{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SGPRMKKCRS4TXFCH53O6FHYKVB","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":"ac49fc9c03b5c8d1b5a3aafd699082a72a7e8eb65446956599f1aa44188a7113","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-16T17:51:33Z","title_canon_sha256":"94120c3ee96eb4a4e656ed2d1e354d30857003bf009de86148347fb646a0ce31"},"schema_version":"1.0","source":{"id":"2506.13741","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.13741","created_at":"2026-07-05T11:22:25Z"},{"alias_kind":"arxiv_version","alias_value":"2506.13741v1","created_at":"2026-07-05T11:22:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13741","created_at":"2026-07-05T11:22:25Z"},{"alias_kind":"pith_short_12","alias_value":"SGPRMKKCRS4T","created_at":"2026-07-05T11:22:25Z"},{"alias_kind":"pith_short_16","alias_value":"SGPRMKKCRS4TXFCH","created_at":"2026-07-05T11:22:25Z"},{"alias_kind":"pith_short_8","alias_value":"SGPRMKKC","created_at":"2026-07-05T11:22:25Z"}],"graph_snapshots":[{"event_id":"sha256:f0e38e97c02c21fe4f02196f407329d85f3ea365542844220bd4c594f4ca4448","target":"graph","created_at":"2026-07-05T11:22:25Z","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/2506.13741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based reinforcement learning (PbRL) has emerged as a promising approach for learning behaviors from human feedback without predefined reward functions. However, current PbRL methods face a critical challenge in effectively exploring the preference space, often converging prematurely to suboptimal policies that satisfy only a narrow subset of human preferences. In this work, we identify and address this preference exploration problem through population-based methods. We demonstrate that maintaining a diverse population of agents enables more comprehensive exploration of the preferenc","authors_text":"Alex Davey, Brahim Driss, Riad Akrour","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-16T17:51:33Z","title":"PB$^2$: Preference Space Exploration via Population-Based Methods in Preference-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13741","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:f5a91ea535413ec9d835aa39a0203b4380cfa57b1c46cabbdf13cd04c8f63284","target":"record","created_at":"2026-07-05T11:22:25Z","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":"ac49fc9c03b5c8d1b5a3aafd699082a72a7e8eb65446956599f1aa44188a7113","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-16T17:51:33Z","title_canon_sha256":"94120c3ee96eb4a4e656ed2d1e354d30857003bf009de86148347fb646a0ce31"},"schema_version":"1.0","source":{"id":"2506.13741","kind":"arxiv","version":1}},"canonical_sha256":"919f1629428cb93b9447eedde29f0aa841ab5a07d1704becfd064e99c3d79991","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"919f1629428cb93b9447eedde29f0aa841ab5a07d1704becfd064e99c3d79991","first_computed_at":"2026-07-05T11:22:25.905341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:25.905341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D2+pKkZT636yMZ0KlDhOTw5qal5AS3/fvu7DD4EwbL101a+bwHMZnKDuviEnaCDT2JB8yR09JqvmdTHV/TNCCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:25.905866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.13741","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5a91ea535413ec9d835aa39a0203b4380cfa57b1c46cabbdf13cd04c8f63284","sha256:f0e38e97c02c21fe4f02196f407329d85f3ea365542844220bd4c594f4ca4448"],"state_sha256":"5cb4deeee104707f4e757a27880891215e8178c9303d119c3f1fc2dfac9c2e0c"}