{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4W7ARWPFODZ26VGBKRTZVBNQCT","short_pith_number":"pith:4W7ARWPF","schema_version":"1.0","canonical_sha256":"e5be08d9e570f3af54c154679a85b014d6b78b3cfd4c6bd548a46451ad4da429","source":{"kind":"arxiv","id":"1711.03357","version":3},"attestation_state":"computed","paper":{"title":"Compact Neural Networks based on the Multiscale Entanglement Renormalization Ansatz","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","quant-ph"],"primary_cat":"cs.NE","authors_text":"Andrew G. Green, Andrew Hallam, Edward Grant, Simone Severini, Vid Stojevic","submitted_at":"2017-11-09T12:55:59Z","abstract_excerpt":"This paper demonstrates a method for tensorizing neural networks based upon an efficient way of approximating scale invariant quantum states, the Multi-scale Entanglement Renormalization Ansatz (MERA). We employ MERA as a replacement for the fully connected layers in a convolutional neural network and test this implementation on the CIFAR-10 and CIFAR-100 datasets. The proposed method outperforms factorization using tensor trains, providing greater compression for the same level of accuracy and greater accuracy for the same level of compression. We demonstrate MERA layers with 14000 times fewe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1711.03357","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-11-09T12:55:59Z","cross_cats_sorted":["cs.CV","quant-ph"],"title_canon_sha256":"0d0a3f989616bbf2fb166004b1b79c4508f225df238ecb438e4fad33b1b9ac3f","abstract_canon_sha256":"014a70bda97736dc74308271d52122f62815e56632d53c913607117ea6f9db31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:25.182648Z","signature_b64":"2oTmgcLV+gldWKtjOBfSHnxxvlDQhWgqKQXYl7KmFwdcUvdKLgupi2zISlpdXBBLr/6SpaDXdDBJBf3rCDhsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5be08d9e570f3af54c154679a85b014d6b78b3cfd4c6bd548a46451ad4da429","last_reissued_at":"2026-05-17T23:58:25.182027Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:25.182027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compact Neural Networks based on the Multiscale Entanglement Renormalization Ansatz","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","quant-ph"],"primary_cat":"cs.NE","authors_text":"Andrew G. Green, Andrew Hallam, Edward Grant, Simone Severini, Vid Stojevic","submitted_at":"2017-11-09T12:55:59Z","abstract_excerpt":"This paper demonstrates a method for tensorizing neural networks based upon an efficient way of approximating scale invariant quantum states, the Multi-scale Entanglement Renormalization Ansatz (MERA). We employ MERA as a replacement for the fully connected layers in a convolutional neural network and test this implementation on the CIFAR-10 and CIFAR-100 datasets. The proposed method outperforms factorization using tensor trains, providing greater compression for the same level of accuracy and greater accuracy for the same level of compression. We demonstrate MERA layers with 14000 times fewe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.03357","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1711.03357","created_at":"2026-05-17T23:58:25.182116+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.03357v3","created_at":"2026-05-17T23:58:25.182116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.03357","created_at":"2026-05-17T23:58:25.182116+00:00"},{"alias_kind":"pith_short_12","alias_value":"4W7ARWPFODZ2","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"4W7ARWPFODZ26VGB","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"4W7ARWPF","created_at":"2026-05-18T12:31:00.734936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2003.03485","citing_title":"Neural Operator: Graph Kernel Network for Partial Differential Equations","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4W7ARWPFODZ26VGBKRTZVBNQCT","json":"https://pith.science/pith/4W7ARWPFODZ26VGBKRTZVBNQCT.json","graph_json":"https://pith.science/api/pith-number/4W7ARWPFODZ26VGBKRTZVBNQCT/graph.json","events_json":"https://pith.science/api/pith-number/4W7ARWPFODZ26VGBKRTZVBNQCT/events.json","paper":"https://pith.science/paper/4W7ARWPF"},"agent_actions":{"view_html":"https://pith.science/pith/4W7ARWPFODZ26VGBKRTZVBNQCT","download_json":"https://pith.science/pith/4W7ARWPFODZ26VGBKRTZVBNQCT.json","view_paper":"https://pith.science/paper/4W7ARWPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.03357&json=true","fetch_graph":"https://pith.science/api/pith-number/4W7ARWPFODZ26VGBKRTZVBNQCT/graph.json","fetch_events":"https://pith.science/api/pith-number/4W7ARWPFODZ26VGBKRTZVBNQCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4W7ARWPFODZ26VGBKRTZVBNQCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4W7ARWPFODZ26VGBKRTZVBNQCT/action/storage_attestation","attest_author":"https://pith.science/pith/4W7ARWPFODZ26VGBKRTZVBNQCT/action/author_attestation","sign_citation":"https://pith.science/pith/4W7ARWPFODZ26VGBKRTZVBNQCT/action/citation_signature","submit_replication":"https://pith.science/pith/4W7ARWPFODZ26VGBKRTZVBNQCT/action/replication_record"}},"created_at":"2026-05-17T23:58:25.182116+00:00","updated_at":"2026-05-17T23:58:25.182116+00:00"}