{"_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_65c0c3b6fd8ab44bedc701b4b1a0d461dc6b07db7a92ea5d60f16f3abbb91b5f","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_65c0c3b6fd8ab44bedc701b4b1a0d461dc6b07db7a92ea5d60f16f3abbb91b5f","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"34781d598deb87646e4613f0d98d039530fa541cbde25e00474703f940abeb6a","published":"Wed, 03 Jun 2026 00:00:00 -0400","receipt_hash":"34781d598deb87646e4613f0d98d039530fa541cbde25e00474703f940abeb6a","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":"34781d598deb87646e4613f0d98d039530fa541cbde25e00474703f940abeb6a","observed_at":"2026-06-03T04:43:57.136784Z","parent_run_hash":"62ae9c8eda846b00bc49666345b338d00756c5203438666c4c1fc694cc364b84","published":"Wed, 03 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:2605.20402v3 Announce Type: replace-cross \nAbstract: MXFP4 arithmetic can dramatically accelerate reinforcement learning (RL) post-training of large language models (LLMs), yet the quantization error introduces severe accuracy degradation. Existing work treats the quantization error as a monolithic noise term, missing the distinct mechanisms upon interpreting how quantization error damages training. We prove an exact three-way decomposition of quantization error and show how each component dominates a distinct RL training pathway. Our theoretical and empirical analysis decomposes the MXFP4 quantization error into three additive components: \"scale bias\" from power-of-two rounding, \"deadzone truncation\" from zeroing small values, and \"grid noise\" from rounding to the nearest 4-bit grid. Each component dominates a distinct RL failure mode: scale bias accumulates multiplicatively through the backward pass, affecting gradient accuracy; deadzone truncation degrades rollout quality; and","title":"Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor","url":"https://arxiv.org/abs/2605.20402","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.20402v3 Announce Type: replace-cross \nAbstract: MXFP4 arithmetic can dramatically accelerate reinforcement learning (RL) post-training of large language models (LLMs), yet the quantization error introduces severe accuracy degradation. Existing work treats the quantization error as a monolithic noise term, missing the distinct mechanisms upon interpreting how quantization error damages training. We prove an exact three-way decomposition of quantization error and show how each component dominates a distinct RL training pathway. Our theoretical and empirical analysis decomposes the MXFP4 quantization error into three additive components: \"scale bias\" from power-of-two rounding, \"deadzone truncation\" from zeroing small values, and \"grid noise\" from rounding to the nearest 4-bit grid. Each component dominates a distinct RL failure mode: scale bias accumulates multiplicatively through the backward pass, affecting gradient accuracy; deadzone truncation degrades rollout quality; and","title":"Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-03T04:43:57Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.20402"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:9036f685ce45445e89d4f8cc6a76efb28bcf20efb4b4e146eb19c47cb593c9cc0c0c8e2780becf6dc1c7499f429d8bab0adc85070d5a5537aac8f594410bb80a","signer":"crovia.substrate","subject":{"observed_at":"2026-06-03T04:43:57Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.20402"},"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":"e112e71465d8f3ecea0c4ea9d97e960bc7f4ddf0c95c3ec2405707ca4b6bcde1","leaf_index":209428,"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":"3b48ef462fa0c89dd9cdf7bae66d44ad4a7ce42c68814bc03fcaecae07d772e9","side":"right"},{"sibling":"9b8c7a9434d46844cbb17adbbeb5423b3ea2abb7316d33f0ba369200a6d8918a","side":"right"},{"sibling":"fe88d1daeec6302cf80dae94f44e7c01504164ad41762f086b4bed51d828aaca","side":"left"},{"sibling":"2133f0ac4927b2cb4e003384bd9708bad3d4e2b251f086bd01109ee6fdd77b4d","side":"right"},{"sibling":"385a1c737c64457152f99ed56d2a68e3d6cf57bc6c9992e5c9092771c7a764e3","side":"left"},{"sibling":"d559fd51a6779addbcf4873e4b3f57dd068a0a4e618a552735f68c4c42472a78","side":"right"},{"sibling":"11ca635b4b48a5b191a023a3e865a6eb46cdcbad96ba62c238e770638277d969","side":"right"},{"sibling":"bd3f18ac9afb820a8496e447be39bc88ed2f38fc07726a205afbf4d7a97200b4","side":"right"},{"sibling":"5644262858e1dd0ce48f35fced719d068af594f17e93eb1cc769fc5838adcf49","side":"right"},{"sibling":"064aa099decb52d50f639e1542dae2860403f9fca4f561c55f796d74f4af6a83","side":"left"},{"sibling":"2b6b45743f97ac502854e489ac38a3366f8ae7ede58a2728b45daadbf29e9d03","side":"right"},{"sibling":"a81babbd79ea0da9e030dd7f43bffb6519d214317decd50727bea4e78189d970","side":"right"},{"sibling":"2dca509b3eb767a47cf215d4315f230ce9103a76264412008ae23a349b519ef1","side":"left"},{"sibling":"24d1bb4b13e0e46131b27b70a48e65fcf4e2e14b95e3bb83ade821e9df530f6b","side":"left"},{"sibling":"8d3baa674a45fd8bc6d3e8d25298f4bec86c72fa8259d576c330d12955c7b4f7","side":"right"},{"sibling":"e32819d1eff909db08066d1703f2db3f091cddac19378b2c0c625ab11e3fdbc0","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":209569,"merkle_root":"c852efc8ad7dfffc196c71380f79e6398bcaf566974cbae7c9950b0f600d5bc8","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260603T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-03T05:37:57Z","sig_algorithm":"ed25519","signature":"1ca417607effc813341721cfdade0a2d2d4ba96a90d361dbc3e864b6991b90abc326ec41d9ba3e7110cc04adb29d7b8d95abea7ff2ab8c591b2f864ed7270c03","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_65c0c3b6fd8ab44bedc701b4b1a0d461dc6b07db7a92ea5d60f16f3abbb91b5f"}}