{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X4G3D7PBVKZQ5BZGLURK2MZNWU","short_pith_number":"pith:X4G3D7PB","schema_version":"1.0","canonical_sha256":"bf0db1fde1aab30e87265d22ad332db515b6594f92a519b02d05e3c8601814ef","source":{"kind":"arxiv","id":"2405.14335","version":2},"attestation_state":"computed","paper":{"title":"Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Imad Aouali, Nicolas Chopin, Otmane Sakhi, Pierre Alquier","submitted_at":"2024-05-23T09:07:27Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.14335","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-23T09:07:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0508f21577a7864473cad4da2d65a2a4c620078d64080e0d7a2ad39759ecd9d1","abstract_canon_sha256":"d7fb9896c20fdc60bfc08172119ee2085f18fdba75ef4fd31298fca6df98fe00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:49.890100Z","signature_b64":"f5ceSBnLWY8w+krZpmu5YJApJj9adtlRwHovYuBEmN4H8EBh83gsGmdf8V708J5MLaFE0x8kSCELj6hAeOq3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf0db1fde1aab30e87265d22ad332db515b6594f92a519b02d05e3c8601814ef","last_reissued_at":"2026-07-05T09:28:49.889653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:49.889653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Imad Aouali, Nicolas Chopin, Otmane Sakhi, Pierre Alquier","submitted_at":"2024-05-23T09:07:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14335","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.14335/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.14335","created_at":"2026-07-05T09:28:49.889709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14335v2","created_at":"2026-07-05T09:28:49.889709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14335","created_at":"2026-07-05T09:28:49.889709+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4G3D7PBVKZQ","created_at":"2026-07-05T09:28:49.889709+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4G3D7PBVKZQ5BZG","created_at":"2026-07-05T09:28:49.889709+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4G3D7PB","created_at":"2026-07-05T09:28:49.889709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4G3D7PBVKZQ5BZGLURK2MZNWU","json":"https://pith.science/pith/X4G3D7PBVKZQ5BZGLURK2MZNWU.json","graph_json":"https://pith.science/api/pith-number/X4G3D7PBVKZQ5BZGLURK2MZNWU/graph.json","events_json":"https://pith.science/api/pith-number/X4G3D7PBVKZQ5BZGLURK2MZNWU/events.json","paper":"https://pith.science/paper/X4G3D7PB"},"agent_actions":{"view_html":"https://pith.science/pith/X4G3D7PBVKZQ5BZGLURK2MZNWU","download_json":"https://pith.science/pith/X4G3D7PBVKZQ5BZGLURK2MZNWU.json","view_paper":"https://pith.science/paper/X4G3D7PB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14335&json=true","fetch_graph":"https://pith.science/api/pith-number/X4G3D7PBVKZQ5BZGLURK2MZNWU/graph.json","fetch_events":"https://pith.science/api/pith-number/X4G3D7PBVKZQ5BZGLURK2MZNWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4G3D7PBVKZQ5BZGLURK2MZNWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4G3D7PBVKZQ5BZGLURK2MZNWU/action/storage_attestation","attest_author":"https://pith.science/pith/X4G3D7PBVKZQ5BZGLURK2MZNWU/action/author_attestation","sign_citation":"https://pith.science/pith/X4G3D7PBVKZQ5BZGLURK2MZNWU/action/citation_signature","submit_replication":"https://pith.science/pith/X4G3D7PBVKZQ5BZGLURK2MZNWU/action/replication_record"}},"created_at":"2026-07-05T09:28:49.889709+00:00","updated_at":"2026-07-05T09:28:49.889709+00:00"}