{"_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_d452cc74ff2338e33e8a6736548ce7bf9305f76df931f8e5e6deade564aab2b3","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_d452cc74ff2338e33e8a6736548ce7bf9305f76df931f8e5e6deade564aab2b3","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"ed76bed358c04e7082567f0b58a1122ff8c58e45b9711230c20a380db38985ee","published":"Thu, 28 May 2026 00:00:00 -0400","receipt_hash":"ed76bed358c04e7082567f0b58a1122ff8c58e45b9711230c20a380db38985ee","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":"ed76bed358c04e7082567f0b58a1122ff8c58e45b9711230c20a380db38985ee","observed_at":"2026-05-28T04:43:38.862500Z","parent_run_hash":"58f8b4a134069e0a15ea3949252489597eb86dd27c9ca3fb15c6fb838ce49ef3","published":"Thu, 28 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:2605.28421v1 Announce Type: new \nAbstract: Reinforcement learning has become a central paradigm for advancing reasoning in large language models, yet most existing methods still depend on stronger teacher models or heavily curated difficult datasets, limiting scalable capability improvement. In this paper, we introduce DenoiseRL, a reinforcement learning framework that substitutes external supervision with recovery-oriented optimization over failures from weak models. Instead of relying on stronger supervision or carefully engineered data, DenoiseRL learns directly from incorrect reasoning traces by converting them into opportunities for improvement, making training more scalable and less dependent on external resources. This yields a richer and more diverse learning signal, improving exploration efficiency from imperfect model behavior. As a result, DenoiseRL improves reasoning performance and overall training efficiency while reducing the need for expensive data curation or str","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","url":"https://arxiv.org/abs/2605.28421","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.28421v1 Announce Type: new \nAbstract: Reinforcement learning has become a central paradigm for advancing reasoning in large language models, yet most existing methods still depend on stronger teacher models or heavily curated difficult datasets, limiting scalable capability improvement. In this paper, we introduce DenoiseRL, a reinforcement learning framework that substitutes external supervision with recovery-oriented optimization over failures from weak models. Instead of relying on stronger supervision or carefully engineered data, DenoiseRL learns directly from incorrect reasoning traces by converting them into opportunities for improvement, making training more scalable and less dependent on external resources. This yields a richer and more diverse learning signal, improving exploration efficiency from imperfect model behavior. As a result, DenoiseRL improves reasoning performance and overall training efficiency while reducing the need for expensive data curation or str","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-28T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.28421"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:30253fc54f2d44cae7fcc2ef251e08076fa7f115883f8507e2f35e36204c01d48b39606eba5cc88a2288021f63ed7cfced8b25eb2eb442fbe1e91d6ffb26a80b","signer":"crovia.substrate","subject":{"observed_at":"2026-05-28T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.28421"},"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":"3dd65d409593c34620d32617989831085540094aac8e98e53010cfe2ed40317b","leaf_index":155686,"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":"8b33c11ea8ace82cd1a0c0bf6679b108d44f6a911b91d7e5299e63f284a021ec","side":"right"},{"sibling":"2e972bfe727cbca62fcd5f9f8f8ae96d06f3ef526715ce9a1b35bb5b22fa2097","side":"left"},{"sibling":"697a283ea3c62a5877506c10e2630ba10e918b1a5e7ef9513562c229f24c7400","side":"left"},{"sibling":"4212d47318c662a8117fb5075cb416374b3962c4c15c003abe4c3f607890889a","side":"right"},{"sibling":"88a5b09bdd647673190e24d8d4d08a26a0d4adf5c599885cd73097d552e601fb","side":"right"},{"sibling":"5743bc352c06496fc3b58c8a3462f60161d9cae157c0e80c0e29b0772529e640","side":"left"},{"sibling":"36a1078bdcaa003b6d473a09d4271a7c46743ba8b6266a216c903bba5595bb84","side":"right"},{"sibling":"afa86de7d2b39f53748bea8c4274ea857aed4694d034da9da1628457bb87cbe4","side":"right"},{"sibling":"0adb35dd3ad9bfc4a781c02606acf0a3ce1e28e1a88066209cc1a35814e790ad","side":"right"},{"sibling":"f292d3278e493ec60902181b8c0bd5c89c0a1168ef928222fe6161287982f7f0","side":"right"},{"sibling":"2209295faf1a5bf51c97c6fd5a839a8181a4ea44f490420381530f35df7d9b2f","side":"right"},{"sibling":"5784576a15214ea9fc3569e6e1cff1ef443c0b1fc0d036028489088af089de27","side":"right"},{"sibling":"311772ec218efcb2da5a337f9e9f042fe1cc0028643adb0a354787e4ea7911b7","side":"right"},{"sibling":"66331bac84ca0f8983eb09fac7eaf95af234f1b82680b793eabff4ee25caac40","side":"left"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"7b6f0bea4291a5e63574dfca9aa0f9756f450c9478c3d07474d39a7ababb51f9","side":"right"},{"sibling":"1d39fe14b21e2ebbfb87e882423b24ee9469eae1e4c77af5b799ac4db9537467","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":156177,"merkle_root":"c5705a0243d16afd8b1ebfd731b7aa304079c442c2a7906493c5bbed374c69ec","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260528T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-28T05:37:36Z","sig_algorithm":"ed25519","signature":"f087e13febc8bb6a2e0812610de64cebc65be92915518d9c4b230799c3b161839b04c4eb1b02741f938f35545a76ab76555b04c782bdc2f9a44852d171d65909","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_d452cc74ff2338e33e8a6736548ce7bf9305f76df931f8e5e6deade564aab2b3"}}