{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XUA4OL4R4OTRA5GL2YUPZM527G","short_pith_number":"pith:XUA4OL4R","schema_version":"1.0","canonical_sha256":"bd01c72f91e3a71074cbd628fcb3baf9be21d396139b5fcfeccad6afae98ed49","source":{"kind":"arxiv","id":"2305.20004","version":3},"attestation_state":"computed","paper":{"title":"Learning to solve Bayesian inverse problems: An amortized variational inference approach using Gaussian and Flow guides","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","physics.data-an"],"primary_cat":"stat.ML","authors_text":"Ilias Bilionis, Sharmila Karumuri","submitted_at":"2023-05-31T16:25:07Z","abstract_excerpt":"Inverse problems, i.e., estimating parameters of physical models from experimental data, are ubiquitous in science and engineering. The Bayesian formulation is the gold standard because it alleviates ill-posedness issues and quantifies epistemic uncertainty. Since analytical posteriors are not typically available, one resorts to Markov chain Monte Carlo sampling or approximate variational inference. However, inference needs to be rerun from scratch for each new set of data. This drawback limits the applicability of the Bayesian formulation to real-time settings, e.g., health monitoring of engi"},"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":"2305.20004","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-31T16:25:07Z","cross_cats_sorted":["cs.LG","physics.data-an"],"title_canon_sha256":"8e4fa09ba89497e8429791e1ee96dec94adcb2b8d9ebc6bacf5538586166e428","abstract_canon_sha256":"68530e484d8d9d7be3ed1a19e7f8cea0ec70d2174511e28023ac5b9bdaefdb24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:09.296762Z","signature_b64":"4FEIhFGBNGxWfn/wo3SaPCFhwQlh5v5QXPI9VIv8NojoxQuv06A7Sgq2v+Yi1uHDe05Qrmnvnn04vSY0ClGlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd01c72f91e3a71074cbd628fcb3baf9be21d396139b5fcfeccad6afae98ed49","last_reissued_at":"2026-07-05T08:23:09.296287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:09.296287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to solve Bayesian inverse problems: An amortized variational inference approach using Gaussian and Flow guides","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","physics.data-an"],"primary_cat":"stat.ML","authors_text":"Ilias Bilionis, Sharmila Karumuri","submitted_at":"2023-05-31T16:25:07Z","abstract_excerpt":"Inverse problems, i.e., estimating parameters of physical models from experimental data, are ubiquitous in science and engineering. The Bayesian formulation is the gold standard because it alleviates ill-posedness issues and quantifies epistemic uncertainty. Since analytical posteriors are not typically available, one resorts to Markov chain Monte Carlo sampling or approximate variational inference. However, inference needs to be rerun from scratch for each new set of data. This drawback limits the applicability of the Bayesian formulation to real-time settings, e.g., health monitoring of engi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.20004","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/2305.20004/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":"2305.20004","created_at":"2026-07-05T08:23:09.296349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.20004v3","created_at":"2026-07-05T08:23:09.296349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.20004","created_at":"2026-07-05T08:23:09.296349+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUA4OL4R4OTR","created_at":"2026-07-05T08:23:09.296349+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUA4OL4R4OTRA5GL","created_at":"2026-07-05T08:23:09.296349+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUA4OL4R","created_at":"2026-07-05T08:23:09.296349+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04565","citing_title":"Solving High-dimensional Inverse Problems Using Amortized Likelihood-free Inference with Noisy and Incomplete Data","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XUA4OL4R4OTRA5GL2YUPZM527G","json":"https://pith.science/pith/XUA4OL4R4OTRA5GL2YUPZM527G.json","graph_json":"https://pith.science/api/pith-number/XUA4OL4R4OTRA5GL2YUPZM527G/graph.json","events_json":"https://pith.science/api/pith-number/XUA4OL4R4OTRA5GL2YUPZM527G/events.json","paper":"https://pith.science/paper/XUA4OL4R"},"agent_actions":{"view_html":"https://pith.science/pith/XUA4OL4R4OTRA5GL2YUPZM527G","download_json":"https://pith.science/pith/XUA4OL4R4OTRA5GL2YUPZM527G.json","view_paper":"https://pith.science/paper/XUA4OL4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.20004&json=true","fetch_graph":"https://pith.science/api/pith-number/XUA4OL4R4OTRA5GL2YUPZM527G/graph.json","fetch_events":"https://pith.science/api/pith-number/XUA4OL4R4OTRA5GL2YUPZM527G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUA4OL4R4OTRA5GL2YUPZM527G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUA4OL4R4OTRA5GL2YUPZM527G/action/storage_attestation","attest_author":"https://pith.science/pith/XUA4OL4R4OTRA5GL2YUPZM527G/action/author_attestation","sign_citation":"https://pith.science/pith/XUA4OL4R4OTRA5GL2YUPZM527G/action/citation_signature","submit_replication":"https://pith.science/pith/XUA4OL4R4OTRA5GL2YUPZM527G/action/replication_record"}},"created_at":"2026-07-05T08:23:09.296349+00:00","updated_at":"2026-07-05T08:23:09.296349+00:00"}