{"_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_200a8cafa650767c41bbb1500f71ec9cf6e172b9b1812d7c86125d6a710816c4","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_200a8cafa650767c41bbb1500f71ec9cf6e172b9b1812d7c86125d6a710816c4","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"757e691ecee4a31b7e75bda841b69c65909c97a58473d7929b6e1ef24f9dbbec","published":"Tue, 02 Jun 2026 00:00:00 -0400","receipt_hash":"757e691ecee4a31b7e75bda841b69c65909c97a58473d7929b6e1ef24f9dbbec","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":"757e691ecee4a31b7e75bda841b69c65909c97a58473d7929b6e1ef24f9dbbec","observed_at":"2026-06-02T04:43:38.825628Z","parent_run_hash":"c2a9665c814770d56765bb764e6a6c7e4fa7d4e9708e157ca0f7440c89927d54","published":"Tue, 02 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:2506.13702v4 Announce Type: replace-cross \nAbstract: Single-trajectory preference optimization methods learn from datasets of ((prompt, response, reward)) tuples, offering a practical alternative to pairwise preference learning by directly leveraging scalar feedback. Existing approaches such as Direct Reward Optimization (DRO) have demonstrated promising results but rely on value function estimation, introducing additional variance, optimization complexity, and sensitivity to off-policy data. We introduce Reward Partition Optimization (RPO), a simple and scalable reward-driven objective that eliminates the need for value function learning. RPO normalizes rewards through a partition-based formulation estimated directly from prompt-level reward distributions, yielding a stable supervised optimization objective without auxiliary models or reinforcement learning loops. We evaluate RPO across multiple encoder-decoder and decoder-only language models using automatic metrics, LLM-as-a-j","title":"Value-Free Policy Optimization via Reward Partitioning","url":"https://arxiv.org/abs/2506.13702","vendor":"arxiv_cs_ai"},"summary":"arXiv:2506.13702v4 Announce Type: replace-cross \nAbstract: Single-trajectory preference optimization methods learn from datasets of ((prompt, response, reward)) tuples, offering a practical alternative to pairwise preference learning by directly leveraging scalar feedback. Existing approaches such as Direct Reward Optimization (DRO) have demonstrated promising results but rely on value function estimation, introducing additional variance, optimization complexity, and sensitivity to off-policy data. We introduce Reward Partition Optimization (RPO), a simple and scalable reward-driven objective that eliminates the need for value function learning. RPO normalizes rewards through a partition-based formulation estimated directly from prompt-level reward distributions, yielding a stable supervised optimization objective without auxiliary models or reinforcement learning loops. We evaluate RPO across multiple encoder-decoder and decoder-only language models using automatic metrics, LLM-as-a-j","title":"Value-Free Policy Optimization via Reward Partitioning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-02T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2506.13702"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:5b48735d7c4132f6c85d9cb9de730924b30d78d4858c75f7b516a33cc898351ee386a21e248bc96a94bac5c7f6202f9cbbe1278a1f12eda149fac4a3735e5b00","signer":"crovia.substrate","subject":{"observed_at":"2026-06-02T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2506.13702"},"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":"6e3264fced9d24d879efd7186c24ca195807e38ef3ffe93074c3437f79e684a2","leaf_index":205859,"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":"bc0173cd9041450bd6aa1a1dd688e37f51a244698721484ad2b2a6145dd00ced","side":"left"},{"sibling":"8bd46c107a928c691a098e3b3b3af463220292db60881eef6b3abce852f95c06","side":"left"},{"sibling":"0e71215a14d4a45c5148089380f933f77027f0f4acc969d93e78657e9a8d9dda","side":"right"},{"sibling":"18884630a27b75dad1f94a40c66bb14dadd20cece9750307bb94e0415ae7416f","side":"right"},{"sibling":"2e8ab506ec416eb20413e6783c7b86ce17c861c5306e40c42ddf6fc03afb6216","side":"right"},{"sibling":"4f16de82ab0db0ac5454af010b59885c3266df92e72c858a67542f343f45793c","side":"left"},{"sibling":"c67e085a85c0f23aa2cb50fd322074122571e52743812cc3860e76bbffd3a91b","side":"right"},{"sibling":"a5c0411da65d36a27f4e797deeace23f77314552708425e4e91c3ebf671bc23b","side":"right"},{"sibling":"6ac554ede1f78dc3a28ebe5e1155c2b9c258b71805fdd7ad2ec992697f3ccd0c","side":"right"},{"sibling":"5e1949edfad76bc6a73d008dc8be8a0c6fe4a7fb64c8beaf70e5023ca11d35e0","side":"right"},{"sibling":"e4bd1aaaf3f336d9b072b4d1fc234246fc3cf2874ca873b7741c03eaf97911f2","side":"left"},{"sibling":"e6adead8216db4cae92f0a036d53baebf30eed95a99c0d10758aa75bb7780f2f","side":"right"},{"sibling":"1acc2b7ff453ffd8c97b80ae4db5358780f0c6796874fd75403791dbe99f8cd7","side":"right"},{"sibling":"24d1bb4b13e0e46131b27b70a48e65fcf4e2e14b95e3bb83ade821e9df530f6b","side":"left"},{"sibling":"5f86f58c28b1a86ae06dfff4666bb9fba8866021a81fd4f1d200aa9af4722dfb","side":"right"},{"sibling":"f6cc6f94f6944ae21390afc65ac9e91dc31f84ee6e060681bba5ae08058294bd","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":206226,"merkle_root":"d2a6d32b13cbf343fb143b21a756d0533864ae6577a376ee84ba867b949207ec","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260602T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-02T05:37:46Z","sig_algorithm":"ed25519","signature":"abd9956cfb19dd1fb8142c46a220bac2514848c6abb0e79b8b0940206cc3ebb00894d4daaf9f786427f82a7cc12482e7fda79054ebb06bceaa9b4b97e23fb30e","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_200a8cafa650767c41bbb1500f71ec9cf6e172b9b1812d7c86125d6a710816c4"}}