{"_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_a9a8c19d3c22f70bf1b1407c10aef1d76320cdd103fecaa519b00efbc9bc8dff","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_a9a8c19d3c22f70bf1b1407c10aef1d76320cdd103fecaa519b00efbc9bc8dff","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"e3b66da8d3d6e1113d2170f05d480f0e0154d082f4c333e3ff26bac374706408","published":"Tue, 02 Jun 2026 00:00:00 -0400","receipt_hash":"e3b66da8d3d6e1113d2170f05d480f0e0154d082f4c333e3ff26bac374706408","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":"e3b66da8d3d6e1113d2170f05d480f0e0154d082f4c333e3ff26bac374706408","observed_at":"2026-06-02T04:43:38.825628Z","parent_run_hash":"c2a9665c814770d56765bb764e6a6c7e4fa7d4e9708e157ca0f7440c89927d54","published":"Tue, 02 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:2606.00130v1 Announce Type: cross \nAbstract: We study Automatically Differentiable Nonlinear Tensor Networks (ADNTNs), a family of structured weight generators whose compact core tensors are trained end-to-end by reverse-mode automatic differentiation (AD). The approach can be viewed as a natural extension of low-rank adaptation and tensor factorisation: instead of using one low-rank matrix update, an ADNTN builds a large weight tensor through a hierarchy of small cores, nonlinear activations, and optional lateral mixing tensors. The paper focuses on three architectures: Tree Tensor Networks (TTNs), augmented TTNs (aTTNs) with boundary disentanglers, and Multi-scale Entanglement Renormalisation Ansatze (MERA).\n  The formulation supports nonlinear activations, task-aware objectives, batching, and hardware-aware execution schedules. At the same time, the paper keeps a clear distinction between \\emph{differentiating} a contraction program and making contraction free: AD does not rem","title":"Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Compression of Deep Neural Networks","url":"https://arxiv.org/abs/2606.00130","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.00130v1 Announce Type: cross \nAbstract: We study Automatically Differentiable Nonlinear Tensor Networks (ADNTNs), a family of structured weight generators whose compact core tensors are trained end-to-end by reverse-mode automatic differentiation (AD). The approach can be viewed as a natural extension of low-rank adaptation and tensor factorisation: instead of using one low-rank matrix update, an ADNTN builds a large weight tensor through a hierarchy of small cores, nonlinear activations, and optional lateral mixing tensors. The paper focuses on three architectures: Tree Tensor Networks (TTNs), augmented TTNs (aTTNs) with boundary disentanglers, and Multi-scale Entanglement Renormalisation Ansatze (MERA).\n  The formulation supports nonlinear activations, task-aware objectives, batching, and hardware-aware execution schedules. At the same time, the paper keeps a clear distinction between \\emph{differentiating} a contraction program and making contraction free: AD does not rem","title":"Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Compression of Deep Neural Networks","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-02T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.00130"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:d210568a34058c30538d5a3ed2072da5e560d7e55303c64a6c5e46d092b9b0a44810e9ca89836fe0baa2b75f1cbd76f272324e910f58ad8a5f45cfc251982f02","signer":"crovia.substrate","subject":{"observed_at":"2026-06-02T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.00130"},"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":"9f5c4e35aee5d8e00a1a680ae93ee96a02bb0920c84e9794720caa2571f07bf1","leaf_index":205400,"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":"0a691d6d734b28dfa6e8d34b757cc39d0156cd0a51d31caac7cce8cca3807d85","side":"right"},{"sibling":"5e3473b9e8d1dfa22abf9e1657de779f3fbd44abfabcf42316c17f3f3c3be5bf","side":"right"},{"sibling":"adfe9136b8c76edb620f4e8b5de972c471708ffc556ff32752cde35573a54f77","side":"right"},{"sibling":"ccb08fb586a5e857a00a52b246e2786ae4e1c19433dd7d473ab0736a51b41882","side":"left"},{"sibling":"1438618cb874613a5cbbce877b5393a9a3bac4d94f65ed88842c5fd322e46b8d","side":"left"},{"sibling":"dea496c0872bfcb89f959618cba20328719efc5ce596ca14f7b55604ffbc0fe6","side":"right"},{"sibling":"d72d8e425a897b82367a9bf8a5963bdb6c1fcaf2c58ea8751c6c3846ae5e1375","side":"left"},{"sibling":"5e8ef229952a4c6fda87dc1edd85b273121854e550efc4d376e399540dde01b3","side":"right"},{"sibling":"24ca17172d6e9b822b45054c27a7852aa461e97a906c83736cd55c5cf9874394","side":"right"},{"sibling":"6620a5008acf732cd3e57b0f2d1437293e88366c2e5b175ebeb7d796fc1e0c62","side":"left"},{"sibling":"a82575bfb494af7afcc13aaae718afa6f74030f09d71b02819ea25efd4186fc4","side":"right"},{"sibling":"e6adead8216db4cae92f0a036d53baebf30eed95a99c0d10758aa75bb7780f2f","side":"right"},{"sibling":"1acc2b7ff453ffd8c97b80ae4db5358780f0c6796874fd75403791dbe99f8cd7","side":"right"},{"sibling":"24d1bb4b13e0e46131b27b70a48e65fcf4e2e14b95e3bb83ade821e9df530f6b","side":"left"},{"sibling":"5f86f58c28b1a86ae06dfff4666bb9fba8866021a81fd4f1d200aa9af4722dfb","side":"right"},{"sibling":"f6cc6f94f6944ae21390afc65ac9e91dc31f84ee6e060681bba5ae08058294bd","side":"right"},{"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":206226,"merkle_root":"d2a6d32b13cbf343fb143b21a756d0533864ae6577a376ee84ba867b949207ec","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260602T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-02T05:37:46Z","sig_algorithm":"ed25519","signature":"abd9956cfb19dd1fb8142c46a220bac2514848c6abb0e79b8b0940206cc3ebb00894d4daaf9f786427f82a7cc12482e7fda79054ebb06bceaa9b4b97e23fb30e","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_a9a8c19d3c22f70bf1b1407c10aef1d76320cdd103fecaa519b00efbc9bc8dff"}}