{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KOFJTV5IKQBDWIYABVX2AOFSBB","short_pith_number":"pith:KOFJTV5I","schema_version":"1.0","canonical_sha256":"538a99d7a854023b23000d6fa038b2085bd19a18559470dfe455642b4b125506","source":{"kind":"arxiv","id":"2101.03709","version":1},"attestation_state":"computed","paper":{"title":"Preconditioned training of normalizing flows for variational inference in inverse problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","physics.geo-ph"],"primary_cat":"stat.ML","authors_text":"Ali Siahkoohi, Felix J. Herrmann, Gabrio Rizzuti, Mathias Louboutin, Philipp A. Witte","submitted_at":"2021-01-11T05:35:36Z","abstract_excerpt":"Obtaining samples from the posterior distribution of inverse problems with expensive forward operators is challenging especially when the unknowns involve the strongly heterogeneous Earth. To meet these challenges, we propose a preconditioning scheme involving a conditional normalizing flow (NF) capable of sampling from a low-fidelity posterior distribution directly. This conditional NF is used to speed up the training of the high-fidelity objective involving minimization of the Kullback-Leibler divergence between the predicted and the desired high-fidelity posterior density for indirect measu"},"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":"2101.03709","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-01-11T05:35:36Z","cross_cats_sorted":["cs.LG","physics.geo-ph"],"title_canon_sha256":"627f455cac788e737c479043cfc6fd19014cfc62d8316da9bcc8147eca91b9b7","abstract_canon_sha256":"b6d32ecf232661eb5c678e71b9b760e6c112bf8b6a276b4055dcad1e1be1787b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:52.978514Z","signature_b64":"yJ7segOyzFmssNo6rQYAf76dKfN0X61ek+ALbi+PlV11uk3t2bVdE2s2EEctNC6qTElPRcTX4Q6+Mbu7uAFxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"538a99d7a854023b23000d6fa038b2085bd19a18559470dfe455642b4b125506","last_reissued_at":"2026-07-05T02:05:52.978162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:52.978162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preconditioned training of normalizing flows for variational inference in inverse problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","physics.geo-ph"],"primary_cat":"stat.ML","authors_text":"Ali Siahkoohi, Felix J. Herrmann, Gabrio Rizzuti, Mathias Louboutin, Philipp A. Witte","submitted_at":"2021-01-11T05:35:36Z","abstract_excerpt":"Obtaining samples from the posterior distribution of inverse problems with expensive forward operators is challenging especially when the unknowns involve the strongly heterogeneous Earth. To meet these challenges, we propose a preconditioning scheme involving a conditional normalizing flow (NF) capable of sampling from a low-fidelity posterior distribution directly. This conditional NF is used to speed up the training of the high-fidelity objective involving minimization of the Kullback-Leibler divergence between the predicted and the desired high-fidelity posterior density for indirect measu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.03709","kind":"arxiv","version":1},"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/2101.03709/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":"2101.03709","created_at":"2026-07-05T02:05:52.978223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.03709v1","created_at":"2026-07-05T02:05:52.978223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.03709","created_at":"2026-07-05T02:05:52.978223+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOFJTV5IKQBD","created_at":"2026-07-05T02:05:52.978223+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOFJTV5IKQBDWIYA","created_at":"2026-07-05T02:05:52.978223+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOFJTV5I","created_at":"2026-07-05T02:05:52.978223+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16353","citing_title":"A Semi-analytic but Biased Uncertainty Assessment Method using Sample Extensions, Analysed for Nonlinear Travel Time Tomography","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KOFJTV5IKQBDWIYABVX2AOFSBB","json":"https://pith.science/pith/KOFJTV5IKQBDWIYABVX2AOFSBB.json","graph_json":"https://pith.science/api/pith-number/KOFJTV5IKQBDWIYABVX2AOFSBB/graph.json","events_json":"https://pith.science/api/pith-number/KOFJTV5IKQBDWIYABVX2AOFSBB/events.json","paper":"https://pith.science/paper/KOFJTV5I"},"agent_actions":{"view_html":"https://pith.science/pith/KOFJTV5IKQBDWIYABVX2AOFSBB","download_json":"https://pith.science/pith/KOFJTV5IKQBDWIYABVX2AOFSBB.json","view_paper":"https://pith.science/paper/KOFJTV5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.03709&json=true","fetch_graph":"https://pith.science/api/pith-number/KOFJTV5IKQBDWIYABVX2AOFSBB/graph.json","fetch_events":"https://pith.science/api/pith-number/KOFJTV5IKQBDWIYABVX2AOFSBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOFJTV5IKQBDWIYABVX2AOFSBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOFJTV5IKQBDWIYABVX2AOFSBB/action/storage_attestation","attest_author":"https://pith.science/pith/KOFJTV5IKQBDWIYABVX2AOFSBB/action/author_attestation","sign_citation":"https://pith.science/pith/KOFJTV5IKQBDWIYABVX2AOFSBB/action/citation_signature","submit_replication":"https://pith.science/pith/KOFJTV5IKQBDWIYABVX2AOFSBB/action/replication_record"}},"created_at":"2026-07-05T02:05:52.978223+00:00","updated_at":"2026-07-05T02:05:52.978223+00:00"}