{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IDKPDBGCZ7H2ZELLQVCFIG2FYK","short_pith_number":"pith:IDKPDBGC","schema_version":"1.0","canonical_sha256":"40d4f184c2cfcfac916b8544541b45c2bb216d6066566e97d9d804a9fc4dbe00","source":{"kind":"arxiv","id":"2110.03898","version":2},"attestation_state":"computed","paper":{"title":"Differentiable Programming of Isometric Tensor Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.str-el","cs.LG"],"primary_cat":"quant-ph","authors_text":"Chenhua Geng, Hong-Ye Hu, Yijian Zou","submitted_at":"2021-10-08T05:29:41Z","abstract_excerpt":"Differentiable programming is a new programming paradigm which enables large scale optimization through automatic calculation of gradients also known as auto-differentiation. This concept emerges from deep learning, and has also been generalized to tensor network optimizations. Here, we extend the differentiable programming to tensor networks with isometric constraints with applications to multiscale entanglement renormalization ansatz (MERA) and tensor network renormalization (TNR). By introducing several gradient-based optimization methods for the isometric tensor network and comparing with "},"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":"2110.03898","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2021-10-08T05:29:41Z","cross_cats_sorted":["cond-mat.str-el","cs.LG"],"title_canon_sha256":"d14755413ec692c8910c1f7da0ea99befa60ef64c1d22b020c57f1b051090c0a","abstract_canon_sha256":"65f9a61c050844b7aca8024bb7bea23cf14e54252c1069d7e32f1c717896c52c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:49.949145Z","signature_b64":"cpGzroFjj7Nutp+UnVfboYL8dPWY/sVntMdBBjjP8zoGBa/Ms0e5IudQKoEhgBqqAG5vHiAOBg3RlmH5pV2oCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40d4f184c2cfcfac916b8544541b45c2bb216d6066566e97d9d804a9fc4dbe00","last_reissued_at":"2026-07-05T03:52:49.948670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:49.948670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Programming of Isometric Tensor Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.str-el","cs.LG"],"primary_cat":"quant-ph","authors_text":"Chenhua Geng, Hong-Ye Hu, Yijian Zou","submitted_at":"2021-10-08T05:29:41Z","abstract_excerpt":"Differentiable programming is a new programming paradigm which enables large scale optimization through automatic calculation of gradients also known as auto-differentiation. This concept emerges from deep learning, and has also been generalized to tensor network optimizations. Here, we extend the differentiable programming to tensor networks with isometric constraints with applications to multiscale entanglement renormalization ansatz (MERA) and tensor network renormalization (TNR). By introducing several gradient-based optimization methods for the isometric tensor network and comparing with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03898","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.03898/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2110.03898","created_at":"2026-07-05T03:52:49.948730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03898v2","created_at":"2026-07-05T03:52:49.948730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03898","created_at":"2026-07-05T03:52:49.948730+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDKPDBGCZ7H2","created_at":"2026-07-05T03:52:49.948730+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDKPDBGCZ7H2ZELL","created_at":"2026-07-05T03:52:49.948730+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDKPDBGC","created_at":"2026-07-05T03:52:49.948730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00130","citing_title":"Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Parameter Compression of Deep Neural Networks","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19876","citing_title":"Scaling at Chiral Clock Criticality via Entanglement Renormalization","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IDKPDBGCZ7H2ZELLQVCFIG2FYK","json":"https://pith.science/pith/IDKPDBGCZ7H2ZELLQVCFIG2FYK.json","graph_json":"https://pith.science/api/pith-number/IDKPDBGCZ7H2ZELLQVCFIG2FYK/graph.json","events_json":"https://pith.science/api/pith-number/IDKPDBGCZ7H2ZELLQVCFIG2FYK/events.json","paper":"https://pith.science/paper/IDKPDBGC"},"agent_actions":{"view_html":"https://pith.science/pith/IDKPDBGCZ7H2ZELLQVCFIG2FYK","download_json":"https://pith.science/pith/IDKPDBGCZ7H2ZELLQVCFIG2FYK.json","view_paper":"https://pith.science/paper/IDKPDBGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03898&json=true","fetch_graph":"https://pith.science/api/pith-number/IDKPDBGCZ7H2ZELLQVCFIG2FYK/graph.json","fetch_events":"https://pith.science/api/pith-number/IDKPDBGCZ7H2ZELLQVCFIG2FYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDKPDBGCZ7H2ZELLQVCFIG2FYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDKPDBGCZ7H2ZELLQVCFIG2FYK/action/storage_attestation","attest_author":"https://pith.science/pith/IDKPDBGCZ7H2ZELLQVCFIG2FYK/action/author_attestation","sign_citation":"https://pith.science/pith/IDKPDBGCZ7H2ZELLQVCFIG2FYK/action/citation_signature","submit_replication":"https://pith.science/pith/IDKPDBGCZ7H2ZELLQVCFIG2FYK/action/replication_record"}},"created_at":"2026-07-05T03:52:49.948730+00:00","updated_at":"2026-07-05T03:52:49.948730+00:00"}