{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EHX4OKLOVCUVU2SJQNXIFMWN6M","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":"9013aadd068dac9930fd6ea611075a2b68c427407533748b5137b5786c411f40","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:05:05Z","title_canon_sha256":"5333a4efa289d22a018c4c87f796a43804d186fe7485aa4ff504f3256e8183d9"},"schema_version":"1.0","source":{"id":"2606.07592","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07592","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07592v1","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07592","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"EHX4OKLOVCUV","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"EHX4OKLOVCUVU2SJ","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"EHX4OKLO","created_at":"2026-06-09T00:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:cb30c82fcb15efcfe19f031bec2af22b26ff302b0189e5075db02edf99688fe8","target":"graph","created_at":"2026-06-09T00:04:44Z","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/2606.07592/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning requires careful conservatism to mitigate distribution shift, yet most existing methods apply a fixed penalty uniformly across all states regardless of local data coverage. We present UNIQ (Uncertainty-Informed Quantile), an offline RL method that introduces state-adaptive conservatism through conformally calibrated uncertainty estimation. Built on the Implicit Q-Learning (IQL) backbone, UNIQ trains a multi-expectile value ensemble, computes distribution-free uncertainty estimates using split conformal prediction, and maps the resulting signal to a state-dependen","authors_text":"Aditya Upadhyay","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:05:05Z","title":"UNIQ: Conformal Calibration for Adaptive Conservatism in Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07592","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":"sha256:4e62107d00799e2afcae24b5cc1ba47a542cb293925d1959e2305044a371cdd8","target":"record","created_at":"2026-06-09T00:04:44Z","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":"9013aadd068dac9930fd6ea611075a2b68c427407533748b5137b5786c411f40","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:05:05Z","title_canon_sha256":"5333a4efa289d22a018c4c87f796a43804d186fe7485aa4ff504f3256e8183d9"},"schema_version":"1.0","source":{"id":"2606.07592","kind":"arxiv","version":1}},"canonical_sha256":"21efc7296ea8a95a6a49836e82b2cdf31115fbbe7d4d3b1f8fc9bd90a702b1c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21efc7296ea8a95a6a49836e82b2cdf31115fbbe7d4d3b1f8fc9bd90a702b1c6","first_computed_at":"2026-06-09T00:04:44.213933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T00:04:44.213933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A8LuTl9Y8JXvoCwnRXsfFk3pddb081oxov02kkV5+jD/5HFj2f3bF22hNVsBtvoK1ilt3AtFQCD336zwXLXOAg==","signature_status":"signed_v1","signed_at":"2026-06-09T00:04:44.214329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07592","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e62107d00799e2afcae24b5cc1ba47a542cb293925d1959e2305044a371cdd8","sha256:cb30c82fcb15efcfe19f031bec2af22b26ff302b0189e5075db02edf99688fe8"],"state_sha256":"e65c7784ef1232737360ff4233a895d4a6d4d2518c5433a371a5356492666c64"}