{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PC6D6PGMZJ4MYFK7HTS7GSQRMZ","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":"ac79f7b513b8f795feb47c2e7e84f7e87563cee1594c4b455847908717a1b5ed","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-04T17:32:06Z","title_canon_sha256":"0bbe585dc2118d4cb30ac6f210aa164fa0c49deaaafeb3dbde27e5471c8eeb4c"},"schema_version":"1.0","source":{"id":"2111.03026","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.03026","created_at":"2026-07-05T03:29:11Z"},{"alias_kind":"arxiv_version","alias_value":"2111.03026v1","created_at":"2026-07-05T03:29:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03026","created_at":"2026-07-05T03:29:11Z"},{"alias_kind":"pith_short_12","alias_value":"PC6D6PGMZJ4M","created_at":"2026-07-05T03:29:11Z"},{"alias_kind":"pith_short_16","alias_value":"PC6D6PGMZJ4MYFK7","created_at":"2026-07-05T03:29:11Z"},{"alias_kind":"pith_short_8","alias_value":"PC6D6PGM","created_at":"2026-07-05T03:29:11Z"}],"graph_snapshots":[{"event_id":"sha256:9553ba409e8b8dc026c5f2201beacecd7e689d759d09923424d2f0d57f4828d3","target":"graph","created_at":"2026-07-05T03:29:11Z","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/2111.03026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) requires access to a reward function that incentivizes the right behavior, but these are notoriously hard to specify for complex tasks. Preference-based RL provides an alternative: learning policies using a teacher's preferences without pre-defined rewards, thus overcoming concerns associated with reward engineering. However, it is difficult to quantify the progress in preference-based RL due to the lack of a commonly adopted benchmark. In this paper, we introduce B-Pref: a benchmark specially designed for preference-based RL. A key challenge with such a benchmark i","authors_text":"Anca Dragan, Kimin Lee, Laura Smith, Pieter Abbeel","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-04T17:32:06Z","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03026","kind":"arxiv","version":1},"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":"sha256:1e136db82179d4dc43af84ab136c95223f562257382c56796074921a681383c7","target":"record","created_at":"2026-07-05T03:29:11Z","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":"ac79f7b513b8f795feb47c2e7e84f7e87563cee1594c4b455847908717a1b5ed","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-04T17:32:06Z","title_canon_sha256":"0bbe585dc2118d4cb30ac6f210aa164fa0c49deaaafeb3dbde27e5471c8eeb4c"},"schema_version":"1.0","source":{"id":"2111.03026","kind":"arxiv","version":1}},"canonical_sha256":"78bc3f3cccca78cc155f3ce5f34a1166599ec621e54423d3d603a5a365cbbd26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78bc3f3cccca78cc155f3ce5f34a1166599ec621e54423d3d603a5a365cbbd26","first_computed_at":"2026-07-05T03:29:11.543347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:29:11.543347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gkO3K7UllplvqROGEDq7agJiVGNgV1hiHZjw8ux0RhhDiTJip+f7F9oa9dGsqg1e7QoZBEul2q+W+Hb4yhCuCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:29:11.543809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.03026","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e136db82179d4dc43af84ab136c95223f562257382c56796074921a681383c7","sha256:9553ba409e8b8dc026c5f2201beacecd7e689d759d09923424d2f0d57f4828d3"],"state_sha256":"8915e816476648869302ab474588ad2451065913b16b727e616b3b73228d4c04"}