{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:RKALPD4QGF4BK5GUESPPQ2JPTK","short_pith_number":"pith:RKALPD4Q","canonical_record":{"source":{"id":"1907.05079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-11T09:59:10Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e0c46ca6b5a8515dc5c87e5a3bc640abd69fdef260aa80f0c33e105a9dc0d427","abstract_canon_sha256":"ebed9e24c62a72b6dd633e81e4fdc63af183cf96da7c0fac31725b6239f044f2"},"schema_version":"1.0"},"canonical_sha256":"8a80b78f9031781574d4249ef8692f9abb3ab63a3e0c07320a27a2eff1a2a984","source":{"kind":"arxiv","id":"1907.05079","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.05079","created_at":"2026-05-17T23:40:54Z"},{"alias_kind":"arxiv_version","alias_value":"1907.05079v1","created_at":"2026-05-17T23:40:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05079","created_at":"2026-05-17T23:40:54Z"},{"alias_kind":"pith_short_12","alias_value":"RKALPD4QGF4B","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RKALPD4QGF4BK5GU","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RKALPD4Q","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:RKALPD4QGF4BK5GUESPPQ2JPTK","target":"record","payload":{"canonical_record":{"source":{"id":"1907.05079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-11T09:59:10Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e0c46ca6b5a8515dc5c87e5a3bc640abd69fdef260aa80f0c33e105a9dc0d427","abstract_canon_sha256":"ebed9e24c62a72b6dd633e81e4fdc63af183cf96da7c0fac31725b6239f044f2"},"schema_version":"1.0"},"canonical_sha256":"8a80b78f9031781574d4249ef8692f9abb3ab63a3e0c07320a27a2eff1a2a984","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:54.037598Z","signature_b64":"1Ppsto7umCuDxYhla9DJfnGT32wvq4qncGennlxeleHXKhvgkODujqI+Hm9IFQ8ws7lkFgnOdITnU9el8/XDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a80b78f9031781574d4249ef8692f9abb3ab63a3e0c07320a27a2eff1a2a984","last_reissued_at":"2026-05-17T23:40:54.036917Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:54.036917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.05079","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":"2026-05-17T23:40:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EljKVGNASov+hASfljF1FvZnDIeC0G0n385fTdyM18vu/y1JRRYxBwoPHoAg9yjhFg+DrsK9/rqnXcadsqJZDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:40:26.878855Z"},"content_sha256":"69b2aeb7d9c7cd7b55af7747d638da77b0d27b0e25d7d575446372e7555c1d44","schema_version":"1.0","event_id":"sha256:69b2aeb7d9c7cd7b55af7747d638da77b0d27b0e25d7d575446372e7555c1d44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:RKALPD4QGF4BK5GUESPPQ2JPTK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safe Policy Improvement with Soft Baseline Bootstrapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kimia Nadjahi, R\\'emi Tachet des Combes, Romain Laroche","submitted_at":"2019-07-11T09:59:10Z","abstract_excerpt":"Batch Reinforcement Learning (Batch RL) consists in training a policy using trajectories collected with another policy, called the behavioural policy. Safe policy improvement (SPI) provides guarantees with high probability that the trained policy performs better than the behavioural policy, also called baseline in this setting. Previous work shows that the SPI objective improves mean performance as compared to using the basic RL objective, which boils down to solving the MDP with maximum likelihood. Here, we build on that work and improve more precisely the SPI with Baseline Bootstrapping algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05079","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":"2026-05-17T23:40:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y5RYzjGiEm3in3mou0y+rqVaE/IJCiR9idUJwHrlO0Q5ob6aPjXDw4HIokQoVlvy4WDlszOPdJMY2zlS78b8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:40:26.879571Z"},"content_sha256":"0a5f165900dbd6656cbe25eed11de874f15d2b8499203bca0bf07f9b34f20d62","schema_version":"1.0","event_id":"sha256:0a5f165900dbd6656cbe25eed11de874f15d2b8499203bca0bf07f9b34f20d62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RKALPD4QGF4BK5GUESPPQ2JPTK/bundle.json","state_url":"https://pith.science/pith/RKALPD4QGF4BK5GUESPPQ2JPTK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RKALPD4QGF4BK5GUESPPQ2JPTK/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":"2026-05-25T17:40:26Z","links":{"resolver":"https://pith.science/pith/RKALPD4QGF4BK5GUESPPQ2JPTK","bundle":"https://pith.science/pith/RKALPD4QGF4BK5GUESPPQ2JPTK/bundle.json","state":"https://pith.science/pith/RKALPD4QGF4BK5GUESPPQ2JPTK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RKALPD4QGF4BK5GUESPPQ2JPTK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RKALPD4QGF4BK5GUESPPQ2JPTK","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":"ebed9e24c62a72b6dd633e81e4fdc63af183cf96da7c0fac31725b6239f044f2","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-11T09:59:10Z","title_canon_sha256":"e0c46ca6b5a8515dc5c87e5a3bc640abd69fdef260aa80f0c33e105a9dc0d427"},"schema_version":"1.0","source":{"id":"1907.05079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.05079","created_at":"2026-05-17T23:40:54Z"},{"alias_kind":"arxiv_version","alias_value":"1907.05079v1","created_at":"2026-05-17T23:40:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05079","created_at":"2026-05-17T23:40:54Z"},{"alias_kind":"pith_short_12","alias_value":"RKALPD4QGF4B","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RKALPD4QGF4BK5GU","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RKALPD4Q","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:0a5f165900dbd6656cbe25eed11de874f15d2b8499203bca0bf07f9b34f20d62","target":"graph","created_at":"2026-05-17T23:40:54Z","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":"Batch Reinforcement Learning (Batch RL) consists in training a policy using trajectories collected with another policy, called the behavioural policy. Safe policy improvement (SPI) provides guarantees with high probability that the trained policy performs better than the behavioural policy, also called baseline in this setting. Previous work shows that the SPI objective improves mean performance as compared to using the basic RL objective, which boils down to solving the MDP with maximum likelihood. Here, we build on that work and improve more precisely the SPI with Baseline Bootstrapping algo","authors_text":"Kimia Nadjahi, R\\'emi Tachet des Combes, Romain Laroche","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-11T09:59:10Z","title":"Safe Policy Improvement with Soft Baseline Bootstrapping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05079","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":"sha256:69b2aeb7d9c7cd7b55af7747d638da77b0d27b0e25d7d575446372e7555c1d44","target":"record","created_at":"2026-05-17T23:40:54Z","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":"ebed9e24c62a72b6dd633e81e4fdc63af183cf96da7c0fac31725b6239f044f2","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-11T09:59:10Z","title_canon_sha256":"e0c46ca6b5a8515dc5c87e5a3bc640abd69fdef260aa80f0c33e105a9dc0d427"},"schema_version":"1.0","source":{"id":"1907.05079","kind":"arxiv","version":1}},"canonical_sha256":"8a80b78f9031781574d4249ef8692f9abb3ab63a3e0c07320a27a2eff1a2a984","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a80b78f9031781574d4249ef8692f9abb3ab63a3e0c07320a27a2eff1a2a984","first_computed_at":"2026-05-17T23:40:54.036917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:54.036917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Ppsto7umCuDxYhla9DJfnGT32wvq4qncGennlxeleHXKhvgkODujqI+Hm9IFQ8ws7lkFgnOdITnU9el8/XDAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:54.037598Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.05079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69b2aeb7d9c7cd7b55af7747d638da77b0d27b0e25d7d575446372e7555c1d44","sha256:0a5f165900dbd6656cbe25eed11de874f15d2b8499203bca0bf07f9b34f20d62"],"state_sha256":"a40fe6c154c500cc2cddd42f88c05ef00964f7cacce584ffd0a7f478704ff276"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XiU4Ay5i53rxFOfVbmsg2T5sy7ib6CssxcCzBxD7R7dmZgRjH6JKaR40cos0gXGZmnIK/9x7zCCa5AIYzcOJBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:40:26.884754Z","bundle_sha256":"a756589c78e932e69a54c2b216faac91b86ba151475bff35c0231082389b115d"}}