{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XIKWTPESKNKHOQVQTA7GVKI2NK","short_pith_number":"pith:XIKWTPES","schema_version":"1.0","canonical_sha256":"ba1569bc9253547742b0983e6aa91a6a9390f28fd180f9eba8a599e77963b4c1","source":{"kind":"arxiv","id":"2510.15839","version":2},"attestation_state":"computed","paper":{"title":"Learning Correlated Reward Models: Statistical Barriers and Opportunities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["econ.EM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Constantinos Daskalakis, Gabriele Farina, Sobhan Mohammadpour, Yeshwanth Cherapanamjeri","submitted_at":"2025-10-17T17:31:17Z","abstract_excerpt":"Random Utility Models (RUMs) are a classical framework for modeling user preferences and play a key role in reward modeling for Reinforcement Learning from Human Feedback (RLHF). However, a crucial shortcoming of many of these techniques is the Independence of Irrelevant Alternatives (IIA) assumption, which collapses \\emph{all} human preferences to a universal underlying utility function, yielding a coarse approximation of the range of human preferences. On the other hand, statistical and computational guarantees for models avoiding this assumption are scarce. In this paper, we investigate the"},"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":"2510.15839","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-17T17:31:17Z","cross_cats_sorted":["econ.EM","stat.ML"],"title_canon_sha256":"8d9a05d9a17ecb2dbdda245872e5370ef29ef9cc12d851b78178f7bcdcfaaf3e","abstract_canon_sha256":"447b5ef37072281d202ebc6937dcde0ade78b9e68b06022becfd1029c11621f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:31.752553Z","signature_b64":"aM6Pvorgun1B6u6ZCi2PHifY+jXXXwRfwHMOM/0wZNTInxbCxtX2UdJePHMVN81Dg1jWbpkq4e80sx30oQIxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba1569bc9253547742b0983e6aa91a6a9390f28fd180f9eba8a599e77963b4c1","last_reissued_at":"2026-05-28T01:04:31.752040Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:31.752040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Correlated Reward Models: Statistical Barriers and Opportunities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["econ.EM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Constantinos Daskalakis, Gabriele Farina, Sobhan Mohammadpour, Yeshwanth Cherapanamjeri","submitted_at":"2025-10-17T17:31:17Z","abstract_excerpt":"Random Utility Models (RUMs) are a classical framework for modeling user preferences and play a key role in reward modeling for Reinforcement Learning from Human Feedback (RLHF). However, a crucial shortcoming of many of these techniques is the Independence of Irrelevant Alternatives (IIA) assumption, which collapses \\emph{all} human preferences to a universal underlying utility function, yielding a coarse approximation of the range of human preferences. On the other hand, statistical and computational guarantees for models avoiding this assumption are scarce. In this paper, we investigate the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.15839","kind":"arxiv","version":2},"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/2510.15839/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":"2510.15839","created_at":"2026-05-28T01:04:31.752099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.15839v2","created_at":"2026-05-28T01:04:31.752099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.15839","created_at":"2026-05-28T01:04:31.752099+00:00"},{"alias_kind":"pith_short_12","alias_value":"XIKWTPESKNKH","created_at":"2026-05-28T01:04:31.752099+00:00"},{"alias_kind":"pith_short_16","alias_value":"XIKWTPESKNKHOQVQ","created_at":"2026-05-28T01:04:31.752099+00:00"},{"alias_kind":"pith_short_8","alias_value":"XIKWTPES","created_at":"2026-05-28T01:04:31.752099+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/XIKWTPESKNKHOQVQTA7GVKI2NK","json":"https://pith.science/pith/XIKWTPESKNKHOQVQTA7GVKI2NK.json","graph_json":"https://pith.science/api/pith-number/XIKWTPESKNKHOQVQTA7GVKI2NK/graph.json","events_json":"https://pith.science/api/pith-number/XIKWTPESKNKHOQVQTA7GVKI2NK/events.json","paper":"https://pith.science/paper/XIKWTPES"},"agent_actions":{"view_html":"https://pith.science/pith/XIKWTPESKNKHOQVQTA7GVKI2NK","download_json":"https://pith.science/pith/XIKWTPESKNKHOQVQTA7GVKI2NK.json","view_paper":"https://pith.science/paper/XIKWTPES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.15839&json=true","fetch_graph":"https://pith.science/api/pith-number/XIKWTPESKNKHOQVQTA7GVKI2NK/graph.json","fetch_events":"https://pith.science/api/pith-number/XIKWTPESKNKHOQVQTA7GVKI2NK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XIKWTPESKNKHOQVQTA7GVKI2NK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XIKWTPESKNKHOQVQTA7GVKI2NK/action/storage_attestation","attest_author":"https://pith.science/pith/XIKWTPESKNKHOQVQTA7GVKI2NK/action/author_attestation","sign_citation":"https://pith.science/pith/XIKWTPESKNKHOQVQTA7GVKI2NK/action/citation_signature","submit_replication":"https://pith.science/pith/XIKWTPESKNKHOQVQTA7GVKI2NK/action/replication_record"}},"created_at":"2026-05-28T01:04:31.752099+00:00","updated_at":"2026-05-28T01:04:31.752099+00:00"}