{"_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_39fc0d4c6ce996a9fc1aa1e8fe8f16bfcb67a1e266610a80211cdacdb70ce131","bitcoin_anchor":{"bitcoin_attestations":["bitcoin_block_949451"],"calendar_attestations":["https://finney.calendar.eternitywall.com","https://btc.calendar.catallaxy.com","https://alice.btc.calendar.opentimestamps.org","https://bob.btc.calendar.opentimestamps.org"],"ots_url":"/registry/data/substrate/anchors/77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3.ots","stamped_at":"2026-05-15T03:00:03Z","status":"bitcoin"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_39fc0d4c6ce996a9fc1aa1e8fe8f16bfcb67a1e266610a80211cdacdb70ce131","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"44869a20b3172749d7036c633da93c17416d6ed0e19bf70285783e62bc828141","published":"Wed, 06 May 2026 00:00:00 -0400","receipt_hash":"44869a20b3172749d7036c633da93c17416d6ed0e19bf70285783e62bc828141","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":"44869a20b3172749d7036c633da93c17416d6ed0e19bf70285783e62bc828141","observed_at":"2026-05-06T04:43:18.518819Z","parent_run_hash":"184209fc0f2ebdc4b721e1a74f74ab17637dab3344682b6e6bd1f3e5e8f2cd00","published":"Wed, 06 May 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:2604.17654v3 Announce Type: replace \nAbstract: Exploration is a cornerstone of learning from experience: it enables agents to find solutions to complex problems, generalize to novel ones, and scale performance with test-time compute. In this paper, we present a framework for post-training language models (LMs) that explicitly encourages optimistic exploration and promotes a synergy between exploration and exploitation. The central idea is to train the LM to generate sets of responses that are collectively accurate under the reward function and exploratory in their reasoning strategies. We first develop a general recipe for optimizing LMs with set reinforcement learning (set RL) under arbitrary objective functions, showing how standard RL algorithms can be adapted to this setting through a modification to the advantage computation. We then propose Polychromic Exploratory Policy Optimization (Poly-EPO), which instantiates this framework with an objective that explicitly synergizes ","title":"Poly-EPO: Training Exploratory Reasoning Models","url":"https://arxiv.org/abs/2604.17654","vendor":"arxiv_cs_ai"},"summary":"arXiv:2604.17654v3 Announce Type: replace \nAbstract: Exploration is a cornerstone of learning from experience: it enables agents to find solutions to complex problems, generalize to novel ones, and scale performance with test-time compute. In this paper, we present a framework for post-training language models (LMs) that explicitly encourages optimistic exploration and promotes a synergy between exploration and exploitation. The central idea is to train the LM to generate sets of responses that are collectively accurate under the reward function and exploratory in their reasoning strategies. We first develop a general recipe for optimizing LMs with set reinforcement learning (set RL) under arbitrary objective functions, showing how standard RL algorithms can be adapted to this setting through a modification to the advantage computation. We then propose Polychromic Exploratory Policy Optimization (Poly-EPO), which instantiates this framework with an objective that explicitly synergizes ","title":"Poly-EPO: Training Exploratory Reasoning Models","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-06T04:43:18Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2604.17654"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:dafb759cc474c24cf49c6879c8d8f48b26548c57735c38049263fc60d2ec1d89d2b002461573ff2c065fbe239acb7641f9eeca66cc425cee68520a1d546d560a","signer":"crovia.substrate","subject":{"observed_at":"2026-05-06T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2604.17654"},"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":"fc87506401f46dc4910e0f4c98e510e2ba46df523c916aa83ee8b7a2ebbc8ca9","leaf_index":116444,"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":"63ada6c312cae1a8648e00ff76cac1810fdbcaef7742776c1e8a92dc63842eea","side":"right"},{"sibling":"3837b2d6ea8497a12e41e236c4baff9554bd542cda2a936d707b569d7d5258d4","side":"right"},{"sibling":"cae88b9130e7aedc785dd52fd199f32ed8883161b2628d4b01bea608668b0d58","side":"left"},{"sibling":"dbdfd3d9a5210c5105a373d3db0f76c0439db9592738eb1b6bc67e2e55fbe0e6","side":"left"},{"sibling":"445419ceee110a7b11b311cd7f73e2bc7b413d1898f20bd4af128d8ce5b363cf","side":"left"},{"sibling":"ef5fe04b64cf0fb50e71dc2d999ac13d32dff59697808d11301613ee8e663a00","side":"right"},{"sibling":"4cc9938ba74578c39e57576728cd5667cffc329ca7f59abc83c2dfe415d03818","side":"left"},{"sibling":"ae2d4d1f9926c807a390f0c20c0a0e8fc89204c3e1f66866d3ea0fda3757402d","side":"left"},{"sibling":"7a43f13f6340a269b939be4b6e73a199a4e8061f0cf9dbb9ba629243174142d3","side":"right"},{"sibling":"c750384c973eaf46aa237cdabe7a75729862dd4101dca10cb8e0626e0ec2d34a","side":"left"},{"sibling":"ddc060ac400459417799f688c75d5b271636afa40d89ec7fc98652473a8061f6","side":"left"},{"sibling":"282afa51266e47629e34d808a360bbb276348bcc5a24bdcc93e83a76e580293e","side":"right"},{"sibling":"05f89b32c00462e60adf95c1fe4579cdc2791b36e8b17573d8f3b5fd5da95a0b","side":"right"},{"sibling":"8ccd9937a2c0d5c04044d07d1557791b7d07bb31eac41a39a675608d44b38f23","side":"right"},{"sibling":"3a5e69cf0803f4c91f3895ed7c9a95748fef240bec4422e167c05300f79f06c0","side":"left"},{"sibling":"f2817ab288b5324fe49770372c7a10f33f7cd11005f8d4c0a730316f5229dc98","side":"left"},{"sibling":"725fac972e772ca0dc598810ea1abc70df472f72d2d6ab8a0baee2b80e5d2f4c","side":"left"},{"sibling":"98fc57dfef8873b512edc8340f7181df57302bb96777625e072235c62d7c5895","side":"right"}]},"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":134292,"merkle_root":"77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260515T023701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-15T02:37:25Z","sig_algorithm":"ed25519","signature":"68107a834b00b24f5d4501e5ec727445311f132a486567ecc4c72a4e6dff24c8c21f2de3105293353ba5fdbe370d032819af6aa70f694e2e39b6af6737507009","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_39fc0d4c6ce996a9fc1aa1e8fe8f16bfcb67a1e266610a80211cdacdb70ce131"}}