{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RGUYQ4RBRRA4HRBNLVEUIMHIZG","short_pith_number":"pith:RGUYQ4RB","schema_version":"1.0","canonical_sha256":"89a98872218c41c3c42d5d494430e8c981e6746c5f677fe1f907a514d26ecf64","source":{"kind":"arxiv","id":"2110.15828","version":2},"attestation_state":"computed","paper":{"title":"Resampling Base Distributions of Normalizing Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Bernhard Sch\\\"olkopf, Jos\\'e Miguel Hern\\'andez-Lobato, Vincent Stimper","submitted_at":"2021-10-29T14:44:44Z","abstract_excerpt":"Normalizing flows are a popular class of models for approximating probability distributions. However, their invertible nature limits their ability to model target distributions whose support have a complex topological structure, such as Boltzmann distributions. Several procedures have been proposed to solve this problem but many of them sacrifice invertibility and, thereby, tractability of the log-likelihood as well as other desirable properties. To address these limitations, we introduce a base distribution for normalizing flows based on learned rejection sampling, allowing the resulting norm"},"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":"2110.15828","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T14:44:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d6429ad07f51764be146399cfc565f7ead797b899ee1be9f9dfb2d024b1fabca","abstract_canon_sha256":"581fe91e8dc4ca7641d6c1990bdf1f6b23593f2d726a2dd96df9b866faca44aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:41.748863Z","signature_b64":"QfCX5kCpD1vA0+gjmawH0z5C6eD0aOCE1V9Veh1Hn2/XfLH9RGsEV3gwHihvgnJd+gQ2GeZodKC8KMuzDHgQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89a98872218c41c3c42d5d494430e8c981e6746c5f677fe1f907a514d26ecf64","last_reissued_at":"2026-07-05T03:59:41.748384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:41.748384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Resampling Base Distributions of Normalizing Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Bernhard Sch\\\"olkopf, Jos\\'e Miguel Hern\\'andez-Lobato, Vincent Stimper","submitted_at":"2021-10-29T14:44:44Z","abstract_excerpt":"Normalizing flows are a popular class of models for approximating probability distributions. However, their invertible nature limits their ability to model target distributions whose support have a complex topological structure, such as Boltzmann distributions. Several procedures have been proposed to solve this problem but many of them sacrifice invertibility and, thereby, tractability of the log-likelihood as well as other desirable properties. To address these limitations, we introduce a base distribution for normalizing flows based on learned rejection sampling, allowing the resulting norm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15828","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/2110.15828/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":"2110.15828","created_at":"2026-07-05T03:59:41.748444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.15828v2","created_at":"2026-07-05T03:59:41.748444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15828","created_at":"2026-07-05T03:59:41.748444+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGUYQ4RBRRA4","created_at":"2026-07-05T03:59:41.748444+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGUYQ4RBRRA4HRBN","created_at":"2026-07-05T03:59:41.748444+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGUYQ4RB","created_at":"2026-07-05T03:59:41.748444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21220","citing_title":"Wavelet Flow For Extragalactic Foreground Simulations","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RGUYQ4RBRRA4HRBNLVEUIMHIZG","json":"https://pith.science/pith/RGUYQ4RBRRA4HRBNLVEUIMHIZG.json","graph_json":"https://pith.science/api/pith-number/RGUYQ4RBRRA4HRBNLVEUIMHIZG/graph.json","events_json":"https://pith.science/api/pith-number/RGUYQ4RBRRA4HRBNLVEUIMHIZG/events.json","paper":"https://pith.science/paper/RGUYQ4RB"},"agent_actions":{"view_html":"https://pith.science/pith/RGUYQ4RBRRA4HRBNLVEUIMHIZG","download_json":"https://pith.science/pith/RGUYQ4RBRRA4HRBNLVEUIMHIZG.json","view_paper":"https://pith.science/paper/RGUYQ4RB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.15828&json=true","fetch_graph":"https://pith.science/api/pith-number/RGUYQ4RBRRA4HRBNLVEUIMHIZG/graph.json","fetch_events":"https://pith.science/api/pith-number/RGUYQ4RBRRA4HRBNLVEUIMHIZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGUYQ4RBRRA4HRBNLVEUIMHIZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGUYQ4RBRRA4HRBNLVEUIMHIZG/action/storage_attestation","attest_author":"https://pith.science/pith/RGUYQ4RBRRA4HRBNLVEUIMHIZG/action/author_attestation","sign_citation":"https://pith.science/pith/RGUYQ4RBRRA4HRBNLVEUIMHIZG/action/citation_signature","submit_replication":"https://pith.science/pith/RGUYQ4RBRRA4HRBNLVEUIMHIZG/action/replication_record"}},"created_at":"2026-07-05T03:59:41.748444+00:00","updated_at":"2026-07-05T03:59:41.748444+00:00"}