{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EMEQVEL4HRHRBB4ZWPMJCWY6PU","short_pith_number":"pith:EMEQVEL4","canonical_record":{"source":{"id":"2301.11774","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T15:18:54Z","cross_cats_sorted":[],"title_canon_sha256":"aa701675061d827cff4f49d5a3a8444951210b0d09626e7fc3a4daccdd06a917","abstract_canon_sha256":"5a1bcb7f7fbb4c1b49362ec4edf7f1c77af1a9eaaac3db5e94bb4f715b3ed37b"},"schema_version":"1.0"},"canonical_sha256":"23090a917c3c4f108799b3d8915b1e7d23ca0efdc59f05ebc585096de1e84d88","source":{"kind":"arxiv","id":"2301.11774","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EMEQVEL4HRHRBB4ZWPMJCWY6PU","target":"record","payload":{"canonical_record":{"source":{"id":"2301.11774","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-27T15:18:54Z","cross_cats_sorted":[],"title_canon_sha256":"aa701675061d827cff4f49d5a3a8444951210b0d09626e7fc3a4daccdd06a917","abstract_canon_sha256":"5a1bcb7f7fbb4c1b49362ec4edf7f1c77af1a9eaaac3db5e94bb4f715b3ed37b"},"schema_version":"1.0"},"canonical_sha256":"23090a917c3c4f108799b3d8915b1e7d23ca0efdc59f05ebc585096de1e84d88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:03.492632Z","signature_b64":"MyJAGXC1TWWtTJuOJp4mNkuEF5/EY7/hhvKbmll/GAQG9G3eWFhKrTtqc9RTEYHUGq1Y3qf/M7vyjowvK6phDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23090a917c3c4f108799b3d8915b1e7d23ca0efdc59f05ebc585096de1e84d88","last_reissued_at":"2026-07-05T08:17:03.492185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:03.492185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.11774","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:17:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d2P6kfV40nR59PIUxBW/sOiI0+t9IfCRjRrBmXWe8x5WIy7yyH8Z7S1cjpGBG/Nxt329L1CsYbB7R+zw36UjDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:35:53.396755Z"},"content_sha256":"9a85d2b44ac9c12d4a0cd7af904a18326d71a70784596bd107aa111213425a5b","schema_version":"1.0","event_id":"sha256:9a85d2b44ac9c12d4a0cd7af904a18326d71a70784596bd107aa111213425a5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EMEQVEL4HRHRBB4ZWPMJCWY6PU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning from Diverse Human Preferences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo An, Shuicheng Yan, Wanqi Xue, Zhongwen Xu","submitted_at":"2023-01-27T15:18:54Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11774","kind":"arxiv","version":3},"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/2301.11774/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:17:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6fatPYdwJfvvcLaAIEdtFJJdyU1iC1ZTFbvyrSUkDXQZpRdfKKlXqxgMhq2M2NngEc0W8caJcasBi3F20sZ6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:35:53.397250Z"},"content_sha256":"4ec4adfdb03ad6d74addab6121f45541e4a752b69174d626a22198e10544a16d","schema_version":"1.0","event_id":"sha256:4ec4adfdb03ad6d74addab6121f45541e4a752b69174d626a22198e10544a16d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EMEQVEL4HRHRBB4ZWPMJCWY6PU/bundle.json","state_url":"https://pith.science/pith/EMEQVEL4HRHRBB4ZWPMJCWY6PU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EMEQVEL4HRHRBB4ZWPMJCWY6PU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T17:35:53Z","links":{"resolver":"https://pith.science/pith/EMEQVEL4HRHRBB4ZWPMJCWY6PU","bundle":"https://pith.science/pith/EMEQVEL4HRHRBB4ZWPMJCWY6PU/bundle.json","state":"https://pith.science/pith/EMEQVEL4HRHRBB4ZWPMJCWY6PU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EMEQVEL4HRHRBB4ZWPMJCWY6PU/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q+LqfJUit88BHsspJRzI1wZYqOABngZjsZ0/fGHUn0jNAZRv1SWMhrTTzzc6eO6ltGqQVovoeMcBO2NZL326Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:35:53.402592Z","bundle_sha256":"ddddd0825f25fb1fa19dcb4b9fcad025ae1e74609961b89c2ac17b8fb654481f"}}