{"_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_142765f8b557bcf28f764709ee28bc9292262c71dec381631a7e274f859eff1f","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_142765f8b557bcf28f764709ee28bc9292262c71dec381631a7e274f859eff1f","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"658fe3b3bd6fea3d654fbaaf2c090f6576997195f8b12cc93d7c83db1cf0ddd7","published":"Mon, 18 May 2026 00:00:00 -0400","receipt_hash":"658fe3b3bd6fea3d654fbaaf2c090f6576997195f8b12cc93d7c83db1cf0ddd7","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":"658fe3b3bd6fea3d654fbaaf2c090f6576997195f8b12cc93d7c83db1cf0ddd7","observed_at":"2026-05-18T04:43:11.219741Z","parent_run_hash":"a8aad7414ebb6b75c726f09cd673410576a7f87e191fbdb9ddac99e9b2b95a05","published":"Mon, 18 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:2605.15290v1 Announce Type: cross \nAbstract: Hyperparameter transfer across model architectures dramatically reduces the amount of compute necessary for tuning large language models (LLMs). The maximal update parameterization ({\\mu}P) ensures transfer through principled mathematical analysis but can be challenging to derive for new model architectures. Building on the spectral feature-learning view of Yang et al. (2023a), we make two advances. First, we promote spectral norm conditions on the weights from a heuristic to the definition of feature learning, and as a consequence arrive at the Complete-P depth and weight-decay scalings without recourse to lazy-learning. Second, we consider a modified spectral norm that preserves the valid scaling law of network weights when weight matrices are not full rank. This enables (to our knowledge, the first) derivation of {\\mu}P scalings for grouped-query attention (GQA). We demonstrate the efficacy of our theoretical derivations by showing ","title":"GQA-{\\mu}P: The maximal parameterization update for grouped query attention","url":"https://arxiv.org/abs/2605.15290","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.15290v1 Announce Type: cross \nAbstract: Hyperparameter transfer across model architectures dramatically reduces the amount of compute necessary for tuning large language models (LLMs). The maximal update parameterization ({\\mu}P) ensures transfer through principled mathematical analysis but can be challenging to derive for new model architectures. Building on the spectral feature-learning view of Yang et al. (2023a), we make two advances. First, we promote spectral norm conditions on the weights from a heuristic to the definition of feature learning, and as a consequence arrive at the Complete-P depth and weight-decay scalings without recourse to lazy-learning. Second, we consider a modified spectral norm that preserves the valid scaling law of network weights when weight matrices are not full rank. This enables (to our knowledge, the first) derivation of {\\mu}P scalings for grouped-query attention (GQA). We demonstrate the efficacy of our theoretical derivations by showing ","title":"GQA-{\\mu}P: The maximal parameterization update for grouped query attention","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-18T04:43:11Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.15290"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:5ecc417e3e7be11bd92b2ddcfcd26476e79aceab43db0bcf4b3c29ce2465fd21f9eb0845f09691b63a7a9b8b2e5b08e7b1cd142eabd2d3291abb55e4c3884804","signer":"crovia.substrate","subject":{"observed_at":"2026-05-18T04:43:11Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.15290"},"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":"5582ed60244913d6ad687e6d49b943dde5b6af1a5490a7a130c033f7a4761971","leaf_index":140571,"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":"9a48a4daee7cc1796de558b1829514274557bcd5bdd6f799e74cfaefeaf537ba","side":"left"},{"sibling":"e3fe56a843467fce5f45be4a7e35cef7b285ffeb20c38c2523d5eb9a79fb977c","side":"left"},{"sibling":"9d21f67d4076e96b98f2121288be850da14fc7a811e07d4c049bca3c03216513","side":"right"},{"sibling":"1c6f2dbddc13e5fc4bd9873ebbde4fde60a6bf3363a02bdd5385e6fb71d60bf2","side":"left"},{"sibling":"77c960d14f524f948c7641cc629bb6e57bdf56b0cd5b6f7dde82ed16702f0d5e","side":"left"},{"sibling":"1f1f26d92a03653ffd7f56f99a44e375f760d3d40a43fb34126b39b693a7e020","side":"right"},{"sibling":"d10f43d638e7e4b5fe1190bff28b23af4dede5ac008b59c8c88d6e509f8c5960","side":"right"},{"sibling":"b29bcbd6adca3228d98aa21ca6aabf98e279340820cd7a960b41569223eebf29","side":"right"},{"sibling":"6bedf73520cf3dd8758d8bdedf3be245de9aea97abd42934aae25539176ae1b2","side":"left"},{"sibling":"07abc3bad689e74e6304772503dc9372a118e6f66883b8e88c43414efddac063","side":"right"},{"sibling":"28b78fb112bcf26b6801664db97eb8f52a9bccbf0a7ae6766e11845d443692df","side":"left"},{"sibling":"68d0a4634c1460a19c92edd9480df3aa733b814463e7420d1e14471bf61b2f83","side":"right"},{"sibling":"8af64f275b862349aa3bbb9d5cd7fa9a7fdd5620af3bf1b36b2a4519b0b53bdf","side":"right"},{"sibling":"8f4c0fbe56b6c010fbb8c782ebcd478079bb3f991d8704e2534209a075d9163c","side":"left"},{"sibling":"b98c2afadb358e5387e88f19588f8343a81b488d9b44a6f7e57a032db3a1b030","side":"right"},{"sibling":"11b0c1591747f09f7c8971a6caa19befcd81317ca9dfd417b143234df4e10c79","side":"right"},{"sibling":"87206f3bcc342797c990d87f7235c01f78d32ca59cfaf8ad18d71afc879ba477","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":140892,"merkle_root":"6cca56ead155990456b8a014cc50bddbe710f409b26e3d1bfa6fb12b0bfcf6bf","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260518T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-18T05:37:30Z","sig_algorithm":"ed25519","signature":"1e1135f7595f79b14fb11f5fa81a2e17ad31b11b44b427a5e40a7d511cd86447daf492babd368ab571cf26404c8c74c450d460130fca4b064eb2760367489a0f","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_142765f8b557bcf28f764709ee28bc9292262c71dec381631a7e274f859eff1f"}}