{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AUCDJWPLW6HY4D3HNALYELNUTG","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":"7b71815d1ad10054c2e4aeefca41c8cb4a7bcb3d5662daf766e1114114347b5e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-15T09:16:09Z","title_canon_sha256":"0629e7c16c6a5d559823037777c6f02fd3c622784989d943588a4dc8c29390f3"},"schema_version":"1.0","source":{"id":"2006.08236","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.08236","created_at":"2026-07-05T02:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"2006.08236v3","created_at":"2026-07-05T02:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08236","created_at":"2026-07-05T02:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"AUCDJWPLW6HY","created_at":"2026-07-05T02:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"AUCDJWPLW6HY4D3H","created_at":"2026-07-05T02:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"AUCDJWPL","created_at":"2026-07-05T02:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:857c19c5354ee720a5cbd8a8adfec6adaa08a9025a62ffb463a66b8a2037ba8b","target":"graph","created_at":"2026-07-05T02:28:49Z","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/2006.08236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy learning is a framework for evaluating and optimizing policies without deploying them, from data collected by another policy. Real-world environments are typically non-stationary and the offline learned policies should adapt to these changes. To address this challenge, we study the novel problem of off-policy optimization in piecewise-stationary contextual bandits. Our proposed solution has two phases. In the offline learning phase, we partition logged data into categorical latent states and learn a near-optimal sub-policy for each state. In the online deployment phase, we adaptivel","authors_text":"Amr Ahmed, Branislav Kveton, Joey Hong, Manzil Zaheer, Yinlam Chow","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-15T09:16:09Z","title":"Non-Stationary Off-Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08236","kind":"arxiv","version":3},"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":"sha256:34dc3a948687ca2a10bcbb67c1ebaeb258bd02ee65a5ae651f5f015f178f599e","target":"record","created_at":"2026-07-05T02:28:49Z","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":"7b71815d1ad10054c2e4aeefca41c8cb4a7bcb3d5662daf766e1114114347b5e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-15T09:16:09Z","title_canon_sha256":"0629e7c16c6a5d559823037777c6f02fd3c622784989d943588a4dc8c29390f3"},"schema_version":"1.0","source":{"id":"2006.08236","kind":"arxiv","version":3}},"canonical_sha256":"050434d9ebb78f8e0f676817822db4999418833f9fd246bea1fe29b450db9837","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"050434d9ebb78f8e0f676817822db4999418833f9fd246bea1fe29b450db9837","first_computed_at":"2026-07-05T02:28:49.770549Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:28:49.770549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Mc7zGIaBezv2yCUyWrSccuwu76/jxLITOBOIWGFRczlKqyFYp7kw+wNj/xE2JGSHllM/q0gaFpMZ5Txoq3nDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:28:49.770991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.08236","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34dc3a948687ca2a10bcbb67c1ebaeb258bd02ee65a5ae651f5f015f178f599e","sha256:857c19c5354ee720a5cbd8a8adfec6adaa08a9025a62ffb463a66b8a2037ba8b"],"state_sha256":"4e4cb882918ef9b2095e69b43b12c1e5f469458659020ce7f5030502ac5aa547"}