{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CPZKZYOOHWOAYHMZS7HQBQXDEU","short_pith_number":"pith:CPZKZYOO","canonical_record":{"source":{"id":"2606.19328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T17:54:32Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"f944da524b2fe1f306063a976819379f05abaa065fe96ec3d93504ba5cbf4795","abstract_canon_sha256":"8dffbbf982dcf913024c528554ff64c3100866d6ad4e1c3e3c5aad9dce50e70b"},"schema_version":"1.0"},"canonical_sha256":"13f2ace1ce3d9c0c1d9997cf00c2e3250b743fbad6aa59377372925e1459a747","source":{"kind":"arxiv","id":"2606.19328","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19328","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19328v1","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19328","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"CPZKZYOOHWOA","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"CPZKZYOOHWOAYHMZ","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"CPZKZYOO","created_at":"2026-06-19T16:12:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CPZKZYOOHWOAYHMZS7HQBQXDEU","target":"record","payload":{"canonical_record":{"source":{"id":"2606.19328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T17:54:32Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"f944da524b2fe1f306063a976819379f05abaa065fe96ec3d93504ba5cbf4795","abstract_canon_sha256":"8dffbbf982dcf913024c528554ff64c3100866d6ad4e1c3e3c5aad9dce50e70b"},"schema_version":"1.0"},"canonical_sha256":"13f2ace1ce3d9c0c1d9997cf00c2e3250b743fbad6aa59377372925e1459a747","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:11.255532Z","signature_b64":"DTmkd7zH+sv5RvP26Sp131szfvmkTESN5QM/TuTUxWu+F7CZksdJiIjA1Jr1eYUWyZje/NiALdD1RxsmidF3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13f2ace1ce3d9c0c1d9997cf00c2e3250b743fbad6aa59377372925e1459a747","last_reissued_at":"2026-06-19T16:12:11.255187Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:11.255187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.19328","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:12:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"74bLAzmf6UWWU9Zy4S5pm54iSjkWEqGQgK3k6J6kZTlorGu8/q82++VixD0cinIy6S9Zx/16SdVGs2Kvm0zrBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T05:45:58.035721Z"},"content_sha256":"aa48a1d058165824cc2f3333190ac88170aece7b74a4571bb51acfd2d675ae10","schema_version":"1.0","event_id":"sha256:aa48a1d058165824cc2f3333190ac88170aece7b74a4571bb51acfd2d675ae10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CPZKZYOOHWOAYHMZS7HQBQXDEU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jingmin Wang, Leo Cheng, Mohamed Nabail, Nicholas Rhinehart","submitted_at":"2026-06-17T17:54:32Z","abstract_excerpt":"Preference-based RL provides an approach to learning reward models from pairwise comparisons of behaviors, bypassing the need for explicit reward design. However, existing methods typically rely on passive data collection and suffer from poor sample efficiency, especially during the early stages of learning. We introduce a model-based approach that actively directs exploration by jointly reasoning over uncertainties in the reward, dynamics, and value functions. Our method, Uncertainty-Balanced Preference Planning (UBP2), uses ensembles of reward, dynamics, and value function models to evaluate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19328","kind":"arxiv","version":1},"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/2606.19328/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":"2026-06-19T16:12:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zh7R3AZp93Zw0BYcgPkA1KV/G+fvGHK3+13YT4bgIOLYJMKS+RqPi8vySK7bRHU5zOfldU3I5VVSup12RmVBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T05:45:58.036118Z"},"content_sha256":"e3072033e5b36f57f1d7249386861ef260d3d6c6b873ae369f27cc89360c792e","schema_version":"1.0","event_id":"sha256:e3072033e5b36f57f1d7249386861ef260d3d6c6b873ae369f27cc89360c792e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CPZKZYOOHWOAYHMZS7HQBQXDEU/bundle.json","state_url":"https://pith.science/pith/CPZKZYOOHWOAYHMZS7HQBQXDEU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CPZKZYOOHWOAYHMZS7HQBQXDEU/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":"2026-06-24T05:45:58Z","links":{"resolver":"https://pith.science/pith/CPZKZYOOHWOAYHMZS7HQBQXDEU","bundle":"https://pith.science/pith/CPZKZYOOHWOAYHMZS7HQBQXDEU/bundle.json","state":"https://pith.science/pith/CPZKZYOOHWOAYHMZS7HQBQXDEU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CPZKZYOOHWOAYHMZS7HQBQXDEU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CPZKZYOOHWOAYHMZS7HQBQXDEU","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":"8dffbbf982dcf913024c528554ff64c3100866d6ad4e1c3e3c5aad9dce50e70b","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T17:54:32Z","title_canon_sha256":"f944da524b2fe1f306063a976819379f05abaa065fe96ec3d93504ba5cbf4795"},"schema_version":"1.0","source":{"id":"2606.19328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19328","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19328v1","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19328","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"CPZKZYOOHWOA","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"CPZKZYOOHWOAYHMZ","created_at":"2026-06-19T16:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"CPZKZYOO","created_at":"2026-06-19T16:12:11Z"}],"graph_snapshots":[{"event_id":"sha256:e3072033e5b36f57f1d7249386861ef260d3d6c6b873ae369f27cc89360c792e","target":"graph","created_at":"2026-06-19T16:12:11Z","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/2606.19328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based RL provides an approach to learning reward models from pairwise comparisons of behaviors, bypassing the need for explicit reward design. However, existing methods typically rely on passive data collection and suffer from poor sample efficiency, especially during the early stages of learning. We introduce a model-based approach that actively directs exploration by jointly reasoning over uncertainties in the reward, dynamics, and value functions. Our method, Uncertainty-Balanced Preference Planning (UBP2), uses ensembles of reward, dynamics, and value function models to evaluate","authors_text":"Jingmin Wang, Leo Cheng, Mohamed Nabail, Nicholas Rhinehart","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T17:54:32Z","title":"UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19328","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:aa48a1d058165824cc2f3333190ac88170aece7b74a4571bb51acfd2d675ae10","target":"record","created_at":"2026-06-19T16:12:11Z","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":"8dffbbf982dcf913024c528554ff64c3100866d6ad4e1c3e3c5aad9dce50e70b","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T17:54:32Z","title_canon_sha256":"f944da524b2fe1f306063a976819379f05abaa065fe96ec3d93504ba5cbf4795"},"schema_version":"1.0","source":{"id":"2606.19328","kind":"arxiv","version":1}},"canonical_sha256":"13f2ace1ce3d9c0c1d9997cf00c2e3250b743fbad6aa59377372925e1459a747","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13f2ace1ce3d9c0c1d9997cf00c2e3250b743fbad6aa59377372925e1459a747","first_computed_at":"2026-06-19T16:12:11.255187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:11.255187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DTmkd7zH+sv5RvP26Sp131szfvmkTESN5QM/TuTUxWu+F7CZksdJiIjA1Jr1eYUWyZje/NiALdD1RxsmidF3Cw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:11.255532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa48a1d058165824cc2f3333190ac88170aece7b74a4571bb51acfd2d675ae10","sha256:e3072033e5b36f57f1d7249386861ef260d3d6c6b873ae369f27cc89360c792e"],"state_sha256":"73933948ba4a433d53cf1f3a208ad26d3374fbf3df859b84ac4a46e11cf904b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9pNqK0XxhuAczgkZhjzcZ05cQ03K9gGsz4BWuG0v84k4AUar4mDxoa2FsoZ0OBbWC0oYbcUpOi7NfG2KhN5xAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T05:45:58.038372Z","bundle_sha256":"b117ebd06c60dd847287f0c9f76a46a13384aebd795844d874312aa8418c026b"}}