{"_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_e1144b521b96756f58a4913e4a10b7df40b2aa44bbb046bd8411ccf0633113e0","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_e1144b521b96756f58a4913e4a10b7df40b2aa44bbb046bd8411ccf0633113e0","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"7da5d427e67211cee3c5448d30d819384aeb3bb05545e53da38f8d1307a87060","published":"Thu, 11 Jun 2026 00:00:00 -0400","receipt_hash":"7da5d427e67211cee3c5448d30d819384aeb3bb05545e53da38f8d1307a87060","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":"7da5d427e67211cee3c5448d30d819384aeb3bb05545e53da38f8d1307a87060","observed_at":"2026-06-11T04:43:37.662146Z","parent_run_hash":"5267801b61ae0d882196b5f37208a9a1633905a64ca7d933f1fa5075cd861491","published":"Thu, 11 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:2605.12655v3 Announce Type: replace \nAbstract: Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing behavior and conflict with long-horizon objectives. However, conditioning rewards on instructions introduces a fundamental failure mode as Bellman updates couple value estimates across instruction contexts, leading to inconsistent values when instructions interrupt macro-actions. We propose Macro-Action Value Correction for Instruction Compliance (MAVIC), which corrects Bellman backups at instruction boundaries by correcting the incoming instruction objective and restoring the continuation value under the current objective. Unlike reward shaping, MAVIC modifies the bootstrapping target itself, enabling consistent value estimation under stochastic instruction switching within a unified policy. We provide theoretical analysis and an actor-critic implementation, and show that MAVIC achieves","title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","url":"https://arxiv.org/abs/2605.12655","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.12655v3 Announce Type: replace \nAbstract: Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing behavior and conflict with long-horizon objectives. However, conditioning rewards on instructions introduces a fundamental failure mode as Bellman updates couple value estimates across instruction contexts, leading to inconsistent values when instructions interrupt macro-actions. We propose Macro-Action Value Correction for Instruction Compliance (MAVIC), which corrects Bellman backups at instruction boundaries by correcting the incoming instruction objective and restoring the continuation value under the current objective. Unlike reward shaping, MAVIC modifies the bootstrapping target itself, enabling consistent value estimation under stochastic instruction switching within a unified policy. We provide theoretical analysis and an actor-critic implementation, and show that MAVIC achieves","title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-11T04:43:37Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.12655"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:89c1b158f29ab0b4b55510d45bd039b8b2da0a0fe6a94fb7aa69a18899e0dd2b30436cb5c14e7ecad16ce6f14d88bb4db3948bc581bb38f44cf43008d4f15a0d","signer":"crovia.substrate","subject":{"observed_at":"2026-06-11T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.12655"},"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":"d2693d045ed89b3c11d7f5ca54167f42fe60e1fb4ec027aad33a42bec3e6fe8c","leaf_index":227551,"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":"a26d72bceda7eb4470421e46c1f1f0d275bde65d592736b3dc5ef52feec65f5d","side":"left"},{"sibling":"0518f252475acc8a2fe2afd395dabf9e3d76d4b94660ad7895eaa6aaacfa28eb","side":"left"},{"sibling":"12a2c3f2f281690ca6e981571ae23f054a2d336c52ab7bbaf8d250cd11dc3c36","side":"left"},{"sibling":"ce7d731a1630c7fa6e5b3c7adf186942a6de0e95c545ada48a9db3b11d828e2e","side":"left"},{"sibling":"49d0d14004752e761f184c0f4df31acdb7b940626c5339b3ffa9bfff699514a7","side":"left"},{"sibling":"2ccad6b71a390eec8f0c3aa9a6685c58ef5928ecac69b5ffff5c4562bf27f422","side":"right"},{"sibling":"c44e4b51d9c7765cca497a557e7b31c0d9d97f529aac756c8c77f7f583bb3eeb","side":"left"},{"sibling":"e5516844190de8c773a2f33a88fdd935790a83aa93beef323f043368177406bc","side":"left"},{"sibling":"2cfac7f042209c8533c6031bddc4a83bc156e0595f1b28efefbda208904f338a","side":"right"},{"sibling":"04e399458c5b36988cae0bf1c6dbe1b01349003b15cb5aa43f95c55acffe4ec3","side":"right"},{"sibling":"1383228337d54218bd8e5563aebb0b0dfe15c5269e3d5138e64c261d6130a88b","side":"right"},{"sibling":"57cb49c192550231071a0bf53a0821da2f79c585ec6c8d0fc76cebd62ccd78b2","side":"left"},{"sibling":"cdb58f86163046d3b15f857b03372ec75e1ad9ea4548e086793d528b9eed364d","side":"left"},{"sibling":"533d82482604463aa4a281b9d8b85917b383b7c5f924b2b494039524c55e8797","side":"left"},{"sibling":"b2590791b920ca2a4ed39de126d2c0b1a10d9e7e62f572f12425f214e767b6e1","side":"left"},{"sibling":"6cea4964f32722eb370847c2f7c9d6a9f0622c239538b07e6815a59d6fd8d49c","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":228173,"merkle_root":"7e416202c0bfd759bd2eea4236713b403993d99793fe8badb5065040080bece3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260611T143708Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-11T21:59:35Z","sig_algorithm":"ed25519","signature":"231c80024bc3982dd493c45b31af95097e97aabc6d712a4e5bad7d0cbdd3c08e01ff395b0f8e72754bac97016e0cd0eed88b8a13cb71edbbcb9b6d72c10a7b03","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_e1144b521b96756f58a4913e4a10b7df40b2aa44bbb046bd8411ccf0633113e0"}}