{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WKGHPHPZQYYKYPMEXUYPB57OYE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1bb32f2857adc005c2850076f4ac4aab884a52e7c351f0b0c09d53815bb08566","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-24T17:50:24Z","title_canon_sha256":"39efa5ec32ac2eb63e7da309150a2c262855e4b3d1f1897721b0a83a6e61a8cd"},"schema_version":"1.0","source":{"id":"2307.12975","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.12975","created_at":"2026-07-05T07:06:32Z"},{"alias_kind":"arxiv_version","alias_value":"2307.12975v2","created_at":"2026-07-05T07:06:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12975","created_at":"2026-07-05T07:06:32Z"},{"alias_kind":"pith_short_12","alias_value":"WKGHPHPZQYYK","created_at":"2026-07-05T07:06:32Z"},{"alias_kind":"pith_short_16","alias_value":"WKGHPHPZQYYKYPME","created_at":"2026-07-05T07:06:32Z"},{"alias_kind":"pith_short_8","alias_value":"WKGHPHPZ","created_at":"2026-07-05T07:06:32Z"}],"graph_snapshots":[{"event_id":"sha256:6579c936e01c5747596e56d15674fffb0c9be836db6a00d94e6b49ab98758afb","target":"graph","created_at":"2026-07-05T07:06:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2307.12975/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Huazheng Wang, Mengdi Wang, Minshuo Chen, Tuo Zhao, Xiang Ji","cross_cats":["math.ST","stat.ML","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-24T17:50:24Z","title":"Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12975","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:07cfc89d83ebc022acb450959d22ac65d2932fdecc84d3c0e642a4ee74c86b8f","target":"record","created_at":"2026-07-05T07:06:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1bb32f2857adc005c2850076f4ac4aab884a52e7c351f0b0c09d53815bb08566","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-24T17:50:24Z","title_canon_sha256":"39efa5ec32ac2eb63e7da309150a2c262855e4b3d1f1897721b0a83a6e61a8cd"},"schema_version":"1.0","source":{"id":"2307.12975","kind":"arxiv","version":2}},"canonical_sha256":"b28c779df98630ac3d84bd30f0f7eec12005e3ae9652346ccceb7fcdbd8b2521","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b28c779df98630ac3d84bd30f0f7eec12005e3ae9652346ccceb7fcdbd8b2521","first_computed_at":"2026-07-05T07:06:32.445639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:32.445639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yJVV55ctQ9/5iR45uyK6uzYDBLz/VQe9LArXlD+mJcIicsTxMrUC7+P7uXqyYsZEOJihDbRQo4sIjB7+RNqRBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:32.446389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.12975","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07cfc89d83ebc022acb450959d22ac65d2932fdecc84d3c0e642a4ee74c86b8f","sha256:6579c936e01c5747596e56d15674fffb0c9be836db6a00d94e6b49ab98758afb"],"state_sha256":"12fc8c50a50dfbbd4bff44f0c85db8dfd7874e61a6e087bfc42c55eb9c7d5f35"}