{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:S5L3RLLXC6SFGHFIDI3I75RCML","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":"e7802cf0cef729b5333d6093cd22d7613820442c3a65ce7431cc25352df1681d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T16:27:06Z","title_canon_sha256":"a99d9258115a812d617d771dc2836232bc48de1e31e9751a789cc6f14586e530"},"schema_version":"1.0","source":{"id":"2310.10556","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10556","created_at":"2026-07-05T07:49:34Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10556v2","created_at":"2026-07-05T07:49:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10556","created_at":"2026-07-05T07:49:34Z"},{"alias_kind":"pith_short_12","alias_value":"S5L3RLLXC6SF","created_at":"2026-07-05T07:49:34Z"},{"alias_kind":"pith_short_16","alias_value":"S5L3RLLXC6SFGHFI","created_at":"2026-07-05T07:49:34Z"},{"alias_kind":"pith_short_8","alias_value":"S5L3RLLX","created_at":"2026-07-05T07:49:34Z"}],"graph_snapshots":[{"event_id":"sha256:49eaf03095b253b0e6e832cd594d1a9313116adef5667bc4aebb6f92167b9c64","target":"graph","created_at":"2026-07-05T07:49:34Z","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/2310.10556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A recently popular approach to solving reinforcement learning is with data from human preferences. In fact, human preference data are now used with classic reinforcement learning algorithms such as actor-critic methods, which involve evaluating an intermediate policy over a reward learned from human preference data with distribution shift, known as off-policy evaluation (OPE). Such algorithm includes (i) learning reward function from human preference dataset, and (ii) learning expected cumulative reward of a target policy. Despite the huge empirical success, existing OPE methods with preferenc","authors_text":"Mengdi Wang, Minshuo Chen, Xiang Ji, Zihao Li","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T16:27:06Z","title":"Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10556","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":"sha256:628aa5c30be6f21cee3d0c94d73b5a1db2bfdc51e479c917b21956acbbfc4744","target":"record","created_at":"2026-07-05T07:49:34Z","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":"e7802cf0cef729b5333d6093cd22d7613820442c3a65ce7431cc25352df1681d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T16:27:06Z","title_canon_sha256":"a99d9258115a812d617d771dc2836232bc48de1e31e9751a789cc6f14586e530"},"schema_version":"1.0","source":{"id":"2310.10556","kind":"arxiv","version":2}},"canonical_sha256":"9757b8ad7717a4531ca81a368ff62262d15280fdd18f6c1270b82dd29bcd7054","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9757b8ad7717a4531ca81a368ff62262d15280fdd18f6c1270b82dd29bcd7054","first_computed_at":"2026-07-05T07:49:34.125134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:34.125134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ku0Gm+yx8JDtw0XrShseGs0HPiAxuLTefKdsMsPzXBRsST6U1sXKNXscGha4I/Ky0fo5dqmHXw/LJFQ1G6tlAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:34.125618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10556","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:628aa5c30be6f21cee3d0c94d73b5a1db2bfdc51e479c917b21956acbbfc4744","sha256:49eaf03095b253b0e6e832cd594d1a9313116adef5667bc4aebb6f92167b9c64"],"state_sha256":"515fe7b0b9cf319c6a04fda2a113949a75915d00301ca910f1b98d4aa3e165e1"}