{"_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_9741048c3dc7298f7f163db18f7f2245ff398b7e3847eec3b470638997b94bc5","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_9741048c3dc7298f7f163db18f7f2245ff398b7e3847eec3b470638997b94bc5","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"ad27dd201ca9a9ace59ee0614c3c7f8132e497307f4045436b103372ceba7d63","published":"Mon, 13 Jul 2026 00:00:00 -0400","receipt_hash":"ad27dd201ca9a9ace59ee0614c3c7f8132e497307f4045436b103372ceba7d63","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":"ad27dd201ca9a9ace59ee0614c3c7f8132e497307f4045436b103372ceba7d63","observed_at":"2026-07-13T04:43:08.394955Z","parent_run_hash":"900c1c934245e788564e199a9619f2dc36ec91d9804ddd9c6a40fb42c8a1e1c0","published":"Mon, 13 Jul 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:2506.01692v2 Announce Type: replace \nAbstract: Human preferences in RLHF are typically modeled as a function of the human's reward function or corresponding optimal state-action values. In this work, we propose that human beliefs about the capabilities of the agent being trained also play a key role in preference generation. We examine two questions related to this hypothesis, one descriptive and one normative, respectively: Do human labelers' beliefs about agent capabilities affect the preferences that they provide? And what is the ideal set of beliefs about an agent -- and resulting preferences -- for humans to have? We propose a new preference model that incorporates human beliefs and provide a normative theory that bounds the error on the final learned policy based on the mismatch between the human's beliefs and an idealized set of beliefs. We then confirm via a human study that beliefs about agent capabilities do, in fact, significantly affect preferences and can be influenc","title":"A Descriptive and Normative Theory of Human Beliefs in RLHF","url":"https://arxiv.org/abs/2506.01692","vendor":"arxiv_cs_ai"},"summary":"arXiv:2506.01692v2 Announce Type: replace \nAbstract: Human preferences in RLHF are typically modeled as a function of the human's reward function or corresponding optimal state-action values. In this work, we propose that human beliefs about the capabilities of the agent being trained also play a key role in preference generation. We examine two questions related to this hypothesis, one descriptive and one normative, respectively: Do human labelers' beliefs about agent capabilities affect the preferences that they provide? And what is the ideal set of beliefs about an agent -- and resulting preferences -- for humans to have? We propose a new preference model that incorporates human beliefs and provide a normative theory that bounds the error on the final learned policy based on the mismatch between the human's beliefs and an idealized set of beliefs. We then confirm via a human study that beliefs about agent capabilities do, in fact, significantly affect preferences and can be influenc","title":"A Descriptive and Normative Theory of Human Beliefs in RLHF","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-13T04:43:08Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2506.01692"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:e5f6d3cec50cd94209bd2540f31ab112901aa71c4674e141d6eeb49c0c112dcbb31b776e3cd140b97c08cd00321d1c159c817c78de528f99aaf7d9cd35aea401","signer":"crovia.substrate","subject":{"observed_at":"2026-07-13T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2506.01692"},"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":"4ee9378cfa91f51b46895a0dadb2c35ffd1ade41ba465f7d22831210d38ac139","leaf_index":309688,"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":"15170270e97fe88a400c238a4a56d192da6e5bc7733945d8824ec423ed39a01e","side":"right"},{"sibling":"55cd94c4c00acbee5a2f9f5e4f602767ed3dd116c70fe8567ed02c2a8c744f30","side":"right"},{"sibling":"6cbf14d0cbc676d0cdabb00fa44cac7584e567d8feb8b107aa013dd31e314fbd","side":"right"},{"sibling":"c5d30af88e4d4a63e84aa32232055f4a8f4069277beeb929e3d07ee76fc507ab","side":"left"},{"sibling":"ab1c0c6d9d8af83eb8492b80da0fc0eed82a2476d6ceb76af9aa30552af8e309","side":"left"},{"sibling":"817e14c6ab3a66a77efac57ff4cc63efe5efe647afce47f5aefa03dc77fc1f24","side":"left"},{"sibling":"a06f2db4ff89b8806c463205a6d957aa0950263fff991c2aa1386688c611457f","side":"right"},{"sibling":"49f7764de5dea797b32547b8437f6d371cde9fb33ac6cf784651dcfa196b149a","side":"left"},{"sibling":"6cbb0c4695e74fa8ec17dfde89fa56c1958a1d4dffbbcbe3556da4a69c699ebc","side":"left"},{"sibling":"c4bde3283be97905033d39c1097ac73b82f180de8830384fe6f9f1933f7fa4b9","side":"right"},{"sibling":"3b5f968ebea87e7be458ef7e63c6637988d27ba6d170e1f3794d385cd76ca23f","side":"right"},{"sibling":"5ed534e945b31085c140b50460415e7960b76a4b6266da67d272b853dc94b352","side":"left"},{"sibling":"91010b271bc8eb5253b3549292ef3146e1d85bc9bac7ca36e0862f1204f84e8d","side":"left"},{"sibling":"772fbc112e94d8e574379343387c65503d3cf8fb16ff89090174eccced871a41","side":"left"},{"sibling":"5d50450cae1a230f682b390c8e28ae822ec6c0c04a9bc79b0d27af97306ccccd","side":"right"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"e9ac4b1e71d3f572751b7984e9ca00893d71628137b4634e82df02cf3db9ab68","side":"right"},{"sibling":"99ff86058e045249bf936a629308be31e4cc71328f0282c4a924f4e6718be5f0","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","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":309862,"merkle_root":"f18a76abb66e7cb448986b6541091416ed4ebdde8124f5208a7c7c94bb4165d1","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260713T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-13T05:38:23Z","sig_algorithm":"ed25519","signature":"0488e3527b1d559ba55116220f91e2f6c22bb5358a135e8a9b94a65450b50511702044fa993555662ebca09f005b277f5f6ad0d044ec96a5568e9993c09ef007","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_9741048c3dc7298f7f163db18f7f2245ff398b7e3847eec3b470638997b94bc5"}}