{"_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_e9727e622a1f7b8e78ef2fc8fc36993ea9466048f814fe414206df46ac854654","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_e9727e622a1f7b8e78ef2fc8fc36993ea9466048f814fe414206df46ac854654","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"78db14d51c35b03c15a329e6259228025ffaca9fa53fcfe59054e73f509e015b","published":"Fri, 10 Jul 2026 00:00:00 -0400","receipt_hash":"78db14d51c35b03c15a329e6259228025ffaca9fa53fcfe59054e73f509e015b","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":"78db14d51c35b03c15a329e6259228025ffaca9fa53fcfe59054e73f509e015b","observed_at":"2026-07-10T04:43:53.465232Z","parent_run_hash":"06997be187ba20932a2030c56de194579eacf484085252a25bee544eab183e91","published":"Fri, 10 Jul 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:2607.08647v1 Announce Type: cross \nAbstract: As autonomous agents are increasingly deployed across diverse operational contexts, aligning their behavior with human intent demands reward functions that remain robust to such changes rather than overfitting to any single environment. Inverse reinforcement learning (IRL) provides a principled way to infer such objectives from human feedback. However, existing analyses of optimal teaching approaches for IRL focus on single-environment, demonstration-only settings, leaving underexplored how heterogeneous feedback modalities and environment dynamics jointly constrain reward functions that generalize across multiple environments. Because demonstrations in one MDP entangle reward information with that environments specific structure, the resulting rewards frequently fail to generalize when the agent is deployed in a new setting. We first analyze how different feedback modalities constrain rewards, showing that, in the unlimited-data regim","title":"Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning","url":"https://arxiv.org/abs/2607.08647","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.08647v1 Announce Type: cross \nAbstract: As autonomous agents are increasingly deployed across diverse operational contexts, aligning their behavior with human intent demands reward functions that remain robust to such changes rather than overfitting to any single environment. Inverse reinforcement learning (IRL) provides a principled way to infer such objectives from human feedback. However, existing analyses of optimal teaching approaches for IRL focus on single-environment, demonstration-only settings, leaving underexplored how heterogeneous feedback modalities and environment dynamics jointly constrain reward functions that generalize across multiple environments. Because demonstrations in one MDP entangle reward information with that environments specific structure, the resulting rewards frequently fail to generalize when the agent is deployed in a new setting. We first analyze how different feedback modalities constrain rewards, showing that, in the unlimited-data regim","title":"Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-10T04:43:53Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.08647"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:0f9b544d592ae8eca671087e81e2cc788ebf7627d65672464fe39273d9b6e30cc03b54d024a6c826d9f4a1412e861cb3174b4de0e61a499db86a08ced21cf901","signer":"crovia.substrate","subject":{"observed_at":"2026-07-10T04:43:53Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.08647"},"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":"b40033a0f335a560b23c5208c74a0cb6c84d5bef168bdb459bcb282b89aa87ec","leaf_index":299500,"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":"eb3b3102810be14e15e97c1a049373491d4eb3eb41a64aa16b06bcf959c79dc0","side":"right"},{"sibling":"5e0830a73aa9175552e4b3db3d7b552be470e311aa02f348d851faa9a3f5fa64","side":"right"},{"sibling":"9bd53a52417173722261374ea8148ce21dad8e53fa57f6766c33494b4a0b01a5","side":"left"},{"sibling":"dbe657c37bdb79e7c0a8985ea778a7202de87316f52db94908bda960eefec124","side":"left"},{"sibling":"65927017fdfd7ca0e9c71a80f1bf99a7c312875fbfd928572651f1ccb80904bf","side":"right"},{"sibling":"1e8021b095c74bdab85562264f566a914165bb59331cdb96722f48e8df9f939a","side":"left"},{"sibling":"7a96803ed93140d8d4c0e1fe53c891fc73447ccfce6e55b7c43e7a06979f307a","side":"left"},{"sibling":"b1b72243c904808d4df9b283c65832a729a411520c97fd9d17f891f214971a0a","side":"left"},{"sibling":"2c5ce75ad134aa442d7fbb5dc9968b0f2e48097c2ffaa2111d405de1c4a9c48b","side":"left"},{"sibling":"36a2c507282befad57202dd10278a66d37b402692f195a22d2275b3d1b2488d8","side":"right"},{"sibling":"f80e8d47e0860527b906fc2dba9a52609f7f623f2772479ae922cc019bab36d9","side":"right"},{"sibling":"cae83500ab2c25555aa6b5eaf9232696d15a868d91b34f7531dd955daadf70f7","side":"right"},{"sibling":"64dab64d51bdcb909e2a5e37efb8909d6704ecf824be484b5d2b60ee6e518890","side":"left"},{"sibling":"576f134a23c19a758ae5efd53016092a74b9900e878cf6eb4f3dab6be682b395","side":"right"},{"sibling":"3c65f53d7c3e4feba7c745e8df1327760ffa768eec84336db14d515a31731532","side":"right"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"8728642cdb98496d916cc653f0d919d7eb2e89d0c529927c9e89091074ad584c","side":"right"},{"sibling":"8025674cb002a22ae243ca0c295c18c1d0ee119189ea88e08ac14a3a1468b8e3","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","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":299721,"merkle_root":"f7115d63193d3285ca28cb9f741ecea2513f9b3e492e785f97076f3cf8f9bb98","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260710T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-10T05:38:19Z","sig_algorithm":"ed25519","signature":"4eeedeb744885bff6523d66b1cb86bde62b36917696367addfd980d90b31011daece2e01b20608e4c0870ec31dd0bcb57d297447f01f153bf0716ad527142b00","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_e9727e622a1f7b8e78ef2fc8fc36993ea9466048f814fe414206df46ac854654"}}