{"_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_93b9bdcc804488cf874e2d0addaa2222894ec11f5e972de0a51935f281dedd1a","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_93b9bdcc804488cf874e2d0addaa2222894ec11f5e972de0a51935f281dedd1a","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"4ce57accfeb3ff47b0b465b7ac23096175727b0539792b00c27e22573f5f17e2","published":"Wed, 27 May 2026 00:00:00 -0400","receipt_hash":"4ce57accfeb3ff47b0b465b7ac23096175727b0539792b00c27e22573f5f17e2","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":"4ce57accfeb3ff47b0b465b7ac23096175727b0539792b00c27e22573f5f17e2","observed_at":"2026-05-27T04:43:18.926230Z","parent_run_hash":"6f581915edab4326e2b95fed7c82c2ee149e978d6d7c2443439442a927c31dfa","published":"Wed, 27 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:2605.26286v1 Announce Type: cross \nAbstract: Real-world multi-agent reinforcement learning (MARL) systems must often operate under stale observations, stochastic communication delays, and intermittent packet loss. Policies trained under idealized synchronous conditions frequently exhibit significant performance degradation in these regimes because they act on outdated feedback. We propose a modular execution-stage state-estimation layer that replaces delayed communicated observations with current belief-state estimates. The framework integrates a learned Gated transition model with a recursive Kalman filtering layer to estimate instantaneous states from asynchronous measurements. A primary advantage of this approach is its modularity, The estimator serves as a plug-in for pre-trained policies, requiring no modifications to the original MARL training algorithm, architecture, or reward structure. Evaluation across diverse multi-agent and continuous-control benchmarks demonstrates t","title":"Decoupled Delay Compensation: Enhancing Pre-trained MARL Policies via Learned Dynamics Filtering","url":"https://arxiv.org/abs/2605.26286","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.26286v1 Announce Type: cross \nAbstract: Real-world multi-agent reinforcement learning (MARL) systems must often operate under stale observations, stochastic communication delays, and intermittent packet loss. Policies trained under idealized synchronous conditions frequently exhibit significant performance degradation in these regimes because they act on outdated feedback. We propose a modular execution-stage state-estimation layer that replaces delayed communicated observations with current belief-state estimates. The framework integrates a learned Gated transition model with a recursive Kalman filtering layer to estimate instantaneous states from asynchronous measurements. A primary advantage of this approach is its modularity, The estimator serves as a plug-in for pre-trained policies, requiring no modifications to the original MARL training algorithm, architecture, or reward structure. Evaluation across diverse multi-agent and continuous-control benchmarks demonstrates t","title":"Decoupled Delay Compensation: Enhancing Pre-trained MARL Policies via Learned Dynamics Filtering","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-27T04:43:18Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.26286"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:a1edf5ed912a339a49ee4a0024a9b0329f9533741be2c3d3e939ce59ed1b51e11058e371e0bcd7bebe5c3a63f19a0ce9db11cbbee039dee8093b6315e4c6e802","signer":"crovia.substrate","subject":{"observed_at":"2026-05-27T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.26286"},"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":"e195e51f5da087ae8cddfed15eb2831331adbe07906fc036b31816157735cfca","leaf_index":153659,"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":"d4da2c2d2c2bb35406681fe1f8cd04c65da1039f968f7ea3dc5aa1720017e197","side":"left"},{"sibling":"ad4b2fa5263e70cec849927d3c24bf94a8a9002a973b236c0c5be11bdc90c458","side":"left"},{"sibling":"9330d12a03d769f771f9bf0736766e4f5c1baf7325d283842b8314a23f09d084","side":"right"},{"sibling":"020ee39985f66e24be735e66e445476548f26a9049f30dbed9d3b27f348e0383","side":"left"},{"sibling":"43da306d445b109a21457c2f146327b66865a7ee35bab0ff38bce7a1df965410","side":"left"},{"sibling":"99164640ca01b6e99a61eafa08e989a9c1354aed40726311d98ae399dce42875","side":"left"},{"sibling":"20fef87d78d7a367f04b7046503b17acf0a805917fa54a478472e2f7833e4d1b","side":"right"},{"sibling":"e6fcc8fd02ff764f6e74465d070f84e313e858647d901e3ee00b83931106f26c","side":"right"},{"sibling":"c56e46802f42ead6bcf79619c80428b6dc22e9afc9611a87f0d04a5ef9acadd7","side":"right"},{"sibling":"3165125427a29042fc9d02858a59a68858dbdcb2e19d1afa5f6dd6a95cfbce6a","side":"right"},{"sibling":"04b9a68b8ec6fa37251564383c685c23ce69e5e031df4eae69f79a3a334b68bf","side":"right"},{"sibling":"816f233274bb10f5a122aac086a0c8c697b78fec67a4af55190bb596b7506fab","side":"left"},{"sibling":"d415e6939aee710631f5062799379b547d2c3e3d9a68f263bbb5a693285ab2ca","side":"left"},{"sibling":"374c02d15fb12bd356c179c94766043a982052c6132af8bfc15361b431ffa9f7","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"990705096edf483cc877217308f731dc42d6f6d99f82880167bbdbbfef32560a","side":"right"},{"sibling":"dd265753d95fa2e2fb4f5768e37fab6f691ccff09ad60d0910ff7dc23bac9226","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":154065,"merkle_root":"4993cfdc172e7880b60667f16789dc2e831ff000f81bb1ecba248e73f1510eca","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260527T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-27T05:37:36Z","sig_algorithm":"ed25519","signature":"76ecf118011540405e96506e6219752df04a2850632f2903dc6f10e08b98bc5a42c8d9e1cb5b7c5bf714479806a403df5f34399afa40c23fbb71493a1f77bd0c","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_93b9bdcc804488cf874e2d0addaa2222894ec11f5e972de0a51935f281dedd1a"}}