7e98ea76a2360786"],"state_sha256":"68ffc9787ccb5de0f906d88c4ee5ae6e3fa585a8405f3642db21cbd40a591904"}