{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X4G3D7PBVKZQ5BZGLURK2MZNWU","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":"d7fb9896c20fdc60bfc08172119ee2085f18fdba75ef4fd31298fca6df98fe00","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-23T09:07:27Z","title_canon_sha256":"0508f21577a7864473cad4da2d65a2a4c620078d64080e0d7a2ad39759ecd9d1"},"schema_version":"1.0","source":{"id":"2405.14335","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14335","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14335v2","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14335","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"X4G3D7PBVKZQ","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"X4G3D7PBVKZQ5BZG","created_at":"2026-07-05T09:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"X4G3D7PB","created_at":"2026-07-05T09:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:1a5d2439509c8485c91062b6bfee7e95342c48fbac45397254981bbaf702ee52","target":"graph","created_at":"2026-07-05T09:28:49Z","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/2405.14335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work investigates the offline formulation of the contextual bandit problem, where the goal is to leverage past interactions collected under a behavior policy to evaluate, select, and learn new, potentially better-performing, policies. Motivated by critical applications, we move beyond point estimators. Instead, we adopt the principle of pessimism where we construct upper bounds that assess a policy's worst-case performance, enabling us to confidently select and learn improved policies. Precisely, we introduce novel, fully empirical concentration bounds for a broad class of importance weig","authors_text":"Imad Aouali, Nicolas Chopin, Otmane Sakhi, Pierre Alquier","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-23T09:07:27Z","title":"Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14335","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":"sha256:038208788bc902f86bfa77412f6ff735488ae3502ab7e3bfd0ba4e7b3e84447c","target":"record","created_at":"2026-07-05T09:28:49Z","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":"d7fb9896c20fdc60bfc08172119ee2085f18fdba75ef4fd31298fca6df98fe00","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-23T09:07:27Z","title_canon_sha256":"0508f21577a7864473cad4da2d65a2a4c620078d64080e0d7a2ad39759ecd9d1"},"schema_version":"1.0","source":{"id":"2405.14335","kind":"arxiv","version":2}},"canonical_sha256":"bf0db1fde1aab30e87265d22ad332db515b6594f92a519b02d05e3c8601814ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf0db1fde1aab30e87265d22ad332db515b6594f92a519b02d05e3c8601814ef","first_computed_at":"2026-07-05T09:28:49.889653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:49.889653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f5ceSBnLWY8w+krZpmu5YJApJj9adtlRwHovYuBEmN4H8EBh83gsGmdf8V708J5MLaFE0x8kSCELj6hAeOq3Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:49.890100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14335","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:038208788bc902f86bfa77412f6ff735488ae3502ab7e3bfd0ba4e7b3e84447c","sha256:1a5d2439509c8485c91062b6bfee7e95342c48fbac45397254981bbaf702ee52"],"state_sha256":"f3f2dd3419954e9ee928a8eeca5f280f75173b33b344524564e589e0ee91fadf"}