{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZOFPANHDSOUOPBUPZNUD3UVVCX","short_pith_number":"pith:ZOFPANHD","schema_version":"1.0","canonical_sha256":"cb8af034e393a8e7868fcb683dd2b515f5e13679ae5e97ddfe4f20e0311a265c","source":{"kind":"arxiv","id":"2002.06707","version":3},"attestation_state":"computed","paper":{"title":"Stochastic Normalizing Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.chem-ph","physics.data-an"],"primary_cat":"stat.ML","authors_text":"Frank No\\'e, Hao Wu, Jonas K\\\"ohler","submitted_at":"2020-02-16T23:29:32Z","abstract_excerpt":"The sampling of probability distributions specified up to a normalization constant is an important problem in both machine learning and statistical mechanics. While classical stochastic sampling methods such as Markov Chain Monte Carlo (MCMC) or Langevin Dynamics (LD) can suffer from slow mixing times there is a growing interest in using normalizing flows in order to learn the transformation of a simple prior distribution to the given target distribution. Here we propose a generalized and combined approach to sample target densities: Stochastic Normalizing Flows (SNF) -- an arbitrary sequence "},"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":"2002.06707","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-16T23:29:32Z","cross_cats_sorted":["cs.LG","physics.chem-ph","physics.data-an"],"title_canon_sha256":"60227d7770124b26ad3a7059be6288b0df786a1f1516710815fd9cbb52ba2c27","abstract_canon_sha256":"dafa5c453cabd21891001f2757c12ec866eed106dc48b6fa74178c1940b467cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:46:00.209445Z","signature_b64":"2pJNZnbQK4fLhVIISYDn93dV/GWbFJ+E9QlLpUtDWFdvg8bn45hJp7Aq3qenwMM547aqBVDcbLY7Se1K7BIQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb8af034e393a8e7868fcb683dd2b515f5e13679ae5e97ddfe4f20e0311a265c","last_reissued_at":"2026-07-05T01:46:00.208948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:46:00.208948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Normalizing Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.chem-ph","physics.data-an"],"primary_cat":"stat.ML","authors_text":"Frank No\\'e, Hao Wu, Jonas K\\\"ohler","submitted_at":"2020-02-16T23:29:32Z","abstract_excerpt":"The sampling of probability distributions specified up to a normalization constant is an important problem in both machine learning and statistical mechanics. While classical stochastic sampling methods such as Markov Chain Monte Carlo (MCMC) or Langevin Dynamics (LD) can suffer from slow mixing times there is a growing interest in using normalizing flows in order to learn the transformation of a simple prior distribution to the given target distribution. Here we propose a generalized and combined approach to sample target densities: Stochastic Normalizing Flows (SNF) -- an arbitrary sequence "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06707","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/2002.06707/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":"2002.06707","created_at":"2026-07-05T01:46:00.209004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.06707v3","created_at":"2026-07-05T01:46:00.209004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06707","created_at":"2026-07-05T01:46:00.209004+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOFPANHDSOUO","created_at":"2026-07-05T01:46:00.209004+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOFPANHDSOUOPBUP","created_at":"2026-07-05T01:46:00.209004+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOFPANHD","created_at":"2026-07-05T01:46:00.209004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.19520","citing_title":"Intrinsic Width of the Flux Tube as a tool to explore confining mechanisms in Lattice Gauge Theories","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25704","citing_title":"Scaling flow-based approaches for topology sampling in $\\mathrm{SU}(3)$ gauge theory","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2006.11239","citing_title":"Denoising Diffusion Probabilistic Models","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZOFPANHDSOUOPBUPZNUD3UVVCX","json":"https://pith.science/pith/ZOFPANHDSOUOPBUPZNUD3UVVCX.json","graph_json":"https://pith.science/api/pith-number/ZOFPANHDSOUOPBUPZNUD3UVVCX/graph.json","events_json":"https://pith.science/api/pith-number/ZOFPANHDSOUOPBUPZNUD3UVVCX/events.json","paper":"https://pith.science/paper/ZOFPANHD"},"agent_actions":{"view_html":"https://pith.science/pith/ZOFPANHDSOUOPBUPZNUD3UVVCX","download_json":"https://pith.science/pith/ZOFPANHDSOUOPBUPZNUD3UVVCX.json","view_paper":"https://pith.science/paper/ZOFPANHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.06707&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOFPANHDSOUOPBUPZNUD3UVVCX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOFPANHDSOUOPBUPZNUD3UVVCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOFPANHDSOUOPBUPZNUD3UVVCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOFPANHDSOUOPBUPZNUD3UVVCX/action/storage_attestation","attest_author":"https://pith.science/pith/ZOFPANHDSOUOPBUPZNUD3UVVCX/action/author_attestation","sign_citation":"https://pith.science/pith/ZOFPANHDSOUOPBUPZNUD3UVVCX/action/citation_signature","submit_replication":"https://pith.science/pith/ZOFPANHDSOUOPBUPZNUD3UVVCX/action/replication_record"}},"created_at":"2026-07-05T01:46:00.209004+00:00","updated_at":"2026-07-05T01:46:00.209004+00:00"}