{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JBLB72BQ4EHP4UMRTQXGQOYAO7","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":"422b7f7b1ad2953dbfc054fdeb9f0ed830d24936719510aea432771128e6c8f0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-12T23:09:21Z","title_canon_sha256":"f550c0ebb1d2b59b4597566f1a19a9875fda117dd5cebffaaaed833474a860a6"},"schema_version":"1.0","source":{"id":"2012.06919","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.06919","created_at":"2026-07-05T01:59:01Z"},{"alias_kind":"arxiv_version","alias_value":"2012.06919v1","created_at":"2026-07-05T01:59:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.06919","created_at":"2026-07-05T01:59:01Z"},{"alias_kind":"pith_short_12","alias_value":"JBLB72BQ4EHP","created_at":"2026-07-05T01:59:01Z"},{"alias_kind":"pith_short_16","alias_value":"JBLB72BQ4EHP4UMR","created_at":"2026-07-05T01:59:01Z"},{"alias_kind":"pith_short_8","alias_value":"JBLB72BQ","created_at":"2026-07-05T01:59:01Z"}],"graph_snapshots":[{"event_id":"sha256:b98c458370dda131911527d53e7c7aa2754165b6e1a2606d145561010baa15a1","target":"graph","created_at":"2026-07-05T01:59:01Z","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/2012.06919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The presence of uncertainty in policy evaluation significantly complicates the process of policy ranking and selection in real-world settings. We formally consider offline policy selection as learning preferences over a set of policy prospects given a fixed experience dataset. While one can select or rank policies based on point estimates of their policy values or high-confidence intervals, access to the full distribution over one's belief of the policy value enables more flexible selection algorithms under a wider range of downstream evaluation metrics. We propose BayesDICE for estimating thi","authors_text":"Bo Dai, Dale Schuurmans, George Tucker, Mengjiao Yang, Ofir Nachum","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-12T23:09:21Z","title":"Offline Policy Selection under Uncertainty"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.06919","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":"sha256:7c4d0915e10d87d9a6e6417a6dc0108755298ca14b9fe11cef953bd6eccf8bef","target":"record","created_at":"2026-07-05T01:59:01Z","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":"422b7f7b1ad2953dbfc054fdeb9f0ed830d24936719510aea432771128e6c8f0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-12T23:09:21Z","title_canon_sha256":"f550c0ebb1d2b59b4597566f1a19a9875fda117dd5cebffaaaed833474a860a6"},"schema_version":"1.0","source":{"id":"2012.06919","kind":"arxiv","version":1}},"canonical_sha256":"48561fe830e10efe51919c2e683b0077e6eee5348839f15742a8615271525a10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48561fe830e10efe51919c2e683b0077e6eee5348839f15742a8615271525a10","first_computed_at":"2026-07-05T01:59:01.371362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:59:01.371362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YASiZgnBsRqNrL5/59gp5ORmwk+twBZweawARAobH5eGHfjL0qC1aPvYFNUTHwKgevOT3Sp9sZP2yCMHEMUTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:59:01.371864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.06919","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c4d0915e10d87d9a6e6417a6dc0108755298ca14b9fe11cef953bd6eccf8bef","sha256:b98c458370dda131911527d53e7c7aa2754165b6e1a2606d145561010baa15a1"],"state_sha256":"3a799b5154fbba0241f6aeaafca8e1d8be173e257448e33fb12552231ea915bc"}