{"_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_e1fac86611337fee1cc0665ff67eb72a495e116da8cd4ab772b5ca7fbad2763d","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_e1fac86611337fee1cc0665ff67eb72a495e116da8cd4ab772b5ca7fbad2763d","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"dc08b615b3d4ce3f87d595b20fd953dc363c1f312e33c79a9d2c681da93e73d4","published":"Thu, 18 Jun 2026 00:00:00 -0400","receipt_hash":"dc08b615b3d4ce3f87d595b20fd953dc363c1f312e33c79a9d2c681da93e73d4","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":"dc08b615b3d4ce3f87d595b20fd953dc363c1f312e33c79a9d2c681da93e73d4","observed_at":"2026-06-18T04:43:37.219665Z","parent_run_hash":"de79a40f7b3537d88842f7ac355e799c5df2adcb4fc32a4e28096d4bbdf01739","published":"Thu, 18 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:2606.18521v1 Announce Type: cross \nAbstract: Reinforcement Learning with Verifiable Reward (RLVR) has emerged as a powerful post-training paradigm that surpasses Supervised Fine-Tuning (SFT) in eliciting reasoning intelligence and resisting catastrophic forgetting. Recent studies further reveal that RLVR induces highly sparse and off-principal parameter updates compared to SFT. This naturally raises the question: does such sparsity make RLVR models more amenable to model merging? If so, model merging would offer a scalable, training-free path to aggregate diverse reasoning capabilities from independently trained RLVR models. Surprisingly, we find the opposite, uncovering a sparsity curse: the sparse RLVR updates are spread farther apart in parameter space, forming near-orthogonal shortcuts that make aggregation inherently fragile. This is likely rooted in the stochasticity of RL optimization and the diversity of emergent reasoning patterns. Unlike SFT models that converge to shar","title":"Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging","url":"https://arxiv.org/abs/2606.18521","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.18521v1 Announce Type: cross \nAbstract: Reinforcement Learning with Verifiable Reward (RLVR) has emerged as a powerful post-training paradigm that surpasses Supervised Fine-Tuning (SFT) in eliciting reasoning intelligence and resisting catastrophic forgetting. Recent studies further reveal that RLVR induces highly sparse and off-principal parameter updates compared to SFT. This naturally raises the question: does such sparsity make RLVR models more amenable to model merging? If so, model merging would offer a scalable, training-free path to aggregate diverse reasoning capabilities from independently trained RLVR models. Surprisingly, we find the opposite, uncovering a sparsity curse: the sparse RLVR updates are spread farther apart in parameter space, forming near-orthogonal shortcuts that make aggregation inherently fragile. This is likely rooted in the stochasticity of RL optimization and the diversity of emergent reasoning patterns. Unlike SFT models that converge to shar","title":"Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-18T04:43:37Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.18521"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:4c20e32eaf01321e9a458f28be7efb08967d46949d526276f4e5dc113eccea2e43d07281c20767bd0262ef7d0b3ef4b056d7e585f30e16de5898f0287c9d2006","signer":"crovia.substrate","subject":{"observed_at":"2026-06-18T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.18521"},"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":"c5f8b1e3edbb78456bcb4a423e5eef6af2abfde2d9abfab6deba556864bd1a05","leaf_index":233337,"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":"eaa10b152be5d4345a928c1060836b1f60f2a39ddd090cde8fc0794c483bb1e7","side":"left"},{"sibling":"a03364e8aaabf569d2f9c1366e13cbe249f859e0341d1b0a7ac07c7ead57ffdd","side":"right"},{"sibling":"393f521235b514832d6ff10e5138e19f3c892bbe264781f0e09c50e682f784b2","side":"right"},{"sibling":"79c2cee6e7be01492939540d590010d272f00710026d891d00f255bd9615e689","side":"left"},{"sibling":"9d7012241c7bc6951603d251ee2991fa5bcb270945a8e93f28b5ac665c4c61ee","side":"left"},{"sibling":"fffc094d5a9b079ba5f4fd126957bc58d6ef5e5cde89e47f776f9bae2ad17a6b","side":"left"},{"sibling":"fb2efccf288f12f103208a3d9da4b3826488e1b2cf803df6c0d9957623efbe10","side":"left"},{"sibling":"0330fab6a2deb3386a57965a262bbfda239c89f35362e27a0c4e7f3a9108ec2e","side":"right"},{"sibling":"429c2a92a65e6eeaa2eda0a35fdb9e541472a1eace4c69a4d01a618a659a110f","side":"left"},{"sibling":"d97d1ebe04af6ea572f9d4334004d01026acffa3da5be2883c7566513c76e2c0","side":"left"},{"sibling":"571eb56e7ce00fe1f38d0ac4fc56828d01b2cfc1ab9089cde245c0656bee0514","side":"left"},{"sibling":"7ac50038a8ced3aeaf1194a2407a4a09346b0e4399da36ecde4390675a0c4bf1","side":"left"},{"sibling":"8c5e2b48dc31ef0edcd35c3db048235aa78cc48443aa2a8da3aa6e9b5524d2c4","side":"right"},{"sibling":"e616c34dbaf9456d5a6d3e2da82cde8621293c9f6d8a4cf9e441d7fd9cc81579","side":"right"},{"sibling":"94c0c932e61657f5e37fdba43f6ca9eddea8359425a7c1558dabe566911d5304","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":234491,"merkle_root":"02576a6980e38bab47864ae2c57b5a5ff21e554e9bdf8f64bdf28155ff1aabec","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260618T143732Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-18T18:33:39Z","sig_algorithm":"ed25519","signature":"b6c708778fc38b7789a2b91156cfe87252a7cd3a1d29121cba11a0c78f8cf104ca3019fc50a962fa5a216bcc4922fc8f3f69c04d1f8332c6dc0d931e1012e502","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_e1fac86611337fee1cc0665ff67eb72a495e116da8cd4ab772b5ca7fbad2763d"}}