{"_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_be9cbda85f22e7aa0601ce4780f986a7c7e6569f6e533c242191d643080a1c29","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_be9cbda85f22e7aa0601ce4780f986a7c7e6569f6e533c242191d643080a1c29","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"698b053fc64b122b79761f7a28836c39bbb2c36961ece1c80377fb1e913dd4b7","published":"Tue, 09 Jun 2026 00:00:00 -0400","receipt_hash":"698b053fc64b122b79761f7a28836c39bbb2c36961ece1c80377fb1e913dd4b7","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":"698b053fc64b122b79761f7a28836c39bbb2c36961ece1c80377fb1e913dd4b7","observed_at":"2026-06-09T04:43:45.619596Z","parent_run_hash":"f2344865fd128464efd1bacba326b5a7ccea707694b8c5650dd51ae8c46ac8a1","published":"Tue, 09 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:2603.25184v2 Announce Type: replace-cross \nAbstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance performance, the computational overhead is a critical issue. In algorithms like GRPO, multiple rollouts per prompt incur prohibitive costs, as a large portion of prompts provide negligible gradients and are thus of low utility. To address this problem, we investigate how to select high-utility prompts before the rollout phase. Our experimental analysis reveals that sample utility is non-uniform and evolving: the strongest learning signals concentrate at the ``learning edge\", the intersection of intermediate difficulty and high uncertainty, which shifts as training proceeds. Motivated by this, we propose HIVE (History-Informed and online-VErified prompt selection), a dual-stage framework for data-efficient RL. HIVE utilizes historical reward trajectories for","title":"Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model","url":"https://arxiv.org/abs/2603.25184","vendor":"arxiv_cs_ai"},"summary":"arXiv:2603.25184v2 Announce Type: replace-cross \nAbstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance performance, the computational overhead is a critical issue. In algorithms like GRPO, multiple rollouts per prompt incur prohibitive costs, as a large portion of prompts provide negligible gradients and are thus of low utility. To address this problem, we investigate how to select high-utility prompts before the rollout phase. Our experimental analysis reveals that sample utility is non-uniform and evolving: the strongest learning signals concentrate at the ``learning edge\", the intersection of intermediate difficulty and high uncertainty, which shifts as training proceeds. Motivated by this, we propose HIVE (History-Informed and online-VErified prompt selection), a dual-stage framework for data-efficient RL. HIVE utilizes historical reward trajectories for","title":"Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-09T04:43:45Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2603.25184"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:e990a6a1295d4ff4fd18e4c078ff9b1e382c044f2007a04b2776336345243b39eae57994b203d644aad1e27a8d575d4d2157f4c43392704c8f8539bb96a2f90a","signer":"crovia.substrate","subject":{"observed_at":"2026-06-09T04:43:45Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2603.25184"},"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":"da8bc399013658f9f9044c3fbfdce250cbed42bc620533c0161674e30d3879f1","leaf_index":224620,"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":"c345ef5fdbff53e6d33f6bbe66a819b522f10b3aa2b6caba6381fb96cecf260b","side":"right"},{"sibling":"a086c2385e4c15774d89990c65630f283634ef13db42e3e56cca699927207d3c","side":"right"},{"sibling":"2c8976625a4c891d812bd12eab5ac50b4877b5df43db00c6118a4bc4d5beaf59","side":"left"},{"sibling":"f62e9d72ef0d84010c9fc11d8ab1cfdbdc8be7bd348a0deee89b03aa0017e952","side":"left"},{"sibling":"6bf1d76bd620489e014232812ba76209e8f31b4c971b4b781908190e37c87de4","side":"right"},{"sibling":"e4da1336c1206aae0c29063e4f69bc492101171727b20d2c68db4ae0b3921fbf","side":"left"},{"sibling":"c0fff0778a9884738bd7bb2c3b5f103904b36267458ec4bcbe17e0a1abdae603","side":"left"},{"sibling":"ce39e453038de7aa49f7571634d02890601b8ad6700079b4c6e4dc3e1d2e8b38","side":"right"},{"sibling":"f54580a307d4bb82e453931aa73e9a0c590486cb8df06af79ad4674f1c4f6963","side":"left"},{"sibling":"b2df6a4bb3e928f0b447931cc688ae01d2415773a2b07cfed0b1cba689078aed","side":"right"},{"sibling":"b1c9ec856caa0fd46bb47b46f18c59ebcd295d774ca17adb3b46f05d394a6a5d","side":"left"},{"sibling":"24fdc29d461691aedb6fa920758206b5bb43851f477ef7a04c34aaed84b8971b","side":"left"},{"sibling":"036922da4e1e2c46d948f070454bfad299b7406fb00735ea9d8bd1e687f5f445","side":"right"},{"sibling":"533d82482604463aa4a281b9d8b85917b383b7c5f924b2b494039524c55e8797","side":"left"},{"sibling":"b2590791b920ca2a4ed39de126d2c0b1a10d9e7e62f572f12425f214e767b6e1","side":"left"},{"sibling":"87c6b850dfec08ac35a693d9db3a3315250a68adb1cfab9b1015f212b63b15bd","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":224761,"merkle_root":"e9f7b49b652e869ab97ffba9c5a31356b2d0e3dc5d00bb28944adf737c46b1e7","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260609T103805Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-09T14:15:34Z","sig_algorithm":"ed25519","signature":"8ad8076fb12c8e486ae1d1559a9a7ba8e2ee996a9ad3d8ba7bcdbdbd88ab3a15bcb429707aca6d3e9d8b97e2ba755b3dcc77b1abb6601ccb829842719a6fb30d","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_be9cbda85f22e7aa0601ce4780f986a7c7e6569f6e533c242191d643080a1c29"}}