{"_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_34cc6a2e1220415d7f24197f9c27c87a3f6759455d65be222341cd97c3415489","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_34cc6a2e1220415d7f24197f9c27c87a3f6759455d65be222341cd97c3415489","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"71b41e0a8d7fef28d45609dc18c399bd80bb79e72898d7141873798b45c1cc91","published":"Fri, 19 Jun 2026 00:00:00 -0400","receipt_hash":"71b41e0a8d7fef28d45609dc18c399bd80bb79e72898d7141873798b45c1cc91","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":"71b41e0a8d7fef28d45609dc18c399bd80bb79e72898d7141873798b45c1cc91","observed_at":"2026-06-19T04:43:39.497162Z","parent_run_hash":"942f204649bd8fb7e5f3ac68f64dc64a5a02624b49ac200c0f629f6ff3a211f3","published":"Fri, 19 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:2602.22495v3 Announce Type: replace-cross \nAbstract: Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most existing knowledge distillation (KD) methods are designed for supervised fine-tuning (SFT), relying on fixed teacher traces or teacher-student Kullback-Leibler (KL) divergence-based regularization. When combined with RL, these approaches often suffer from distribution mismatch and objective interference: teacher supervision may not align with the student's evolving rollout distribution, and the KL regularizer can compete with reward maximization and require careful loss balancing. To address these issues, we propose RL-aware distillation (RLAD), which performs selective imitation during RL -- guiding the student toward the teacher only when it improves the current policy update. Our core component, ","title":"Reinforcement-aware Knowledge Distillation for LLM Reasoning","url":"https://arxiv.org/abs/2602.22495","vendor":"arxiv_cs_ai"},"summary":"arXiv:2602.22495v3 Announce Type: replace-cross \nAbstract: Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most existing knowledge distillation (KD) methods are designed for supervised fine-tuning (SFT), relying on fixed teacher traces or teacher-student Kullback-Leibler (KL) divergence-based regularization. When combined with RL, these approaches often suffer from distribution mismatch and objective interference: teacher supervision may not align with the student's evolving rollout distribution, and the KL regularizer can compete with reward maximization and require careful loss balancing. To address these issues, we propose RL-aware distillation (RLAD), which performs selective imitation during RL -- guiding the student toward the teacher only when it improves the current policy update. Our core component, ","title":"Reinforcement-aware Knowledge Distillation for LLM Reasoning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-19T04:43:39Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2602.22495"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:60e4eaf6c61fe8edfd2f5f0b888f1e33cbed5672fa4eb70a13353731b4b3b42952f21978f094504c0400f62a11f956548016f02f6bc15c506048bc696656d700","signer":"crovia.substrate","subject":{"observed_at":"2026-06-19T04:43:39Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2602.22495"},"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":"8282faede2e21a5e3f061b8f97771db22d2dfc637be7a6010ae686cbd4f1dcb5","leaf_index":235734,"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":"d0798a89585b389d53a055f9b57897899928f7b26ba80f7bfc51f15e9178bb2a","side":"right"},{"sibling":"a4fa428e4364ed881e5f64a6ad61374cd7553331e12918e8281a1383cdeddab9","side":"left"},{"sibling":"01657422d2ae9e029c6639baf9a2b492e0c4e15356bae198ee59e447bd8ade1c","side":"left"},{"sibling":"818ee66de2c0d04357cb58f55fd5f832983c697704e5e3135ee88cc4b1f75d81","side":"right"},{"sibling":"d3804b0fab1731eeb30a2eee878bec7ce7ba8ce7702faec751d3e2bf1331464d","side":"left"},{"sibling":"39f412afa28766221bce1f35a009b6692e5c927315ca493d86f4954d9ac09857","side":"right"},{"sibling":"cff664a6462d639aed9e14805d8bb57d59dd159a92997aa1da18b50dd5d6c34f","side":"left"},{"sibling":"9af7ea2b04101a414ff44ef903d5d381777f0286b489347e7e959b64158ff697","side":"left"},{"sibling":"aa68ebe8f5e8e96388fc8d1af3aa08be7ccd27ab4cebcf5913560c48d877bc27","side":"right"},{"sibling":"8253d44cf1ed30d3ab19c2b339fb4000a1fa173182c65390e9e8dabf8173b9e9","side":"right"},{"sibling":"e2bf9b60400244c698c0196109f54323457abc5b64dee08ec33ab14cc4faaef7","side":"right"},{"sibling":"86664e7f68ba08b8dfcf77dda51a4dfa7fcfc986d4ad7c704ffb71b669202da7","side":"left"},{"sibling":"410c633928fea11c5b4bdddb431956b1d7c320db9cda00d2fe32e0fcf888d7b7","side":"left"},{"sibling":"b52a771530dd1686bca49e42088898b86da94879579cd6a995c6ab0598a665fe","side":"right"},{"sibling":"a116bb92f9b0350491155b470acc86d006c33ec558759e49e56614a54c39f242","side":"right"},{"sibling":"a04392fb9f2a3a620840e3b3fecd93d12e6d224e481c162389d8ae64e7194599","side":"left"},{"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":241122,"merkle_root":"7a906c6a26ff6c6feabc2feaba6a1a70c515e6fd72a38c779293b0f78ff291c4","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260622T183701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-23T06:25:25Z","sig_algorithm":"ed25519","signature":"5576b1d56d5dbb0d96c780fa3ca0940d805c8de95c6251bc87297f0be058aa5e37eb53a6aa1b601381f489f093842cf674b28737ed8e46ce3a49814b5e57290c","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_34cc6a2e1220415d7f24197f9c27c87a3f6759455d65be222341cd97c3415489"}}