{"_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_361e774112c67f2b21fd2be39bda2abf880d7112cdb6183e8d46bef1ad55ac34","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_361e774112c67f2b21fd2be39bda2abf880d7112cdb6183e8d46bef1ad55ac34","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"c7d173097dd71df1c0108667dda33a3307ce8f70f93a29856667b568d25d7a02","published":"Wed, 01 Jul 2026 00:00:00 -0400","receipt_hash":"c7d173097dd71df1c0108667dda33a3307ce8f70f93a29856667b568d25d7a02","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":"c7d173097dd71df1c0108667dda33a3307ce8f70f93a29856667b568d25d7a02","observed_at":"2026-07-01T04:43:38.812993Z","parent_run_hash":"0e10ec7d671a375a4e18d8645653df2b4352c82fe16fae2a400af6f7634d6699","published":"Wed, 01 Jul 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:2606.30813v1 Announce Type: cross \nAbstract: Deep neural networks with repeated architectural blocks, such as transformers, often exhibit structured relationships across layers that emerge during training. Motivated by this observation, we introduce \\emph{Depth-wise Gradient Augmentation}, a general optimization paradigm in which the update applied to each layer is obtained by transforming the collection of block-wise optimizer updates along the depth dimension. Within this framework, we study \\emph{Gradient Smoothing}, a family of depth-wise smoothing methods, and instantiate it with a simple local \\emph{Window Smoothing} operator. The resulting method operates directly on block-wise updates produced by arbitrary base optimizers (e.g., SGD, Adam, Muon), incurs minimal computational overhead, and is compatible with existing optimization pipelines. We evaluate Gradient Smoothing across a diverse set of architectures and training regimes, including language model pretraining, RL po","title":"Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization","url":"https://arxiv.org/abs/2606.30813","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.30813v1 Announce Type: cross \nAbstract: Deep neural networks with repeated architectural blocks, such as transformers, often exhibit structured relationships across layers that emerge during training. Motivated by this observation, we introduce \\emph{Depth-wise Gradient Augmentation}, a general optimization paradigm in which the update applied to each layer is obtained by transforming the collection of block-wise optimizer updates along the depth dimension. Within this framework, we study \\emph{Gradient Smoothing}, a family of depth-wise smoothing methods, and instantiate it with a simple local \\emph{Window Smoothing} operator. The resulting method operates directly on block-wise updates produced by arbitrary base optimizers (e.g., SGD, Adam, Muon), incurs minimal computational overhead, and is compatible with existing optimization pipelines. We evaluate Gradient Smoothing across a diverse set of architectures and training regimes, including language model pretraining, RL po","title":"Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-01T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.30813"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:1dd1ff0eb56802bb3d31cc22ffe8a9418444e714e4963f2903e4867ca121f241259989ec6ea26a14bab6877fdc9f3eef87adfdad6a5126c74ed2ff22d55b7506","signer":"crovia.substrate","subject":{"observed_at":"2026-07-01T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.30813"},"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":"10c849d5cee9b349ee472281bde7a595120a1d16ce149913d684a75fc0dc5623","leaf_index":268506,"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":"c793946c6c657c62ad45fd3ac53c37f906e4f797ace8d72b2d88388c3717f39f","side":"right"},{"sibling":"3b481cf06aefa10b491046a96d319f492577475ad7ff5874ac8f85aa9f511466","side":"left"},{"sibling":"42b6bcd37e0fb801d33be01fae5cea90ce897f1bf6ffbefa16c4a94fdd858974","side":"right"},{"sibling":"4d396d13b0940ae9e6db5d4d26e59ef0d828a86bdda5a8811d40f29e6f895aec","side":"left"},{"sibling":"8237f11ae5aed9d85a2f5614e53b6e6f20a08d7623c319d0fe6e042bd137d849","side":"left"},{"sibling":"1f57a328336cba4f64ebda75a50e218bfbd4e765f97b60048ff838beb1cadf1d","side":"right"},{"sibling":"8325907723322726e28223e7a58209725d2c897da06068f32115d78744fe46e1","side":"left"},{"sibling":"373441c77391345a6bdd59f6d24909be6fec81e993e9a7050109db1522722b95","side":"left"},{"sibling":"25b5e7b84bfdaf7764d4179af698e218f4b2858d756d4fd6c30f7dc8f562c1b9","side":"right"},{"sibling":"bbd9a20451913e8c7b910f616d5661d9b281a94af70d201ba50b3112d429521b","side":"right"},{"sibling":"85af80e45748c1e0da1e2f42d9d66da8996016888a034f20eb17ff0a73b69eab","side":"right"},{"sibling":"4575fde969d1d9a2984cc01a37ac8441238f74527d42874272dc5582dadebb4f","side":"left"},{"sibling":"f536de281672cbf0b583a3dc46faef1de2823b72bd9265c7b60e889131cc268d","side":"left"},{"sibling":"95b8b0f67237052a17c41fa8cbdce2b79bcb5aeeba3fdb239d4c4497e598115d","side":"right"},{"sibling":"c2f351f771cee329448890504d9436792ba482e50250ca9a19289311131f96c8","side":"right"},{"sibling":"c39bfb2e911ca37ae997690bfc04128ae32e6806ee1cb3908781a7e6685022a0","side":"right"},{"sibling":"a101b4c60ef6854ac3d750eef02d8e2e06c153284b5ecb7111302f97eb129797","side":"right"},{"sibling":"eae2a3de5cb35455ad60125e196cfadaba8a590c53146e95028469f53f70349c","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","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":268860,"merkle_root":"d098f25810d0569730b6c0e170d57f329a70359d483b47874b5f2fc51d23de65","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260701T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-01T05:38:05Z","sig_algorithm":"ed25519","signature":"64f37f0e3df0556baa55b924a736cab8005643fa0ab65b503f22407de30eab293e6e0bd62904270fda38d05084bb350c8c0d0aadb2c5a6bae5f1c54598e6d30c","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_361e774112c67f2b21fd2be39bda2abf880d7112cdb6183e8d46bef1ad55ac34"}}