{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6KNPOMNLWPOQMFACE6WBFQKOWD","short_pith_number":"pith:6KNPOMNL","schema_version":"1.0","canonical_sha256":"f29af731abb3dd06140227ac12c14eb0f5ee8b09fd777fb9c4b93b33989d1e71","source":{"kind":"arxiv","id":"1802.02840","version":4},"attestation_state":"computed","paper":{"title":"Neural Network Renormalization Group","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cond-mat.stat-mech","authors_text":"Lei Wang, Shuo-Hui Li","submitted_at":"2018-02-08T13:16:01Z","abstract_excerpt":"We present a variational renormalization group (RG) approach using a deep generative model based on normalizing flows. The model performs hierarchical change-of-variables transformations from the physical space to a latent space with reduced mutual information. Conversely, the neural net directly maps independent Gaussian noises to physical configurations following the inverse RG flow. The model has an exact and tractable likelihood, which allows unbiased training and direct access to the renormalized energy function of the latent variables. To train the model, we employ probability density di"},"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":"1802.02840","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.stat-mech","submitted_at":"2018-02-08T13:16:01Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"88ed8469ca805dbcb31e9ed37c1d100f0d5d2770da7bebfa76e098e2e39b4919","abstract_canon_sha256":"81cc96b451c501764b36a5f2a766ffb396ea08f0ada53a24d87939d8d13c1d6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:21.670630Z","signature_b64":"29v9+IFrcJy1FXa/Ll3Ohy2rJ7aEhba5QFFv60j1H+YrLthWhDg3jmBe32LslBbyqLRYta3ky1vjyW0gb24CCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f29af731abb3dd06140227ac12c14eb0f5ee8b09fd777fb9c4b93b33989d1e71","last_reissued_at":"2026-05-17T23:57:21.670044Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:21.670044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Network Renormalization Group","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cond-mat.stat-mech","authors_text":"Lei Wang, Shuo-Hui Li","submitted_at":"2018-02-08T13:16:01Z","abstract_excerpt":"We present a variational renormalization group (RG) approach using a deep generative model based on normalizing flows. The model performs hierarchical change-of-variables transformations from the physical space to a latent space with reduced mutual information. Conversely, the neural net directly maps independent Gaussian noises to physical configurations following the inverse RG flow. The model has an exact and tractable likelihood, which allows unbiased training and direct access to the renormalized energy function of the latent variables. To train the model, we employ probability density di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.02840","kind":"arxiv","version":4},"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":"1802.02840","created_at":"2026-05-17T23:57:21.670132+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.02840v4","created_at":"2026-05-17T23:57:21.670132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.02840","created_at":"2026-05-17T23:57:21.670132+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KNPOMNLWPOQ","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KNPOMNLWPOQMFAC","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KNPOMNL","created_at":"2026-05-18T12:32:08.215937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09769","citing_title":"Differentiable free energy surface: a variational approach to directly observing rare events using generative deep-learning models","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6KNPOMNLWPOQMFACE6WBFQKOWD","json":"https://pith.science/pith/6KNPOMNLWPOQMFACE6WBFQKOWD.json","graph_json":"https://pith.science/api/pith-number/6KNPOMNLWPOQMFACE6WBFQKOWD/graph.json","events_json":"https://pith.science/api/pith-number/6KNPOMNLWPOQMFACE6WBFQKOWD/events.json","paper":"https://pith.science/paper/6KNPOMNL"},"agent_actions":{"view_html":"https://pith.science/pith/6KNPOMNLWPOQMFACE6WBFQKOWD","download_json":"https://pith.science/pith/6KNPOMNLWPOQMFACE6WBFQKOWD.json","view_paper":"https://pith.science/paper/6KNPOMNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.02840&json=true","fetch_graph":"https://pith.science/api/pith-number/6KNPOMNLWPOQMFACE6WBFQKOWD/graph.json","fetch_events":"https://pith.science/api/pith-number/6KNPOMNLWPOQMFACE6WBFQKOWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KNPOMNLWPOQMFACE6WBFQKOWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KNPOMNLWPOQMFACE6WBFQKOWD/action/storage_attestation","attest_author":"https://pith.science/pith/6KNPOMNLWPOQMFACE6WBFQKOWD/action/author_attestation","sign_citation":"https://pith.science/pith/6KNPOMNLWPOQMFACE6WBFQKOWD/action/citation_signature","submit_replication":"https://pith.science/pith/6KNPOMNLWPOQMFACE6WBFQKOWD/action/replication_record"}},"created_at":"2026-05-17T23:57:21.670132+00:00","updated_at":"2026-05-17T23:57:21.670132+00:00"}