{"_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_e26afe7d585e9c2a6b9dd1a95fb67802a3443aef7858846b42c8f952ee58e3a5","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_e26afe7d585e9c2a6b9dd1a95fb67802a3443aef7858846b42c8f952ee58e3a5","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"9d1d47086a0df5fcaf61337dcdf267d6cd742486f16b7f90a3f44b6fab9ac45f","published":"Wed, 03 Jun 2026 00:00:00 -0400","receipt_hash":"9d1d47086a0df5fcaf61337dcdf267d6cd742486f16b7f90a3f44b6fab9ac45f","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":"9d1d47086a0df5fcaf61337dcdf267d6cd742486f16b7f90a3f44b6fab9ac45f","observed_at":"2026-06-03T04:43:57.136784Z","parent_run_hash":"62ae9c8eda846b00bc49666345b338d00756c5203438666c4c1fc694cc364b84","published":"Wed, 03 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:2606.03962v1 Announce Type: cross \nAbstract: Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward. Yet, modern applications such as language model fine-tuning or scientific discovery demand diversity. Existing remedies such as entropy regularization or diversity bonuses often require fragile trade-offs that sacrifice performance for stochasticity or rely on heuristic metrics that can misalign policy rankings. We argue that diversity is more naturally understood as the rational response to uncertainty in the reward. When the reward function is not perfectly known--as is the case with ambiguous preferences or imperfect reward models--committing to a single action can be sub-optimal. Building on this, we propose a fundamental reformulation of the RL objective by replacing the scalar reward with a distribution over reward functions, and applying a non-linear objective over sets of actions. The result is a fram","title":"Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning","url":"https://arxiv.org/abs/2606.03962","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.03962v1 Announce Type: cross \nAbstract: Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward. Yet, modern applications such as language model fine-tuning or scientific discovery demand diversity. Existing remedies such as entropy regularization or diversity bonuses often require fragile trade-offs that sacrifice performance for stochasticity or rely on heuristic metrics that can misalign policy rankings. We argue that diversity is more naturally understood as the rational response to uncertainty in the reward. When the reward function is not perfectly known--as is the case with ambiguous preferences or imperfect reward models--committing to a single action can be sub-optimal. Building on this, we propose a fundamental reformulation of the RL objective by replacing the scalar reward with a distribution over reward functions, and applying a non-linear objective over sets of actions. The result is a fram","title":"Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-03T04:43:57Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.03962"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:32c3c5c5a5253ff360fb380c207d326ce9f87a7a664ed07e8b5affe85687bf065897c2490f86c3023ac8a19af141358c3fc51d946cba15f7d8f1b26a0fb0dc06","signer":"crovia.substrate","subject":{"observed_at":"2026-06-03T04:43:57Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.03962"},"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":"95db3ca3fb3c2df91c6ff63b0db04daa7d2ebb5c7abf28e96b780fee720a69bf","leaf_index":209284,"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":"3ed0b1dee67c410c468bc2178df5ae18a3e4eb236ae763c39cc6fa2d0e7cbd65","side":"right"},{"sibling":"cc9ccf39c6efe6b47791966dd44ec07d278063a458e0df71e8eec276efe126f9","side":"right"},{"sibling":"842d1701941b94bcb6d8f0a2d6e0e4b795a81cb1dd78de8ac43ebef9a215266f","side":"left"},{"sibling":"5abee4130b32d161f50272e702bc170d30450a3c149d1da8b3f89e9626df89dc","side":"right"},{"sibling":"aaace006d6e5cea564ef313cb3055aefc3b9efd7e0ff19bdff31f493263d73c5","side":"right"},{"sibling":"af50a6738c0a0cbbb5706152f1a54334201f0cef59b76290ea936626445333cc","side":"right"},{"sibling":"4a9041cff48b223827c44d2d56d150c595450d4a6390b4eb331519bc36b634f1","side":"right"},{"sibling":"768ffa75e0a020ca1e4038beeef0da5c26e64a7ba3a0528188d49b4d35664067","side":"left"},{"sibling":"2b9867040ec52d22722edc26b204e15651723dcc66d361cc1af11490a854d461","side":"left"},{"sibling":"2abcec6d14b256f82b270a3141886de6129141dec525543607b760f02588a877","side":"right"},{"sibling":"2b6b45743f97ac502854e489ac38a3366f8ae7ede58a2728b45daadbf29e9d03","side":"right"},{"sibling":"a81babbd79ea0da9e030dd7f43bffb6519d214317decd50727bea4e78189d970","side":"right"},{"sibling":"2dca509b3eb767a47cf215d4315f230ce9103a76264412008ae23a349b519ef1","side":"left"},{"sibling":"24d1bb4b13e0e46131b27b70a48e65fcf4e2e14b95e3bb83ade821e9df530f6b","side":"left"},{"sibling":"8d3baa674a45fd8bc6d3e8d25298f4bec86c72fa8259d576c330d12955c7b4f7","side":"right"},{"sibling":"e32819d1eff909db08066d1703f2db3f091cddac19378b2c0c625ab11e3fdbc0","side":"right"},{"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":209569,"merkle_root":"c852efc8ad7dfffc196c71380f79e6398bcaf566974cbae7c9950b0f600d5bc8","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260603T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-03T05:37:57Z","sig_algorithm":"ed25519","signature":"1ca417607effc813341721cfdade0a2d2d4ba96a90d361dbc3e864b6991b90abc326ec41d9ba3e7110cc04adb29d7b8d95abea7ff2ab8c591b2f864ed7270c03","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_e26afe7d585e9c2a6b9dd1a95fb67802a3443aef7858846b42c8f952ee58e3a5"}}