{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SRZL2PWTP23PEURUQNTP6VTKB2","short_pith_number":"pith:SRZL2PWT","schema_version":"1.0","canonical_sha256":"9472bd3ed37eb6f252348366ff566a0eb15e5eae2cf7b93b5b370971bab7da68","source":{"kind":"arxiv","id":"2306.07923","version":2},"attestation_state":"computed","paper":{"title":"Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Aleksandrs Slivkins, Lequn Wang","submitted_at":"2023-06-13T17:29:50Z","abstract_excerpt":"We consider offline policy optimization (OPO) in contextual bandits, where one is given a fixed dataset of logged interactions. While pessimistic regularizers are typically used to mitigate distribution shift, prior implementations thereof are either specialized or computationally inefficient. We present the first general oracle-efficient algorithm for pessimistic OPO: it reduces to supervised learning, leading to broad applicability. We obtain statistical guarantees analogous to those for prior pessimistic approaches. We instantiate our approach for both discrete and continuous actions and pe"},"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":"2306.07923","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T17:29:50Z","cross_cats_sorted":[],"title_canon_sha256":"742e7533fb388747aef29a2c6e04de5e8b7f9572f4abd484a3f40fc5be409714","abstract_canon_sha256":"feafcddbf27269059926b9867d9fb86284cd82d6e46d804c671f3dc4f7bbf4a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:09.972131Z","signature_b64":"Tl8WswoyVMiqsfIJpREtxa8vuCcPZ1rQ4udmeKlNCyH7H9vhqfPNFKb5GoFljo+igYbv3GTxIfAocMWM4MQ7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9472bd3ed37eb6f252348366ff566a0eb15e5eae2cf7b93b5b370971bab7da68","last_reissued_at":"2026-07-05T07:05:09.971529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:09.971529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Aleksandrs Slivkins, Lequn Wang","submitted_at":"2023-06-13T17:29:50Z","abstract_excerpt":"We consider offline policy optimization (OPO) in contextual bandits, where one is given a fixed dataset of logged interactions. While pessimistic regularizers are typically used to mitigate distribution shift, prior implementations thereof are either specialized or computationally inefficient. We present the first general oracle-efficient algorithm for pessimistic OPO: it reduces to supervised learning, leading to broad applicability. We obtain statistical guarantees analogous to those for prior pessimistic approaches. We instantiate our approach for both discrete and continuous actions and pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07923","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/2306.07923/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":"2306.07923","created_at":"2026-07-05T07:05:09.971597+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07923v2","created_at":"2026-07-05T07:05:09.971597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07923","created_at":"2026-07-05T07:05:09.971597+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRZL2PWTP23P","created_at":"2026-07-05T07:05:09.971597+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRZL2PWTP23PEURU","created_at":"2026-07-05T07:05:09.971597+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRZL2PWT","created_at":"2026-07-05T07:05:09.971597+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13768","citing_title":"Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis","ref_index":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRZL2PWTP23PEURUQNTP6VTKB2","json":"https://pith.science/pith/SRZL2PWTP23PEURUQNTP6VTKB2.json","graph_json":"https://pith.science/api/pith-number/SRZL2PWTP23PEURUQNTP6VTKB2/graph.json","events_json":"https://pith.science/api/pith-number/SRZL2PWTP23PEURUQNTP6VTKB2/events.json","paper":"https://pith.science/paper/SRZL2PWT"},"agent_actions":{"view_html":"https://pith.science/pith/SRZL2PWTP23PEURUQNTP6VTKB2","download_json":"https://pith.science/pith/SRZL2PWTP23PEURUQNTP6VTKB2.json","view_paper":"https://pith.science/paper/SRZL2PWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07923&json=true","fetch_graph":"https://pith.science/api/pith-number/SRZL2PWTP23PEURUQNTP6VTKB2/graph.json","fetch_events":"https://pith.science/api/pith-number/SRZL2PWTP23PEURUQNTP6VTKB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRZL2PWTP23PEURUQNTP6VTKB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRZL2PWTP23PEURUQNTP6VTKB2/action/storage_attestation","attest_author":"https://pith.science/pith/SRZL2PWTP23PEURUQNTP6VTKB2/action/author_attestation","sign_citation":"https://pith.science/pith/SRZL2PWTP23PEURUQNTP6VTKB2/action/citation_signature","submit_replication":"https://pith.science/pith/SRZL2PWTP23PEURUQNTP6VTKB2/action/replication_record"}},"created_at":"2026-07-05T07:05:09.971597+00:00","updated_at":"2026-07-05T07:05:09.971597+00:00"}