{"_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_095ef3601cea5e5bcdd757556234ce2dc03379ce095d2c4a048cf2b519e2b31e","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_095ef3601cea5e5bcdd757556234ce2dc03379ce095d2c4a048cf2b519e2b31e","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"90dbdbe89eb1c0d68bb2ab3b430a99121fee3b5b541b0dac558f19aced08382f","published":"Fri, 12 Jun 2026 00:00:00 -0400","receipt_hash":"90dbdbe89eb1c0d68bb2ab3b430a99121fee3b5b541b0dac558f19aced08382f","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":"90dbdbe89eb1c0d68bb2ab3b430a99121fee3b5b541b0dac558f19aced08382f","observed_at":"2026-06-12T04:43:44.933383Z","parent_run_hash":"a8b304a31db3809a528f5a45e58597f7bb9f23028e53b4f9ed2f5599dd731b5e","published":"Fri, 12 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:2606.13233v1 Announce Type: cross \nAbstract: Large reasoning models (LRMs) improve complex problem-solving by generating long intermediate reasoning traces, but this substantially increases inference costs. NVFP4 inference offers a promising approach to reduce both computational and memory costs through hardware-supported low-precision execution. However, directly applying NVFP4 to LRMs introduces two practical limitations: reasoning accuracy degrades under quantization, and existing NVFP4 kernels do not fully realize latency benefits in small-batch autoregressive decoding. In this work, we analyze the effect of NVFP4 quantization on token-level uncertainty during reasoning. We show that quantization increases incorrect sampling at low-entropy symbolic tokens, while causing over-concentration on a small set of tokens in high-uncertainty reasoning steps. Based on this observation, we propose \\textbf{ReSET}, a reasoning-step entropy-based temperature-scaling method that estimates s","title":"ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling","url":"https://arxiv.org/abs/2606.13233","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.13233v1 Announce Type: cross \nAbstract: Large reasoning models (LRMs) improve complex problem-solving by generating long intermediate reasoning traces, but this substantially increases inference costs. NVFP4 inference offers a promising approach to reduce both computational and memory costs through hardware-supported low-precision execution. However, directly applying NVFP4 to LRMs introduces two practical limitations: reasoning accuracy degrades under quantization, and existing NVFP4 kernels do not fully realize latency benefits in small-batch autoregressive decoding. In this work, we analyze the effect of NVFP4 quantization on token-level uncertainty during reasoning. We show that quantization increases incorrect sampling at low-entropy symbolic tokens, while causing over-concentration on a small set of tokens in high-uncertainty reasoning steps. Based on this observation, we propose \\textbf{ReSET}, a reasoning-step entropy-based temperature-scaling method that estimates s","title":"ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-12T04:43:44Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.13233"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:93934017e99c129b001ca00d54cc9cef565e07b94225ed1fc194986fcfd7c2c30c2e8a8777aa09242bee314316424203eaf0d9833cbe9e31cd6ebaf934561c0e","signer":"crovia.substrate","subject":{"observed_at":"2026-06-12T04:43:44Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.13233"},"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":"b7f2e11a692ae464206706ecc9171fc41d6609df28cf5597eb7ce97baa0ee35a","leaf_index":229764,"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":"863589c9a3e68135babaa774e4b27753af93348f8bb9c073b42d7362b87c95ad","side":"right"},{"sibling":"5a08e4e430c08c7b8068ff9d6b92bae31189a24be3807073360248d979e39796","side":"right"},{"sibling":"866582347594db5e6f2c3593420eaa818ec72f723f5b0e3dddc2491d2f172b7d","side":"left"},{"sibling":"93f8492e535cd81f14ac2118f64e7d3938181e2900ddacd0303aeccbe0953947","side":"right"},{"sibling":"45a32b7aef6152d34dcb5759a3d2c12cdd6b2bc2b476b845db396597a6626cb3","side":"right"},{"sibling":"f980b09d747f400406442a2d8e6636d297423fefcfc4f6dd933ef6f37a1d3e0c","side":"right"},{"sibling":"f8bab1c4b4d78ecdc0c7c24f3f0491d32c6f49b960c42926df1ece7da77ecd89","side":"right"},{"sibling":"ae0aa292f48289283e26aa363532f22206cc7cea51771c75c6c011c898bec69c","side":"left"},{"sibling":"99d288e6cd43a807fba958865176bb1c08b82471afe942f6e4989eaeeb7275aa","side":"left"},{"sibling":"d385017d38a86f6abc492026a7cd60ceb3b3ff2486142dc49e5acb179f4b7d11","side":"right"},{"sibling":"bde25d7e94e64717e426a97f6fcb4907e92b5c61fc89d92d7e0947a2249c3f6b","side":"right"},{"sibling":"d10d772a4984cae00e65ab24af21d1d260e475bbaae3f17871859eb705bd3999","side":"right"},{"sibling":"e79159853f2f35ddae8e3247d515e433c534277b287d65bbd77ae989aa4992fa","side":"right"},{"sibling":"3054319f1840cce0eaaf0bc4b1ae38e5bf8b6210927d924a750775cc7d77cca6","side":"right"},{"sibling":"0fd8b5059f279c4a4a6688de2472fdbc25543fee183df19b21dacca880354cff","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":232015,"merkle_root":"62bfb7809bb55667ad7eeebdb48267b9b2c1ee89bb808ea1e6d3a814a15aa402","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260617T133701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-17T13:39:59Z","sig_algorithm":"ed25519","signature":"930a3563c643cc7518d048b12a1f5392a96a5edce49533ba0a56f11b6cc69319bb1c800aacc46b52a6941c4d05dae255a45cac757d6093c971b96852c24f140e","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_095ef3601cea5e5bcdd757556234ce2dc03379ce095d2c4a048cf2b519e2b31e"}}