{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WKGHPHPZQYYKYPMEXUYPB57OYE","short_pith_number":"pith:WKGHPHPZ","schema_version":"1.0","canonical_sha256":"b28c779df98630ac3d84bd30f0f7eec12005e3ae9652346ccceb7fcdbd8b2521","source":{"kind":"arxiv","id":"2307.12975","version":2},"attestation_state":"computed","paper":{"title":"Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Huazheng Wang, Mengdi Wang, Minshuo Chen, Tuo Zhao, Xiang Ji","submitted_at":"2023-07-24T17:50:24Z","abstract_excerpt":"For a real-world decision-making problem, the reward function often needs to be engineered or learned. A popular approach is to utilize human feedback to learn a reward function for training. The most straightforward way to do so is to ask humans to provide ratings for state-action pairs on an absolute scale and take these ratings as reward samples directly. Another popular way is to ask humans to rank a small set of state-action pairs by preference and learn a reward function from these preference data. Recently, preference-based methods have demonstrated substantial success in empirical appl"},"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":"2307.12975","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-24T17:50:24Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"39efa5ec32ac2eb63e7da309150a2c262855e4b3d1f1897721b0a83a6e61a8cd","abstract_canon_sha256":"1bb32f2857adc005c2850076f4ac4aab884a52e7c351f0b0c09d53815bb08566"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:32.446389Z","signature_b64":"yJVV55ctQ9/5iR45uyK6uzYDBLz/VQe9LArXlD+mJcIicsTxMrUC7+P7uXqyYsZEOJihDbRQo4sIjB7+RNqRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b28c779df98630ac3d84bd30f0f7eec12005e3ae9652346ccceb7fcdbd8b2521","last_reissued_at":"2026-07-05T07:06:32.445639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:32.445639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Huazheng Wang, Mengdi Wang, Minshuo Chen, Tuo Zhao, Xiang Ji","submitted_at":"2023-07-24T17:50:24Z","abstract_excerpt":"For a real-world decision-making problem, the reward function often needs to be engineered or learned. A popular approach is to utilize human feedback to learn a reward function for training. The most straightforward way to do so is to ask humans to provide ratings for state-action pairs on an absolute scale and take these ratings as reward samples directly. Another popular way is to ask humans to rank a small set of state-action pairs by preference and learn a reward function from these preference data. Recently, preference-based methods have demonstrated substantial success in empirical appl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12975","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/2307.12975/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":"2307.12975","created_at":"2026-07-05T07:06:32.445707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12975v2","created_at":"2026-07-05T07:06:32.445707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12975","created_at":"2026-07-05T07:06:32.445707+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKGHPHPZQYYK","created_at":"2026-07-05T07:06:32.445707+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKGHPHPZQYYKYPME","created_at":"2026-07-05T07:06:32.445707+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKGHPHPZ","created_at":"2026-07-05T07:06:32.445707+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/WKGHPHPZQYYKYPMEXUYPB57OYE","json":"https://pith.science/pith/WKGHPHPZQYYKYPMEXUYPB57OYE.json","graph_json":"https://pith.science/api/pith-number/WKGHPHPZQYYKYPMEXUYPB57OYE/graph.json","events_json":"https://pith.science/api/pith-number/WKGHPHPZQYYKYPMEXUYPB57OYE/events.json","paper":"https://pith.science/paper/WKGHPHPZ"},"agent_actions":{"view_html":"https://pith.science/pith/WKGHPHPZQYYKYPMEXUYPB57OYE","download_json":"https://pith.science/pith/WKGHPHPZQYYKYPMEXUYPB57OYE.json","view_paper":"https://pith.science/paper/WKGHPHPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12975&json=true","fetch_graph":"https://pith.science/api/pith-number/WKGHPHPZQYYKYPMEXUYPB57OYE/graph.json","fetch_events":"https://pith.science/api/pith-number/WKGHPHPZQYYKYPMEXUYPB57OYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKGHPHPZQYYKYPMEXUYPB57OYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKGHPHPZQYYKYPMEXUYPB57OYE/action/storage_attestation","attest_author":"https://pith.science/pith/WKGHPHPZQYYKYPMEXUYPB57OYE/action/author_attestation","sign_citation":"https://pith.science/pith/WKGHPHPZQYYKYPMEXUYPB57OYE/action/citation_signature","submit_replication":"https://pith.science/pith/WKGHPHPZQYYKYPMEXUYPB57OYE/action/replication_record"}},"created_at":"2026-07-05T07:06:32.445707+00:00","updated_at":"2026-07-05T07:06:32.445707+00:00"}