{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3U5LCPTS7VR3LINSXZA2LK6PMM","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":"a5e83299de933ad94829046dd242630e7c24dc71e05523e2dfaed3a7f0ab5418","cross_cats_sorted":["econ.EM","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2025-05-20T01:41:44Z","title_canon_sha256":"4565f2b60f05ced5b3c49d441ec3c396c01bfd6b7299e9d5111c6e5948706d1e"},"schema_version":"1.0","source":{"id":"2505.13809","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13809","created_at":"2026-06-29T00:13:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13809v5","created_at":"2026-06-29T00:13:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13809","created_at":"2026-06-29T00:13:59Z"},{"alias_kind":"pith_short_12","alias_value":"3U5LCPTS7VR3","created_at":"2026-06-29T00:13:59Z"},{"alias_kind":"pith_short_16","alias_value":"3U5LCPTS7VR3LINS","created_at":"2026-06-29T00:13:59Z"},{"alias_kind":"pith_short_8","alias_value":"3U5LCPTS","created_at":"2026-06-29T00:13:59Z"}],"graph_snapshots":[{"event_id":"sha256:503660ee78f5d44d4473f80cf7ba24ecd5578dda2e89cff0931a6c6ca3712706","target":"graph","created_at":"2026-06-29T00:13:59Z","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/2505.13809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy evaluation (OPE) constructs confidence intervals for the value of a target policy using data generated under a different behavior policy. Most existing inference methods focus on fixed target policies and may fail when the target policy is estimated as optimal, particularly when the optimal policy is non-unique or nearly deterministic.\n  We study inference for the value of optimal policies in Markov decision processes. In an auxiliary augmented transition-sampling experiment, we characterize the existence of the efficient influence function and show that non-regularity arises when c","authors_text":"Haoyu Wei","cross_cats":["econ.EM","stat.ML","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2025-05-20T01:41:44Z","title":"Semiparametric Off-Policy Inference for Optimal Policy Values under Possible Non-Uniqueness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13809","kind":"arxiv","version":5},"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":"sha256:3ed020d9a0894f53d96aa235b566f6efe7a4dd19521dcfc87817305c1be5d3d0","target":"record","created_at":"2026-06-29T00:13:59Z","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":"a5e83299de933ad94829046dd242630e7c24dc71e05523e2dfaed3a7f0ab5418","cross_cats_sorted":["econ.EM","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2025-05-20T01:41:44Z","title_canon_sha256":"4565f2b60f05ced5b3c49d441ec3c396c01bfd6b7299e9d5111c6e5948706d1e"},"schema_version":"1.0","source":{"id":"2505.13809","kind":"arxiv","version":5}},"canonical_sha256":"dd3ab13e72fd63b5a1b2be41a5abcf631677be70f0f646d950f35a04ad1f4b6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd3ab13e72fd63b5a1b2be41a5abcf631677be70f0f646d950f35a04ad1f4b6f","first_computed_at":"2026-06-29T00:13:59.936846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T00:13:59.936846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"33bLV7yLJXfl/dL8Hs6sv2vt1h22+Nm08L63Lk7/eGgKM3QpNOkhh6TLy3qBkZIkMdX7KVnskWdAOugGaq3ICg==","signature_status":"signed_v1","signed_at":"2026-06-29T00:13:59.937303Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13809","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ed020d9a0894f53d96aa235b566f6efe7a4dd19521dcfc87817305c1be5d3d0","sha256:503660ee78f5d44d4473f80cf7ba24ecd5578dda2e89cff0931a6c6ca3712706"],"state_sha256":"2494e24230a8ce5776aa32e64849d885554ad37e4882127951b988f86f8a3826"}