{"_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_1c31020b320354e0c9f4aeb310b0ffb9c5bf0358434519be5c19fccc29b2d33b","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_1c31020b320354e0c9f4aeb310b0ffb9c5bf0358434519be5c19fccc29b2d33b","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"e3ebe95addb36c9dcb5218a263b8b53a12472ce89ea3fa80783ed96212ee08a7","published":"Thu, 14 May 2026 00:00:00 -0400","receipt_hash":"e3ebe95addb36c9dcb5218a263b8b53a12472ce89ea3fa80783ed96212ee08a7","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":"e3ebe95addb36c9dcb5218a263b8b53a12472ce89ea3fa80783ed96212ee08a7","observed_at":"2026-05-14T04:43:36.462865Z","parent_run_hash":"eb105e641aec4518c665fb1a0f748c2a8c8189675990bd4092425661eb7af1d8","published":"Thu, 14 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:2512.13399v2 Announce Type: replace \nAbstract: Crafting effective reward signals remains a central challenge in Reinforcement Learning (RL), especially for complex reasoning tasks. Existing automated reward optimization methods typically rely on derivative-free search heuristics that treat the reward function as a black box, failing to exploit the causal dynamics between reward structure modifications and policy performance. We introduce Differentiable Evolutionary Reinforcement Learning (DERL), a bi-level framework for the autonomous discovery of optimal reward structures. DERL employs a Meta-Optimizer that evolves a reward function through the composition of structured atomic primitives to guide an inner-loop policy. Unlike prior black-box methods, DERL introduces differentiability into the meta-optimization process by updating the Meta-Optimizer using policy gradients derived from inner-loop validation performance. This allows for the progressive learning of a \"meta-gradient\" ","title":"Differentiable Evolutionary Reinforcement Learning","url":"https://arxiv.org/abs/2512.13399","vendor":"arxiv_cs_ai"},"summary":"arXiv:2512.13399v2 Announce Type: replace \nAbstract: Crafting effective reward signals remains a central challenge in Reinforcement Learning (RL), especially for complex reasoning tasks. Existing automated reward optimization methods typically rely on derivative-free search heuristics that treat the reward function as a black box, failing to exploit the causal dynamics between reward structure modifications and policy performance. We introduce Differentiable Evolutionary Reinforcement Learning (DERL), a bi-level framework for the autonomous discovery of optimal reward structures. DERL employs a Meta-Optimizer that evolves a reward function through the composition of structured atomic primitives to guide an inner-loop policy. Unlike prior black-box methods, DERL introduces differentiability into the meta-optimization process by updating the Meta-Optimizer using policy gradients derived from inner-loop validation performance. This allows for the progressive learning of a \"meta-gradient\" ","title":"Differentiable Evolutionary Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-14T04:43:36Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2512.13399"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:61ae70c3b61ac01b0345276de73dbda2d251293e3d8afbd1f258e78aceb99ffe506319e70e5d6f2a627dbacb1d3637f13fb764e9142ce26e81246475d7bec904","signer":"crovia.substrate","subject":{"observed_at":"2026-05-14T04:43:36Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2512.13399"},"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":"56840a555297794f5da796877b58576bce22878f672d0452550474bfaf8fb1e6","leaf_index":132690,"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":"e375fbd37d74435947e0a7fabcd6a56df2eab8cc0e6c9736dd026ba9e8cc7654","side":"right"},{"sibling":"80bda832cb74a96c208a5a84d1aea3936fc1e3cc358b1abe50aca41ca5c14e99","side":"left"},{"sibling":"ad6bc182af144e3aba1ce42b6c2732eb08b27a18488b585994dbe7fae6bdc7c7","side":"right"},{"sibling":"f99c3b9298c3682293c85026c6c4a37df2f7059844115e6d63f1b548f13ee9be","side":"right"},{"sibling":"e77870f2e4f89777b4ba81167c43d9eb805047f8cac81eac1d3c8cc2603aa317","side":"left"},{"sibling":"4e580670ad0e172af691752fc5b3e7647f7538b828f191b10b027add93132413","side":"right"},{"sibling":"73af79eefe7f2500d8fdddaeaf703a7c14107b1426b5c5b09ec0f985220d54f1","side":"left"},{"sibling":"d5482331e2cc5acdd0d08391a6a4507a80863b313a18e39660a4565d5c9fa7ea","side":"right"},{"sibling":"2ae8cbb1d93652ee36f693c3d63e733765fbafcd7765d6d596692bf393ce0a1d","side":"right"},{"sibling":"a957418f640d5dc3181a7628c2646bb86c6da0ea6888670b451e534693a0c7cb","side":"left"},{"sibling":"c03f0a468f574a08ffe8b17e1a17bd88216e1359f0e33a54447e160cd8675da0","side":"left"},{"sibling":"038ff12da6f55509125ef0d96e1e57dda29a2fe63bf03fba2af4cf7cbcd88b36","side":"right"},{"sibling":"b0419206fe62ef216df3900ca93cffd44df267435a4643dda354c1310079cf91","side":"right"},{"sibling":"0d4a9c03674f9d0ce64df15c15e9f656a54b41f93c428aac8e615fda26291956","side":"right"},{"sibling":"7856d920f3f1f1d2194c1ed7351bf0d674440df3cb423a6911f89cb3e9578c0b","side":"right"},{"sibling":"6ac6396bdd2e9df315427a46155531476e7f9012b4bd962e0d2d6d1209b11723","side":"right"},{"sibling":"7c8dc85cbfe43e19ac759ad176cfa11dba2467ae17927c471d5c55663c4f490d","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":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_1c31020b320354e0c9f4aeb310b0ffb9c5bf0358434519be5c19fccc29b2d33b"}}