{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZNGSSIMVE3IY4PALCQ6N77AMN7","short_pith_number":"pith:ZNGSSIMV","schema_version":"1.0","canonical_sha256":"cb4d29219526d18e3c0b143cdffc0c6ff9d35df20357b39256177032c47b601c","source":{"kind":"arxiv","id":"2501.18282","version":4},"attestation_state":"computed","paper":{"title":"Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lie He, Michael Gastpar, Yunzhen Yao","submitted_at":"2025-01-30T11:41:13Z","abstract_excerpt":"This paper considers the sample-efficiency of preference learning, which models and predicts human choices based on comparative judgments. The minimax optimal estimation error rate $\\Theta(d/n)$ in classical estimation theory requires that the number of samples $n$ scales linearly with the dimensionality of the feature space $d$. However, the high dimensionality of the feature space and the high cost of collecting human-annotated data challenge the efficiency of traditional estimation methods. To remedy this, we leverage sparsity in the preference model and establish sharp error rates. We show"},"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":"2501.18282","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T11:41:13Z","cross_cats_sorted":[],"title_canon_sha256":"3bf62a792a8a1dad3f06b44caf4e20b43079c729383d2f3cb0391d0db7e380ec","abstract_canon_sha256":"f014d33c6f1685f3659de561289777ac15a0e981d3469925b7cb30158c746610"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:19.141916Z","signature_b64":"JMZf6uyW36jqkoICsP/ewoPIrQZvycjwpAC0uxF1VREEh46zCVjcj7h7+V/0BtGLl7DGv7POpb5LyC7ToFNPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb4d29219526d18e3c0b143cdffc0c6ff9d35df20357b39256177032c47b601c","last_reissued_at":"2026-07-05T11:15:19.141479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:19.141479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lie He, Michael Gastpar, Yunzhen Yao","submitted_at":"2025-01-30T11:41:13Z","abstract_excerpt":"This paper considers the sample-efficiency of preference learning, which models and predicts human choices based on comparative judgments. The minimax optimal estimation error rate $\\Theta(d/n)$ in classical estimation theory requires that the number of samples $n$ scales linearly with the dimensionality of the feature space $d$. However, the high dimensionality of the feature space and the high cost of collecting human-annotated data challenge the efficiency of traditional estimation methods. To remedy this, we leverage sparsity in the preference model and establish sharp error rates. We show"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18282","kind":"arxiv","version":4},"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/2501.18282/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":"2501.18282","created_at":"2026-07-05T11:15:19.141539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18282v4","created_at":"2026-07-05T11:15:19.141539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18282","created_at":"2026-07-05T11:15:19.141539+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNGSSIMVE3IY","created_at":"2026-07-05T11:15:19.141539+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNGSSIMVE3IY4PAL","created_at":"2026-07-05T11:15:19.141539+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNGSSIMV","created_at":"2026-07-05T11:15:19.141539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23557","citing_title":"Learning Parametric Distributions from Samples and Preferences","ref_index":2013,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZNGSSIMVE3IY4PALCQ6N77AMN7","json":"https://pith.science/pith/ZNGSSIMVE3IY4PALCQ6N77AMN7.json","graph_json":"https://pith.science/api/pith-number/ZNGSSIMVE3IY4PALCQ6N77AMN7/graph.json","events_json":"https://pith.science/api/pith-number/ZNGSSIMVE3IY4PALCQ6N77AMN7/events.json","paper":"https://pith.science/paper/ZNGSSIMV"},"agent_actions":{"view_html":"https://pith.science/pith/ZNGSSIMVE3IY4PALCQ6N77AMN7","download_json":"https://pith.science/pith/ZNGSSIMVE3IY4PALCQ6N77AMN7.json","view_paper":"https://pith.science/paper/ZNGSSIMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18282&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNGSSIMVE3IY4PALCQ6N77AMN7/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNGSSIMVE3IY4PALCQ6N77AMN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNGSSIMVE3IY4PALCQ6N77AMN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNGSSIMVE3IY4PALCQ6N77AMN7/action/storage_attestation","attest_author":"https://pith.science/pith/ZNGSSIMVE3IY4PALCQ6N77AMN7/action/author_attestation","sign_citation":"https://pith.science/pith/ZNGSSIMVE3IY4PALCQ6N77AMN7/action/citation_signature","submit_replication":"https://pith.science/pith/ZNGSSIMVE3IY4PALCQ6N77AMN7/action/replication_record"}},"created_at":"2026-07-05T11:15:19.141539+00:00","updated_at":"2026-07-05T11:15:19.141539+00:00"}