{"_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_9dd896c5ecd7e525863664b503c95f0f58a3b75d511b5cec1f825cf32f4e8b4b","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_9dd896c5ecd7e525863664b503c95f0f58a3b75d511b5cec1f825cf32f4e8b4b","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"134f754b44434f2fec5a7d9f11142d4c5ac458e2a655a2025a9992a20fc438c9","published":"Wed, 17 Jun 2026 00:00:00 -0400","receipt_hash":"134f754b44434f2fec5a7d9f11142d4c5ac458e2a655a2025a9992a20fc438c9","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":"134f754b44434f2fec5a7d9f11142d4c5ac458e2a655a2025a9992a20fc438c9","observed_at":"2026-06-17T04:43:17.968423Z","parent_run_hash":"8f56c4deb22b28178ba7974d6ffc5ff17336d44c95dd94de80095705245fa113","published":"Wed, 17 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:2602.03846v2 Announce Type: replace-cross \nAbstract: We develop a continual learning method for pretrained models that \\emph{requires no access to old-task data}, addressing a practical barrier in foundation model adaptation where pretraining distributions are often unavailable. Our key observation is that pretrained networks exhibit substantial \\emph{geometric redundancy}, and that this redundancy can be exploited in two complementary ways. First, redundant neurons provide a proxy for dominant pretraining-era feature directions, enabling the construction of approximately protected update subspaces directly from pretrained weights. Second, redundancy offers a natural bias for \\emph{where} to place plasticity: by restricting updates to a subset of redundant neurons and constraining the remaining degrees of freedom, we obtain update families with reduced functional drift on the old-data distribution and improved worst-case retention guarantees. These insights lead to \\textsc{PLATE}","title":"PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning","url":"https://arxiv.org/abs/2602.03846","vendor":"arxiv_cs_ai"},"summary":"arXiv:2602.03846v2 Announce Type: replace-cross \nAbstract: We develop a continual learning method for pretrained models that \\emph{requires no access to old-task data}, addressing a practical barrier in foundation model adaptation where pretraining distributions are often unavailable. Our key observation is that pretrained networks exhibit substantial \\emph{geometric redundancy}, and that this redundancy can be exploited in two complementary ways. First, redundant neurons provide a proxy for dominant pretraining-era feature directions, enabling the construction of approximately protected update subspaces directly from pretrained weights. Second, redundancy offers a natural bias for \\emph{where} to place plasticity: by restricting updates to a subset of redundant neurons and constraining the remaining degrees of freedom, we obtain update families with reduced functional drift on the old-data distribution and improved worst-case retention guarantees. These insights lead to \\textsc{PLATE}","title":"PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-17T04:43:17Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2602.03846"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:ff576dc9bc52f12b5a69197d805e504d5b2f11d9cec8830a2389de22b8a070a100cc580aa92f2665c4faaeb90792e2ea785acff3ad0607a21b9d5dcd66f06a07","signer":"crovia.substrate","subject":{"observed_at":"2026-06-17T04:43:17Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2602.03846"},"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":"5bcdc109932209e7e8f6798448decb05932bdc6a86704b47f5f1d994c1e3c7db","leaf_index":231130,"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":"a51dcc7cdc772381d5576b269af465e2249b851b917b90a277d57813e49a4b0b","side":"right"},{"sibling":"4eccf4fd0c409e5808e0159c39ae5b90d20fea92ec3443565c6c262de6a2e39f","side":"left"},{"sibling":"6b2de52cc16886a04a8e9bb92647aa7b42acb376b6e23ba4d5318acd70da3792","side":"right"},{"sibling":"6938f3417ee4bd2d91f2bc65606cdbbc001935cbea05d98dc4a22fd20a2c360b","side":"left"},{"sibling":"8e7d85583cd24300c9b4976df50bae5f41dc08f0618d01ce66a8bcfd03851752","side":"left"},{"sibling":"52feda4d4d9359d2d68ff2fa63fa82d002bd8aaff07215ae8020598205725938","side":"right"},{"sibling":"c2be4562846190ba3164039cd94048f5bbae396d8f7927deaa875af1a5888a4b","side":"left"},{"sibling":"f9fc1f172b9aaac5635bc943e16d4e16badadc9ca81e3f68212276c41230e861","side":"left"},{"sibling":"ebbec9ce4bf43a3f5f71e2c07df4c91301abefa2da727a4d748099a74e980bc3","side":"right"},{"sibling":"1d74941c32baeab8cad08f8700cb49427d8256f231534f2a225b2bb3e84e4ff8","side":"left"},{"sibling":"d5b9f8b1a2c9f6a46e17982dfbe6ce1f3b5fa4e730220397f2253d114dcc8486","side":"left"},{"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_9dd896c5ecd7e525863664b503c95f0f58a3b75d511b5cec1f825cf32f4e8b4b"}}