{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JTQ7EXKWPEE2IDHI626IZCWI5H","short_pith_number":"pith:JTQ7EXKW","schema_version":"1.0","canonical_sha256":"4ce1f25d567909a40ce8f6bc8c8ac8e9e00009719d6019124b4429a595575efe","source":{"kind":"arxiv","id":"2003.06281","version":4},"attestation_state":"computed","paper":{"title":"BayesFlow: Learning complex stochastic models with invertible neural networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Voss, Lynton Ardizzone, Stefan T. Radev, Ulf K. Mertens, Ullrich K\\\"othe","submitted_at":"2020-03-13T13:39:31Z","abstract_excerpt":"Estimating the parameters of mathematical models is a common problem in almost all branches of science. However, this problem can prove notably difficult when processes and model descriptions become increasingly complex and an explicit likelihood function is not available. With this work, we propose a novel method for globally amortized Bayesian inference based on invertible neural networks which we call BayesFlow. The method uses simulation to learn a global estimator for the probabilistic mapping from observed data to underlying model parameters. A neural network pre-trained in this way can "},"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":"2003.06281","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2020-03-13T13:39:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9c3c324bc4890a1ef3dfdb1e3cd140867a4aa256a3075ddad658b96a8bddd457","abstract_canon_sha256":"8e9deb78c470fa33271846d70e2f066781506e86fd9b453c2b3ae69ff6efbc1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:59.292973Z","signature_b64":"dHdGu+UFsDJ88SMfejikO7t+ZLRi+e/3ORSZ0jR0tq2Dc8QyAaJvyYJaxECdh1e/vKZXX9jO4m0n6CEq2lPCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ce1f25d567909a40ce8f6bc8c8ac8e9e00009719d6019124b4429a595575efe","last_reissued_at":"2026-07-05T07:42:59.292450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:59.292450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BayesFlow: Learning complex stochastic models with invertible neural networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Voss, Lynton Ardizzone, Stefan T. Radev, Ulf K. Mertens, Ullrich K\\\"othe","submitted_at":"2020-03-13T13:39:31Z","abstract_excerpt":"Estimating the parameters of mathematical models is a common problem in almost all branches of science. However, this problem can prove notably difficult when processes and model descriptions become increasingly complex and an explicit likelihood function is not available. With this work, we propose a novel method for globally amortized Bayesian inference based on invertible neural networks which we call BayesFlow. The method uses simulation to learn a global estimator for the probabilistic mapping from observed data to underlying model parameters. A neural network pre-trained in this way can "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.06281","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2003.06281/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":"2003.06281","created_at":"2026-07-05T07:42:59.292516+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.06281v4","created_at":"2026-07-05T07:42:59.292516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.06281","created_at":"2026-07-05T07:42:59.292516+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTQ7EXKWPEE2","created_at":"2026-07-05T07:42:59.292516+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTQ7EXKWPEE2IDHI","created_at":"2026-07-05T07:42:59.292516+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTQ7EXKW","created_at":"2026-07-05T07:42:59.292516+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06252","citing_title":"A Convex Approximation Framework for Neural Likelihood-Based Bayesian Inverse Problems","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23791","citing_title":"One Generator, Any Process: LLM-Conditioning for the LHC","ref_index":193,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27499","citing_title":"GenSBI: Generative Methods for Simulation-Based Inference in JAX","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23791","citing_title":"One Generator, Any Process: LLM-Conditioning for the LHC","ref_index":189,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15407","citing_title":"Amortized Energy-Based Bayesian Inference","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26055","citing_title":"Extending Evidence Accumulation Models to Bounded Continuous Self-report Data","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26055","citing_title":"Extending Evidence Accumulation Models to Bounded Continuous Self-report Data","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTQ7EXKWPEE2IDHI626IZCWI5H","json":"https://pith.science/pith/JTQ7EXKWPEE2IDHI626IZCWI5H.json","graph_json":"https://pith.science/api/pith-number/JTQ7EXKWPEE2IDHI626IZCWI5H/graph.json","events_json":"https://pith.science/api/pith-number/JTQ7EXKWPEE2IDHI626IZCWI5H/events.json","paper":"https://pith.science/paper/JTQ7EXKW"},"agent_actions":{"view_html":"https://pith.science/pith/JTQ7EXKWPEE2IDHI626IZCWI5H","download_json":"https://pith.science/pith/JTQ7EXKWPEE2IDHI626IZCWI5H.json","view_paper":"https://pith.science/paper/JTQ7EXKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.06281&json=true","fetch_graph":"https://pith.science/api/pith-number/JTQ7EXKWPEE2IDHI626IZCWI5H/graph.json","fetch_events":"https://pith.science/api/pith-number/JTQ7EXKWPEE2IDHI626IZCWI5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTQ7EXKWPEE2IDHI626IZCWI5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTQ7EXKWPEE2IDHI626IZCWI5H/action/storage_attestation","attest_author":"https://pith.science/pith/JTQ7EXKWPEE2IDHI626IZCWI5H/action/author_attestation","sign_citation":"https://pith.science/pith/JTQ7EXKWPEE2IDHI626IZCWI5H/action/citation_signature","submit_replication":"https://pith.science/pith/JTQ7EXKWPEE2IDHI626IZCWI5H/action/replication_record"}},"created_at":"2026-07-05T07:42:59.292516+00:00","updated_at":"2026-07-05T07:42:59.292516+00:00"}