{"_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_53a4b79974939aa7e7529a586d11b1fd4560c837c1a21ab002eadbe079bfe89d","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_53a4b79974939aa7e7529a586d11b1fd4560c837c1a21ab002eadbe079bfe89d","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"2514dd5915d0913dd01c9f93059db8cafa0e9ce4dddfc44b80bd7d625d52fe9d","published":"Thu, 11 Jun 2026 00:00:00 -0400","receipt_hash":"2514dd5915d0913dd01c9f93059db8cafa0e9ce4dddfc44b80bd7d625d52fe9d","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":"2514dd5915d0913dd01c9f93059db8cafa0e9ce4dddfc44b80bd7d625d52fe9d","observed_at":"2026-06-11T04:43:37.662146Z","parent_run_hash":"5267801b61ae0d882196b5f37208a9a1633905a64ca7d933f1fa5075cd861491","published":"Thu, 11 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:2606.11634v1 Announce Type: new \nAbstract: The rapid progress of reasoning and agentic large language models (LLMs) has increased the demand for long-context inference, but self-attention (SA) scales quadratically with context length.\n  To address this, we study SWARR (Sliding-Window Attention with Reinforced Adaptation for Math Reasoning), a practical recipe for adapting SWA models to mathematical reasoning. SWARR has two stages: (1) efficient conversion from a pretrained SA model to SWA with supervised fine-tuning (SFT), which avoids pretraining a new base model, and (2) policy adaptation with reinforcement learning (RL).\n  We find that SWA still underperforms SA after SFT, and we hypothesize that this gap is caused in part by a data-architecture mismatch: most SFT data are prepared for SA models and may contain long-range dependencies that are difficult for SWA to model. Because on-policy RL optimizes self-generated trajectories under the SWA constraint, it can adapt trajector","title":"Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning","url":"https://arxiv.org/abs/2606.11634","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.11634v1 Announce Type: new \nAbstract: The rapid progress of reasoning and agentic large language models (LLMs) has increased the demand for long-context inference, but self-attention (SA) scales quadratically with context length.\n  To address this, we study SWARR (Sliding-Window Attention with Reinforced Adaptation for Math Reasoning), a practical recipe for adapting SWA models to mathematical reasoning. SWARR has two stages: (1) efficient conversion from a pretrained SA model to SWA with supervised fine-tuning (SFT), which avoids pretraining a new base model, and (2) policy adaptation with reinforcement learning (RL).\n  We find that SWA still underperforms SA after SFT, and we hypothesize that this gap is caused in part by a data-architecture mismatch: most SFT data are prepared for SA models and may contain long-range dependencies that are difficult for SWA to model. Because on-policy RL optimizes self-generated trajectories under the SWA constraint, it can adapt trajector","title":"Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-11T04:43:37Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.11634"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:c32a69ae316be002f1ef36e60f633d595080bc0b5ddc4f6146e427cfca40730d07d10fb92b4ecc11aecb68e33d709cc3ff8c8b64f95989c1a49efec9eecba406","signer":"crovia.substrate","subject":{"observed_at":"2026-06-11T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.11634"},"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":"75332a2f3ec85e20c83b5de522bf9711efa3b32255f8734df05e79ae8f88df99","leaf_index":227335,"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":"44a946e8d147d235f79c6447af3daab2ee3091fb7b935dba6fc3c0a3971ce7c3","side":"left"},{"sibling":"18f0b4308ea179502adc4868c7e444474c593f3e1ff85c39a0d05a8c8eb1f26d","side":"left"},{"sibling":"4200d3f54790ee8f6f7ef1ca82af4f952774f7439a4576333be02ccf70984d93","side":"left"},{"sibling":"f1a332d3f77229bd4171c99e88019794d985dd3adb588da296cae0a5318565b5","side":"right"},{"sibling":"01c61f70d74c0bc0936d3f32814f6628cb17cd1e57ab800df12350d1551ec9ec","side":"right"},{"sibling":"b2b753a82c989b78f14b304926149833480952d0604588016e1128cd65a65961","side":"right"},{"sibling":"98a196a185b8283495ee2af791dddabecad12b9667f3282e20e2ada5f5abd314","side":"right"},{"sibling":"a6d2c01df24bdf78d7a3a20470793a1585a197c5d8c3f07fc4049ed07458246d","side":"right"},{"sibling":"2cfac7f042209c8533c6031bddc4a83bc156e0595f1b28efefbda208904f338a","side":"right"},{"sibling":"04e399458c5b36988cae0bf1c6dbe1b01349003b15cb5aa43f95c55acffe4ec3","side":"right"},{"sibling":"1383228337d54218bd8e5563aebb0b0dfe15c5269e3d5138e64c261d6130a88b","side":"right"},{"sibling":"57cb49c192550231071a0bf53a0821da2f79c585ec6c8d0fc76cebd62ccd78b2","side":"left"},{"sibling":"cdb58f86163046d3b15f857b03372ec75e1ad9ea4548e086793d528b9eed364d","side":"left"},{"sibling":"533d82482604463aa4a281b9d8b85917b383b7c5f924b2b494039524c55e8797","side":"left"},{"sibling":"b2590791b920ca2a4ed39de126d2c0b1a10d9e7e62f572f12425f214e767b6e1","side":"left"},{"sibling":"6cea4964f32722eb370847c2f7c9d6a9f0622c239538b07e6815a59d6fd8d49c","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":228173,"merkle_root":"7e416202c0bfd759bd2eea4236713b403993d99793fe8badb5065040080bece3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260611T143708Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-11T21:59:35Z","sig_algorithm":"ed25519","signature":"231c80024bc3982dd493c45b31af95097e97aabc6d712a4e5bad7d0cbdd3c08e01ff395b0f8e72754bac97016e0cd0eed88b8a13cb71edbbcb9b6d72c10a7b03","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_53a4b79974939aa7e7529a586d11b1fd4560c837c1a21ab002eadbe079bfe89d"}}