{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MMIGJ4P4JARQPUTT5QFUR2YBXT","short_pith_number":"pith:MMIGJ4P4","schema_version":"1.0","canonical_sha256":"631064f1fc482307d273ec0b48eb01bcf12fe2de76fa08b17f463d365e9b76bd","source":{"kind":"arxiv","id":"1906.06329","version":1},"attestation_state":"computed","paper":{"title":"TensorNetwork for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.str-el","cs.CV","physics.comp-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jack Hidary, Stavros Efthymiou, Stefan Leichenauer","submitted_at":"2019-06-07T17:58:31Z","abstract_excerpt":"We demonstrate the use of tensor networks for image classification with the TensorNetwork open source library. We explain in detail the encoding of image data into a matrix product state form, and describe how to contract the network in a way that is parallelizable and well-suited to automatic gradients for optimization. Applying the technique to the MNIST and Fashion-MNIST datasets we find out-of-the-box performance of 98% and 88% accuracy, respectively, using the same tensor network architecture. The TensorNetwork library allows us to seamlessly move from CPU to GPU hardware, and we see a fa"},"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":"1906.06329","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T17:58:31Z","cross_cats_sorted":["cond-mat.str-el","cs.CV","physics.comp-ph","stat.ML"],"title_canon_sha256":"3188ec1dcf998c258d8806e9af9a60fb3c3066bede1815ceeb8d2307c54de3a9","abstract_canon_sha256":"714d664239d46f8335fb706d23475cdc7d59912b94f26768e305331ab4775791"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:19.003416Z","signature_b64":"wnJekBxFvzzJguBtH50juDBvTL0Bw0lGcCUE6ohlZjw8FTcoQYn2MONPIrcOiAbrivyDPCDxFozZd6Z/AGHZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"631064f1fc482307d273ec0b48eb01bcf12fe2de76fa08b17f463d365e9b76bd","last_reissued_at":"2026-05-17T23:43:19.002764Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:19.002764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TensorNetwork for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.str-el","cs.CV","physics.comp-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jack Hidary, Stavros Efthymiou, Stefan Leichenauer","submitted_at":"2019-06-07T17:58:31Z","abstract_excerpt":"We demonstrate the use of tensor networks for image classification with the TensorNetwork open source library. We explain in detail the encoding of image data into a matrix product state form, and describe how to contract the network in a way that is parallelizable and well-suited to automatic gradients for optimization. Applying the technique to the MNIST and Fashion-MNIST datasets we find out-of-the-box performance of 98% and 88% accuracy, respectively, using the same tensor network architecture. The TensorNetwork library allows us to seamlessly move from CPU to GPU hardware, and we see a fa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06329","kind":"arxiv","version":1},"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":"1906.06329","created_at":"2026-05-17T23:43:19.002835+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.06329v1","created_at":"2026-05-17T23:43:19.002835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06329","created_at":"2026-05-17T23:43:19.002835+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMIGJ4P4JARQ","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMIGJ4P4JARQPUTT","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMIGJ4P4","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.12030","citing_title":"TensorNetwork on TensorFlow: Entanglement Renormalization for quantum critical lattice models","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08072","citing_title":"Tensor-Augmented Convolutional Neural Networks: Enhancing Expressivity with Generic Tensor Kernels","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06265","citing_title":"SMT-AD: a scalable quantum-inspired anomaly detection approach","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MMIGJ4P4JARQPUTT5QFUR2YBXT","json":"https://pith.science/pith/MMIGJ4P4JARQPUTT5QFUR2YBXT.json","graph_json":"https://pith.science/api/pith-number/MMIGJ4P4JARQPUTT5QFUR2YBXT/graph.json","events_json":"https://pith.science/api/pith-number/MMIGJ4P4JARQPUTT5QFUR2YBXT/events.json","paper":"https://pith.science/paper/MMIGJ4P4"},"agent_actions":{"view_html":"https://pith.science/pith/MMIGJ4P4JARQPUTT5QFUR2YBXT","download_json":"https://pith.science/pith/MMIGJ4P4JARQPUTT5QFUR2YBXT.json","view_paper":"https://pith.science/paper/MMIGJ4P4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.06329&json=true","fetch_graph":"https://pith.science/api/pith-number/MMIGJ4P4JARQPUTT5QFUR2YBXT/graph.json","fetch_events":"https://pith.science/api/pith-number/MMIGJ4P4JARQPUTT5QFUR2YBXT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMIGJ4P4JARQPUTT5QFUR2YBXT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMIGJ4P4JARQPUTT5QFUR2YBXT/action/storage_attestation","attest_author":"https://pith.science/pith/MMIGJ4P4JARQPUTT5QFUR2YBXT/action/author_attestation","sign_citation":"https://pith.science/pith/MMIGJ4P4JARQPUTT5QFUR2YBXT/action/citation_signature","submit_replication":"https://pith.science/pith/MMIGJ4P4JARQPUTT5QFUR2YBXT/action/replication_record"}},"created_at":"2026-05-17T23:43:19.002835+00:00","updated_at":"2026-05-17T23:43:19.002835+00:00"}