{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_2b2626e1e6cb9788b47ab422cf1673d6a7b63558b44aa990458e7895fa1f30db","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_2b2626e1e6cb9788b47ab422cf1673d6a7b63558b44aa990458e7895fa1f30db","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"e35af61c23016d8c77f6d1abdcac9c9ac72234ad832e784a6353a7a2800fc7e0","published":"Thu, 18 Jun 2026 00:00:00 -0400","receipt_hash":"e35af61c23016d8c77f6d1abdcac9c9ac72234ad832e784a6353a7a2800fc7e0","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"e35af61c23016d8c77f6d1abdcac9c9ac72234ad832e784a6353a7a2800fc7e0","observed_at":"2026-06-18T04:43:37.219665Z","parent_run_hash":"de79a40f7b3537d88842f7ac355e799c5df2adcb4fc32a4e28096d4bbdf01739","published":"Thu, 18 Jun 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2606.19328v1 Announce Type: cross \nAbstract: 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 candidate trajectories according to a unified score that combines expected reward, terminal value, and epistemic uncertainty. Planning under this objective yields an explicit tradeoff between exploitation and information acquisition without requiring ad hoc exploration heuristics. Under standard regularity assumptions, we establish sublinear regr","title":"UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning","url":"https://arxiv.org/abs/2606.19328","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.19328v1 Announce Type: cross \nAbstract: 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 candidate trajectories according to a unified score that combines expected reward, terminal value, and epistemic uncertainty. Planning under this objective yields an explicit tradeoff between exploitation and information acquisition without requiring ad hoc exploration heuristics. Under standard regularity assumptions, we establish sublinear regr","title":"UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-18T04:43:37Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.19328"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:13e0e11efa053414d1f21ded6e73122d495058f63d54f91cf49747fbb36205285b2cca3d5616d2075953e0f538d466ced2830932e07b5945e9a36eaae4a60806","signer":"crovia.substrate","subject":{"observed_at":"2026-06-18T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.19328"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"2b0f4522f1c1949e25bd4ec79c7cffc995f25a5a600207191ad95081239303ec","leaf_index":233424,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"bd673fa3fb9a2bdfefc93ca8a87b97b05598cb177b4e75240bbb37724b5ca3b7","side":"right"},{"sibling":"dae7aa58ca53e53d830ea0cdbd1915d07622843a74c3f6d26c24e828139cf164","side":"right"},{"sibling":"cdf9008f185f850f84f151a4f06c8b6ac82e85164498e9f2bc2643175e4f735f","side":"right"},{"sibling":"977504b35f875dc030854dd2d77c8d2fda45509cf13a43bbce36227bb1165609","side":"right"},{"sibling":"e87d3586a31858fbf8b65081695b952d3a108457207fefae8bf8247f1d2a9f5e","side":"left"},{"sibling":"8c610da56e97c6514b09dd5f45c229dc3a880e5ee127aa6c1cb747aa9abcccc0","side":"right"},{"sibling":"8942c0022e58c4389bb72bd28400c56919b0d25c91e8d4c9f09dec03626b6f4b","side":"left"},{"sibling":"b4c26795680b2096400acbdc34159290b2a0589778819fc7e052c7a60bb5c873","side":"left"},{"sibling":"429c2a92a65e6eeaa2eda0a35fdb9e541472a1eace4c69a4d01a618a659a110f","side":"left"},{"sibling":"d97d1ebe04af6ea572f9d4334004d01026acffa3da5be2883c7566513c76e2c0","side":"left"},{"sibling":"571eb56e7ce00fe1f38d0ac4fc56828d01b2cfc1ab9089cde245c0656bee0514","side":"left"},{"sibling":"7ac50038a8ced3aeaf1194a2407a4a09346b0e4399da36ecde4390675a0c4bf1","side":"left"},{"sibling":"8c5e2b48dc31ef0edcd35c3db048235aa78cc48443aa2a8da3aa6e9b5524d2c4","side":"right"},{"sibling":"e616c34dbaf9456d5a6d3e2da82cde8621293c9f6d8a4cf9e441d7fd9cc81579","side":"right"},{"sibling":"94c0c932e61657f5e37fdba43f6ca9eddea8359425a7c1558dabe566911d5304","side":"right"},{"sibling":"a04392fb9f2a3a620840e3b3fecd93d12e6d224e481c162389d8ae64e7194599","side":"left"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":234491,"merkle_root":"02576a6980e38bab47864ae2c57b5a5ff21e554e9bdf8f64bdf28155ff1aabec","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260618T143732Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-18T18:33:39Z","sig_algorithm":"ed25519","signature":"b6c708778fc38b7789a2b91156cfe87252a7cd3a1d29121cba11a0c78f8cf104ca3019fc50a962fa5a216bcc4922fc8f3f69c04d1f8332c6dc0d931e1012e502","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_2b2626e1e6cb9788b47ab422cf1673d6a7b63558b44aa990458e7895fa1f30db"}}