{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EMEQVEL4HRHRBB4ZWPMJCWY6PU","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":"5a1bcb7f7fbb4c1b49362ec4edf7f1c77af1a9eaaac3db5e94bb4f715b3ed37b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T15:18:54Z","title_canon_sha256":"aa701675061d827cff4f49d5a3a8444951210b0d09626e7fc3a4daccdd06a917"},"schema_version":"1.0","source":{"id":"2301.11774","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.11774","created_at":"2026-07-05T08:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2301.11774v3","created_at":"2026-07-05T08:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11774","created_at":"2026-07-05T08:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"EMEQVEL4HRHR","created_at":"2026-07-05T08:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"EMEQVEL4HRHRBB4Z","created_at":"2026-07-05T08:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"EMEQVEL4","created_at":"2026-07-05T08:17:03Z"}],"graph_snapshots":[{"event_id":"sha256:4ec4adfdb03ad6d74addab6121f45541e4a752b69174d626a22198e10544a16d","target":"graph","created_at":"2026-07-05T08:17:03Z","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/2301.11774/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The complexity of designing reward functions has been a major obstacle to the wide application of deep reinforcement learning (RL) techniques. Describing an agent's desired behaviors and properties can be difficult, even for experts. A new paradigm called reinforcement learning from human preferences (or preference-based RL) has emerged as a promising solution, in which reward functions are learned from human preference labels among behavior trajectories. However, existing methods for preference-based RL are limited by the need for accurate oracle preference labels. This paper addresses this l","authors_text":"Bo An, Shuicheng Yan, Wanqi Xue, Zhongwen Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T15:18:54Z","title":"Reinforcement Learning from Diverse Human Preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11774","kind":"arxiv","version":3},"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":"sha256:9a85d2b44ac9c12d4a0cd7af904a18326d71a70784596bd107aa111213425a5b","target":"record","created_at":"2026-07-05T08:17:03Z","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":"5a1bcb7f7fbb4c1b49362ec4edf7f1c77af1a9eaaac3db5e94bb4f715b3ed37b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T15:18:54Z","title_canon_sha256":"aa701675061d827cff4f49d5a3a8444951210b0d09626e7fc3a4daccdd06a917"},"schema_version":"1.0","source":{"id":"2301.11774","kind":"arxiv","version":3}},"canonical_sha256":"23090a917c3c4f108799b3d8915b1e7d23ca0efdc59f05ebc585096de1e84d88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23090a917c3c4f108799b3d8915b1e7d23ca0efdc59f05ebc585096de1e84d88","first_computed_at":"2026-07-05T08:17:03.492185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:17:03.492185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MyJAGXC1TWWtTJuOJp4mNkuEF5/EY7/hhvKbmll/GAQG9G3eWFhKrTtqc9RTEYHUGq1Y3qf/M7vyjowvK6phDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:17:03.492632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.11774","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a85d2b44ac9c12d4a0cd7af904a18326d71a70784596bd107aa111213425a5b","sha256:4ec4adfdb03ad6d74addab6121f45541e4a752b69174d626a22198e10544a16d"],"state_sha256":"914f73fd4052a0fcf36d44921546aed2444b7a464ccf145ee96d461b4e62109b"}