{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EHX4OKLOVCUVU2SJQNXIFMWN6M","short_pith_number":"pith:EHX4OKLO","schema_version":"1.0","canonical_sha256":"21efc7296ea8a95a6a49836e82b2cdf31115fbbe7d4d3b1f8fc9bd90a702b1c6","source":{"kind":"arxiv","id":"2606.07592","version":1},"attestation_state":"computed","paper":{"title":"UNIQ: Conformal Calibration for Adaptive Conservatism in Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Upadhyay","submitted_at":"2026-05-28T17:05:05Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.07592","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:05:05Z","cross_cats_sorted":[],"title_canon_sha256":"5333a4efa289d22a018c4c87f796a43804d186fe7485aa4ff504f3256e8183d9","abstract_canon_sha256":"9013aadd068dac9930fd6ea611075a2b68c427407533748b5137b5786c411f40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T00:04:44.214329Z","signature_b64":"A8LuTl9Y8JXvoCwnRXsfFk3pddb081oxov02kkV5+jD/5HFj2f3bF22hNVsBtvoK1ilt3AtFQCD336zwXLXOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21efc7296ea8a95a6a49836e82b2cdf31115fbbe7d4d3b1f8fc9bd90a702b1c6","last_reissued_at":"2026-06-09T00:04:44.213933Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T00:04:44.213933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UNIQ: Conformal Calibration for Adaptive Conservatism in Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Upadhyay","submitted_at":"2026-05-28T17:05:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07592","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.07592/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.07592","created_at":"2026-06-09T00:04:44.213996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07592v1","created_at":"2026-06-09T00:04:44.213996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07592","created_at":"2026-06-09T00:04:44.213996+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHX4OKLOVCUV","created_at":"2026-06-09T00:04:44.213996+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHX4OKLOVCUVU2SJ","created_at":"2026-06-09T00:04:44.213996+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHX4OKLO","created_at":"2026-06-09T00:04:44.213996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EHX4OKLOVCUVU2SJQNXIFMWN6M","json":"https://pith.science/pith/EHX4OKLOVCUVU2SJQNXIFMWN6M.json","graph_json":"https://pith.science/api/pith-number/EHX4OKLOVCUVU2SJQNXIFMWN6M/graph.json","events_json":"https://pith.science/api/pith-number/EHX4OKLOVCUVU2SJQNXIFMWN6M/events.json","paper":"https://pith.science/paper/EHX4OKLO"},"agent_actions":{"view_html":"https://pith.science/pith/EHX4OKLOVCUVU2SJQNXIFMWN6M","download_json":"https://pith.science/pith/EHX4OKLOVCUVU2SJQNXIFMWN6M.json","view_paper":"https://pith.science/paper/EHX4OKLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07592&json=true","fetch_graph":"https://pith.science/api/pith-number/EHX4OKLOVCUVU2SJQNXIFMWN6M/graph.json","fetch_events":"https://pith.science/api/pith-number/EHX4OKLOVCUVU2SJQNXIFMWN6M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHX4OKLOVCUVU2SJQNXIFMWN6M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHX4OKLOVCUVU2SJQNXIFMWN6M/action/storage_attestation","attest_author":"https://pith.science/pith/EHX4OKLOVCUVU2SJQNXIFMWN6M/action/author_attestation","sign_citation":"https://pith.science/pith/EHX4OKLOVCUVU2SJQNXIFMWN6M/action/citation_signature","submit_replication":"https://pith.science/pith/EHX4OKLOVCUVU2SJQNXIFMWN6M/action/replication_record"}},"created_at":"2026-06-09T00:04:44.213996+00:00","updated_at":"2026-06-09T00:04:44.213996+00:00"}