{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:26WK7BJTHBDNKJHJ7U6PEJOUWZ","short_pith_number":"pith:26WK7BJT","schema_version":"1.0","canonical_sha256":"d7acaf85333846d524e9fd3cf225d4b671e76aa81dc542f9d503182ddfceabfa","source":{"kind":"arxiv","id":"2607.14373","version":1},"attestation_state":"computed","paper":{"title":"A Noise-Robust Elicit-to-Optimize Framework for Distortion Riskmetrics via Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-fin.RM"],"primary_cat":"cs.LG","authors_text":"Yang Liu, Yuhao Liu, Yunran Wei","submitted_at":"2026-07-15T21:22:50Z","abstract_excerpt":"We propose a noise-robust elicit-to-optimize framework that integrates inverse reinforcement learning (IRL) and reinforcement learning (RL) for eliciting agents' risk preferences and optimizing policies under a broad class of risk objectives characterized by distortion riskmetrics. On the elicitation side, we propose an adaptive Bayesian IRL method that infers agents' latent risk objectives from their noisy observed decisions, explicitly allowing agents to take stochastic and suboptimal actions. We establish the existence of a finite set of distinguishing questions that identifies the preferre"},"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":"2607.14373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T21:22:50Z","cross_cats_sorted":["q-fin.RM"],"title_canon_sha256":"7c47877e96bca92a32e910227f0f163a6ab48912d363d813e1f29338f9ca5359","abstract_canon_sha256":"75cf6418d74087e28ac65da1bbaf7d6c238f6fc3ed8a71b826627dd02788f9c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:21:08.424763Z","signature_b64":"79FQka6a646tm25+hk/fZvykXGSjF9iqzh9APEo6aqkOU8O9VcOUNpA/AbHpEUrwtYq3z5oPgEhEnqOi9V1kAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7acaf85333846d524e9fd3cf225d4b671e76aa81dc542f9d503182ddfceabfa","last_reissued_at":"2026-07-17T00:21:08.423926Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:21:08.423926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Noise-Robust Elicit-to-Optimize Framework for Distortion Riskmetrics via Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-fin.RM"],"primary_cat":"cs.LG","authors_text":"Yang Liu, Yuhao Liu, Yunran Wei","submitted_at":"2026-07-15T21:22:50Z","abstract_excerpt":"We propose a noise-robust elicit-to-optimize framework that integrates inverse reinforcement learning (IRL) and reinforcement learning (RL) for eliciting agents' risk preferences and optimizing policies under a broad class of risk objectives characterized by distortion riskmetrics. On the elicitation side, we propose an adaptive Bayesian IRL method that infers agents' latent risk objectives from their noisy observed decisions, explicitly allowing agents to take stochastic and suboptimal actions. We establish the existence of a finite set of distinguishing questions that identifies the preferre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14373","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/2607.14373/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":"2607.14373","created_at":"2026-07-17T00:21:08.424362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14373v1","created_at":"2026-07-17T00:21:08.424362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14373","created_at":"2026-07-17T00:21:08.424362+00:00"},{"alias_kind":"pith_short_12","alias_value":"26WK7BJTHBDN","created_at":"2026-07-17T00:21:08.424362+00:00"},{"alias_kind":"pith_short_16","alias_value":"26WK7BJTHBDNKJHJ","created_at":"2026-07-17T00:21:08.424362+00:00"},{"alias_kind":"pith_short_8","alias_value":"26WK7BJT","created_at":"2026-07-17T00:21:08.424362+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/26WK7BJTHBDNKJHJ7U6PEJOUWZ","json":"https://pith.science/pith/26WK7BJTHBDNKJHJ7U6PEJOUWZ.json","graph_json":"https://pith.science/api/pith-number/26WK7BJTHBDNKJHJ7U6PEJOUWZ/graph.json","events_json":"https://pith.science/api/pith-number/26WK7BJTHBDNKJHJ7U6PEJOUWZ/events.json","paper":"https://pith.science/paper/26WK7BJT"},"agent_actions":{"view_html":"https://pith.science/pith/26WK7BJTHBDNKJHJ7U6PEJOUWZ","download_json":"https://pith.science/pith/26WK7BJTHBDNKJHJ7U6PEJOUWZ.json","view_paper":"https://pith.science/paper/26WK7BJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14373&json=true","fetch_graph":"https://pith.science/api/pith-number/26WK7BJTHBDNKJHJ7U6PEJOUWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/26WK7BJTHBDNKJHJ7U6PEJOUWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26WK7BJTHBDNKJHJ7U6PEJOUWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26WK7BJTHBDNKJHJ7U6PEJOUWZ/action/storage_attestation","attest_author":"https://pith.science/pith/26WK7BJTHBDNKJHJ7U6PEJOUWZ/action/author_attestation","sign_citation":"https://pith.science/pith/26WK7BJTHBDNKJHJ7U6PEJOUWZ/action/citation_signature","submit_replication":"https://pith.science/pith/26WK7BJTHBDNKJHJ7U6PEJOUWZ/action/replication_record"}},"created_at":"2026-07-17T00:21:08.424362+00:00","updated_at":"2026-07-17T00:21:08.424362+00:00"}