{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IXTLG7GI43XSXXA6HY64AKK7OK","short_pith_number":"pith:IXTLG7GI","schema_version":"1.0","canonical_sha256":"45e6b37cc8e6ef2bdc1e3e3dc0295f729aac6fe3354a2e5394226ee36c7b6a2e","source":{"kind":"arxiv","id":"2012.13196","version":3},"attestation_state":"computed","paper":{"title":"RBM-Flow and D-Flow: Invertible Flows with Discrete Energy Base Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel O'Connor, Walter Vinci","submitted_at":"2020-12-24T11:05:27Z","abstract_excerpt":"Efficient sampling of complex data distributions can be achieved using trained invertible flows (IF), where the model distribution is generated by pushing a simple base distribution through multiple non-linear bijective transformations. However, the iterative nature of the transformations in IFs can limit the approximation to the target distribution. In this paper we seek to mitigate this by implementing RBM-Flow, an IF model whose base distribution is a Restricted Boltzmann Machine (RBM) with a continuous smoothing applied. We show that by using RBM-Flow we are able to improve the quality of "},"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":"2012.13196","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-24T11:05:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2e576f46a9754caa97b8a64cf3ec2109667dccd5d1d9290ff94fa71311dec448","abstract_canon_sha256":"cd1bd865dd7010d8b47f2c0d36b488e2e2fb44a95b81d9f8c5945a7d9bb65a18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:55.250998Z","signature_b64":"gJAKxhAZ18KHfP66M3Cx1MrJtBpXtL+TcCWw1M1SJQG1d+hT+o6jigArfQfm5WoBQARnqKGoYK5MCz2rzMaLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45e6b37cc8e6ef2bdc1e3e3dc0295f729aac6fe3354a2e5394226ee36c7b6a2e","last_reissued_at":"2026-07-05T02:56:55.250562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:55.250562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RBM-Flow and D-Flow: Invertible Flows with Discrete Energy Base Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel O'Connor, Walter Vinci","submitted_at":"2020-12-24T11:05:27Z","abstract_excerpt":"Efficient sampling of complex data distributions can be achieved using trained invertible flows (IF), where the model distribution is generated by pushing a simple base distribution through multiple non-linear bijective transformations. However, the iterative nature of the transformations in IFs can limit the approximation to the target distribution. In this paper we seek to mitigate this by implementing RBM-Flow, an IF model whose base distribution is a Restricted Boltzmann Machine (RBM) with a continuous smoothing applied. We show that by using RBM-Flow we are able to improve the quality of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.13196","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.13196/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":"2012.13196","created_at":"2026-07-05T02:56:55.250617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.13196v3","created_at":"2026-07-05T02:56:55.250617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.13196","created_at":"2026-07-05T02:56:55.250617+00:00"},{"alias_kind":"pith_short_12","alias_value":"IXTLG7GI43XS","created_at":"2026-07-05T02:56:55.250617+00:00"},{"alias_kind":"pith_short_16","alias_value":"IXTLG7GI43XSXXA6","created_at":"2026-07-05T02:56:55.250617+00:00"},{"alias_kind":"pith_short_8","alias_value":"IXTLG7GI","created_at":"2026-07-05T02:56:55.250617+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.10406","citing_title":"How to Build a Quantum Supercomputer: Scaling from Hundreds to Millions of Qubits","ref_index":104,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IXTLG7GI43XSXXA6HY64AKK7OK","json":"https://pith.science/pith/IXTLG7GI43XSXXA6HY64AKK7OK.json","graph_json":"https://pith.science/api/pith-number/IXTLG7GI43XSXXA6HY64AKK7OK/graph.json","events_json":"https://pith.science/api/pith-number/IXTLG7GI43XSXXA6HY64AKK7OK/events.json","paper":"https://pith.science/paper/IXTLG7GI"},"agent_actions":{"view_html":"https://pith.science/pith/IXTLG7GI43XSXXA6HY64AKK7OK","download_json":"https://pith.science/pith/IXTLG7GI43XSXXA6HY64AKK7OK.json","view_paper":"https://pith.science/paper/IXTLG7GI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.13196&json=true","fetch_graph":"https://pith.science/api/pith-number/IXTLG7GI43XSXXA6HY64AKK7OK/graph.json","fetch_events":"https://pith.science/api/pith-number/IXTLG7GI43XSXXA6HY64AKK7OK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IXTLG7GI43XSXXA6HY64AKK7OK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IXTLG7GI43XSXXA6HY64AKK7OK/action/storage_attestation","attest_author":"https://pith.science/pith/IXTLG7GI43XSXXA6HY64AKK7OK/action/author_attestation","sign_citation":"https://pith.science/pith/IXTLG7GI43XSXXA6HY64AKK7OK/action/citation_signature","submit_replication":"https://pith.science/pith/IXTLG7GI43XSXXA6HY64AKK7OK/action/replication_record"}},"created_at":"2026-07-05T02:56:55.250617+00:00","updated_at":"2026-07-05T02:56:55.250617+00:00"}