{"_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_57d8b4d5f2de07ce2fda8dd7beeb88c8a4036bf4d4770a295fe6689547b9d655","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_57d8b4d5f2de07ce2fda8dd7beeb88c8a4036bf4d4770a295fe6689547b9d655","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"d50d1a2a4bc2633d7bb7912fff45f9b00b4f9f03e66312e04cd16543d01eb595","published":"Wed, 20 May 2026 00:00:00 -0400","receipt_hash":"d50d1a2a4bc2633d7bb7912fff45f9b00b4f9f03e66312e04cd16543d01eb595","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":"d50d1a2a4bc2633d7bb7912fff45f9b00b4f9f03e66312e04cd16543d01eb595","observed_at":"2026-05-20T04:43:44.562035Z","parent_run_hash":"5f904c2c2fecb6b44f2adce8bdc9de914b9a39f7c4fdd7bf086a6c2361a30f8c","published":"Wed, 20 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:2605.17003v2 Announce Type: replace-cross \nAbstract: Reinforcement Learning (RL) post-training has emerged as the dominant paradigm for eliciting mathematical reasoning in Large Language Models (LLMs), yet prevailing techniques such as GRPO and DAPO distribute rollout and gradient budgets nearly uniformly across prompts, squandering compute on samples that are already mastered or remain far beyond the model's current capability. To address this fundamental inefficiency, we propose Learning-Zone Energy (LZE), a theoretically grounded, fully online data selection framework that concentrates computation on the model's active learning frontier. At its core, we define a closed-form Learning-Zone Energy Score that fuses three complementary signals, an initial-difficulty anchor, a normalized outcome-uncertainty term, and a pass-rate momentum, into a single scalar that is provably aligned with the expected magnitude of group-relative policy gradient updates. A forward pruner with replay ","title":"Learning-Zone Energy: Online Data Selection for Efficient RL Post-Training","url":"https://arxiv.org/abs/2605.17003","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.17003v2 Announce Type: replace-cross \nAbstract: Reinforcement Learning (RL) post-training has emerged as the dominant paradigm for eliciting mathematical reasoning in Large Language Models (LLMs), yet prevailing techniques such as GRPO and DAPO distribute rollout and gradient budgets nearly uniformly across prompts, squandering compute on samples that are already mastered or remain far beyond the model's current capability. To address this fundamental inefficiency, we propose Learning-Zone Energy (LZE), a theoretically grounded, fully online data selection framework that concentrates computation on the model's active learning frontier. At its core, we define a closed-form Learning-Zone Energy Score that fuses three complementary signals, an initial-difficulty anchor, a normalized outcome-uncertainty term, and a pass-rate momentum, into a single scalar that is provably aligned with the expected magnitude of group-relative policy gradient updates. A forward pruner with replay ","title":"Learning-Zone Energy: Online Data Selection for Efficient RL Post-Training","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-20T04:43:44Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.17003"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:977236465a61c949d009d54fa6d9bdac80c23999a1d8484e2471a76305ee19ad827a93316c9262665bfec947f6d7409b2856739116c02dbc6d2cad89ae765b03","signer":"crovia.substrate","subject":{"observed_at":"2026-05-20T04:43:44Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.17003"},"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":"2d07848558274336a5caa460dfdc89dee20f270fbc15a47141b3dc73a84d9d29","leaf_index":145345,"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":"606839efe8afd7553abaab0f89abdd932eb61e134e82c98c602f3d86a92c19f2","side":"left"},{"sibling":"2a4a3bde0b9d80fb407a36641ee43f26892a78a8f713b4c62f2d8b9adb4576fb","side":"right"},{"sibling":"8717e9400e6037ada1e014bd8ec9e3eb5a3387d7ae67bd51d856c128c8297740","side":"right"},{"sibling":"99847565226f7e4652eed0a5cb8d5218f965c3aac4a1d7787f7f50bbe3a5d8cc","side":"right"},{"sibling":"1241ed9622cf8c3d0c4fd5e88336919d3ac9f5cf3503d4f5c9303cafcf977d7c","side":"right"},{"sibling":"6b406bad314535ee61e3fbddbbffacdca080be8798462ae83a9fd9406b0c2839","side":"right"},{"sibling":"1c41acf62b30d3c9dba07caadc151a1ad66701ff05acb0b48c20435560b78db4","side":"left"},{"sibling":"cc6b64c1eb047b460e9fe9beb452cf69fe3eb490dcf6d93d8193dda021cdf8ef","side":"left"},{"sibling":"f073aa7be27ee7e1d9eb0de5f129f7e9bae0c584fb959378c395b65831dc1d1d","side":"left"},{"sibling":"1526885f19d1fadf6955cf519dbc4e62d593a4bba99d741e8c301740a7068233","side":"left"},{"sibling":"e3a7d5c07f161682d61bd453ffc02ecdf87cfeda70f986d6650017f9d2d6b265","side":"left"},{"sibling":"edbc49f08e5b92291934c05c9e6efd270a6b0698d8d2fa474006366027dfe098","side":"right"},{"sibling":"3e4df6e7457cecbf36f350375e72dcab336a3984422e4c406ef809e4e2944e96","side":"left"},{"sibling":"8f4c0fbe56b6c010fbb8c782ebcd478079bb3f991d8704e2534209a075d9163c","side":"left"},{"sibling":"be08fedc4e72a6fb56606f66812fae7317e09690b9acb18385f4ab117a981238","side":"right"},{"sibling":"0534329a7475dc9df51998c83c16892126679dade0fa34182f21e869599386c7","side":"right"},{"sibling":"2d24720928ead0e7670650eb55f558c4f20e4c18df376f47ba72cfa8cf0ed344","side":"right"},{"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":147301,"merkle_root":"08903d7159c3b38eeeeafc09eab15139ea417f1d94f02f1fbc87296b37db840a","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260521T183701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-21T18:37:33Z","sig_algorithm":"ed25519","signature":"905f2924632dfa2970c8690285f5b5d4a1d891d0e0ef1cbc404ebec2fd937215ac768e16f0a9f28b18977a55ae0bfd226db6833ae7ef588729054117d2da7303","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_57d8b4d5f2de07ce2fda8dd7beeb88c8a4036bf4d4770a295fe6689547b9d655"}}