{"_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_ca72eb9509f70a649c6498430e1358c4cfb73f28dce5d34d80a1aaf673db3ce0","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_ca72eb9509f70a649c6498430e1358c4cfb73f28dce5d34d80a1aaf673db3ce0","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"c77988af1062088747322d726b56eb11eddee3ec8be68bc38f0b0e2219b78937","published":"Tue, 05 May 2026 00:00:00 -0400","receipt_hash":"c77988af1062088747322d726b56eb11eddee3ec8be68bc38f0b0e2219b78937","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":"c77988af1062088747322d726b56eb11eddee3ec8be68bc38f0b0e2219b78937","observed_at":"2026-05-05T04:43:28.458286Z","parent_run_hash":"84f40dd8e6af9caa9f2a7fd632024f0e0192177c4532d9af5caf61b409324d7a","published":"Tue, 05 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:2605.00667v1 Announce Type: cross \nAbstract: Safety is a primary challenge in real-world reinforcement learning (RL). Formulating safety requirements as state-wise constraints has become a prominent paradigm. Handling state-wise constraints with the Lagrangian method requires a distinct multiplier for every state, necessitating neural networks to approximate them as a multiplier network. However, applying standard dual gradient ascent to multiplier networks induces severe training oscillations. This is because the inherent instability of dual ascent is exacerbated by network generalization -- local overshoots and delayed updates propagate to adjacent states, further amplifying policy fluctuations. Existing stabilization techniques are designed for scalar multipliers, which are inadequate for state-dependent multiplier networks. To address this challenge, we propose an augmented Lagrangian multiplier network (ALaM) framework for stable learning of state-wise multipliers. ALaM cons","title":"Augmented Lagrangian Multiplier Network for State-wise Safety in Reinforcement Learning","url":"https://arxiv.org/abs/2605.00667","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.00667v1 Announce Type: cross \nAbstract: Safety is a primary challenge in real-world reinforcement learning (RL). Formulating safety requirements as state-wise constraints has become a prominent paradigm. Handling state-wise constraints with the Lagrangian method requires a distinct multiplier for every state, necessitating neural networks to approximate them as a multiplier network. However, applying standard dual gradient ascent to multiplier networks induces severe training oscillations. This is because the inherent instability of dual ascent is exacerbated by network generalization -- local overshoots and delayed updates propagate to adjacent states, further amplifying policy fluctuations. Existing stabilization techniques are designed for scalar multipliers, which are inadequate for state-dependent multiplier networks. To address this challenge, we propose an augmented Lagrangian multiplier network (ALaM) framework for stable learning of state-wise multipliers. ALaM cons","title":"Augmented Lagrangian Multiplier Network for State-wise Safety in Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-05T04:43:28Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.00667"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:5fe4e1f931b791b261788c576203b8c8960a5439060d4e87fb59823c253968145def0cd7ac63e635b901c277b8b5a6537976d7765892ab7fb6b3221b6d28150e","signer":"crovia.substrate","subject":{"observed_at":"2026-05-05T04:43:28Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.00667"},"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":"3ef4541a55a8c49497724f3d3ef493d6eff90c50a40ef2a677010c50a44d4dc2","leaf_index":114333,"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":"4fc9bdf947f75fd4da114e123ff8db135c0e8ec0d7ba491ce8af06e65a1e819f","side":"left"},{"sibling":"f32abebdc1b195701f469dcba55b30bde09cdd3cccdc00081e4d9404c1c45d58","side":"right"},{"sibling":"55163fc19ad83b529ceebc4ed7e05fc5a3bc436dc872a8dace43901dd4b27519","side":"left"},{"sibling":"2860df28868302177c34b0ba69e90286ec8cf60b4ac40b6397cddccf806cd5fb","side":"left"},{"sibling":"6b2091a994e0a69bd3afe4bba8a85024d6d3490428c5be459413de2fe6f0e18d","side":"left"},{"sibling":"6f9157b001fd7cf24893e921262c7f413e24fda3c05b1f0a50f6f0487e3c27f3","side":"right"},{"sibling":"8d93413b71ef416d945411f76ceb942da4715d54accb63f2761b83bb6b41ddef","side":"right"},{"sibling":"cbcf8d239488334c83b4e4700b65758e992d56d579302bc08e5c2df1fa69ea5a","side":"left"},{"sibling":"17e21f83c86c2a86dddad911d22393ee81f41d8e0b79ef8c0c48668ea846f2ca","side":"right"},{"sibling":"8df6c69f776fbba620634f6baf125eeaa6fdf9426e461e649028010d9a703f42","side":"left"},{"sibling":"ea40d1bd0432ad4dd90f023c692aaab8c8f54e27ce652e82f2ec8e16cacfb632","side":"left"},{"sibling":"673cd6d27b696232f7f65e7a0733c7df6bc9fac3bcb569907ebb0de1c72c4bb2","side":"left"},{"sibling":"76d7c4385d71ae8104107105be66eddb792e01ed6e493db5a9b4eec5441abb76","side":"left"},{"sibling":"b03f005860bf95148ea89c703a32ca19ab7a2ca71b58bb628ff94a9edb8703b0","side":"left"},{"sibling":"21d1e30b556f553dc939fddc23e6367f0a7755ebe3dd489dc0001cef017beb7f","side":"right"},{"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_ca72eb9509f70a649c6498430e1358c4cfb73f28dce5d34d80a1aaf673db3ce0"}}