{"_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_0dee6a17450fc718a01977e71b79d2b08ffaaa96d0a2e0fba484e7dd10f2da25","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_0dee6a17450fc718a01977e71b79d2b08ffaaa96d0a2e0fba484e7dd10f2da25","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"916f6446a0a3bc03499f05335be47b91fed24ee5307f52434f787c67b4a0a65d","published":"Thu, 21 May 2026 00:00:00 -0400","receipt_hash":"916f6446a0a3bc03499f05335be47b91fed24ee5307f52434f787c67b4a0a65d","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":"916f6446a0a3bc03499f05335be47b91fed24ee5307f52434f787c67b4a0a65d","observed_at":"2026-05-21T04:43:31.073835Z","parent_run_hash":"5047c4a56b18dd764734c0da16c60af14d40680f3bac4bcad4e9983899d001f9","published":"Thu, 21 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:2605.19409v2 Announce Type: cross \nAbstract: Continual Model Merging (CMM) enables rapid customization of foundation models across sequentially arriving tasks, offering a scalable alternative to repeated retraining. However, existing merging rules lack explicit controllability over the allocation of learning capacity between previously learned capabilities and newly merged models. Consequently, as tasks are merged sequentially, this deficiency accumulates into severe forgetting, particularly in scenarios with heterogeneous task importance, where performance allocation becomes highly inconsistent. The key reason can be attributed to the fact that previous methods treat each task model as an isolated parameter point and apply fixed algebraic combinations, rather than explicitly constructing a transition that respects how independently trained models can be connected in parameter space. Motivated by mode connectivity, we assume that desirable merged models lie on low loss connecting","title":"Unlocking the Potential of Continual Model Merging: An ODE Perspective","url":"https://arxiv.org/abs/2605.19409","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.19409v2 Announce Type: cross \nAbstract: Continual Model Merging (CMM) enables rapid customization of foundation models across sequentially arriving tasks, offering a scalable alternative to repeated retraining. However, existing merging rules lack explicit controllability over the allocation of learning capacity between previously learned capabilities and newly merged models. Consequently, as tasks are merged sequentially, this deficiency accumulates into severe forgetting, particularly in scenarios with heterogeneous task importance, where performance allocation becomes highly inconsistent. The key reason can be attributed to the fact that previous methods treat each task model as an isolated parameter point and apply fixed algebraic combinations, rather than explicitly constructing a transition that respects how independently trained models can be connected in parameter space. Motivated by mode connectivity, we assume that desirable merged models lie on low loss connecting","title":"Unlocking the Potential of Continual Model Merging: An ODE Perspective","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-21T04:43:31Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.19409"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:d227347edcb76e0aaabf65f5413273e6105373111a7403b8986a4095e79a09f3fa2d08f1e91c636432dbec157e280398cc723e9634767a5a9adfcd3d7ecf1d07","signer":"crovia.substrate","subject":{"observed_at":"2026-05-21T04:43:31Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.19409"},"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":"2016d9cb1250c07b4e478b3c4556aca7b03e24cf3652a28ea6df0ba4f04aec08","leaf_index":146067,"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":"2d3b7f4a7e702544e2e1d2f8d5ce2ed1efd160620bdc1a724098d7955a831d41","side":"left"},{"sibling":"671c441b371bd211835c9a86ef48e7709eecb706034d325043232f6a66f08da7","side":"left"},{"sibling":"8bd8b5d54781156764e88dcea022774e0f0fb18005cd7dc0f5ef34ea5966d3f4","side":"right"},{"sibling":"f3e6b67ad8cfb471fab17c8f2fb4c62cef62429fa6ec27cb7377aea125138ec7","side":"right"},{"sibling":"b957aa3392a47d83fbb1a6819563adb3ad6dd0f86a5aafbb38a1d68e952d2645","side":"left"},{"sibling":"b2a2594970499ef0b84e8624114d226ef874a95c1d9b9a6de0646e0d7fca0d4c","side":"right"},{"sibling":"cfdfcdf15c10b7f30f2c03e430270fe58f21c87e1dd8b50b3e107416147771ca","side":"right"},{"sibling":"e2d788db0d8449372377479a631b42a652a64ed491d720f74dda5781d988ae76","side":"left"},{"sibling":"f39a7335aa6b82bde60c7b432781bd9e0a9e8ae7bfc7bd50eeb0fe7acdf83691","side":"right"},{"sibling":"3d048271f4871de655c4d4e2d83c1a269789f9e8b4e12a7f789beea57480c8a4","side":"left"},{"sibling":"14b1a643ffa50eeeb494fd3a15fd505a15e79133c339d915d5cac16c81067c49","side":"right"},{"sibling":"8c417ae33891ef4f8dbdef16d48b6a102716fb1ddbdcae54ff85dcedb4f657d4","side":"left"},{"sibling":"3e4df6e7457cecbf36f350375e72dcab336a3984422e4c406ef809e4e2944e96","side":"left"},{"sibling":"8f4c0fbe56b6c010fbb8c782ebcd478079bb3f991d8704e2534209a075d9163c","side":"left"},{"sibling":"be08fedc4e72a6fb56606f66812fae7317e09690b9acb18385f4ab117a981238","side":"right"},{"sibling":"0534329a7475dc9df51998c83c16892126679dade0fa34182f21e869599386c7","side":"right"},{"sibling":"2d24720928ead0e7670650eb55f558c4f20e4c18df376f47ba72cfa8cf0ed344","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":147301,"merkle_root":"08903d7159c3b38eeeeafc09eab15139ea417f1d94f02f1fbc87296b37db840a","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260521T183701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-21T18:37:33Z","sig_algorithm":"ed25519","signature":"905f2924632dfa2970c8690285f5b5d4a1d891d0e0ef1cbc404ebec2fd937215ac768e16f0a9f28b18977a55ae0bfd226db6833ae7ef588729054117d2da7303","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_0dee6a17450fc718a01977e71b79d2b08ffaaa96d0a2e0fba484e7dd10f2da25"}}