{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:47DI2SJROIN6AQGCEK7ZH3TCA5","short_pith_number":"pith:47DI2SJR","schema_version":"1.0","canonical_sha256":"e7c68d4931721be040c222bf93ee620750f88bcd179a7568a8823c822fb22cfe","source":{"kind":"arxiv","id":"2412.16462","version":1},"attestation_state":"computed","paper":{"title":"Condensed Stein Variational Gradient Descent for Uncertainty Quantification of Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.comp-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cosmin Safta, Govinda Anantha Padmanabha, Nikolaos Bouklas, Reese E. Jones","submitted_at":"2024-12-21T03:28:07Z","abstract_excerpt":"We propose a Stein variational gradient descent method to concurrently sparsify, train, and provide uncertainty quantification of a complexly parameterized model such as a neural network. It employs a graph reconciliation and condensation process to reduce complexity and increase similarity in the Stein ensemble of parameterizations. Therefore, the proposed condensed Stein variational gradient (cSVGD) method provides uncertainty quantification on parameters, not just outputs. Furthermore, the parameter reduction speeds up the convergence of the Stein gradient descent as it reduces the combinat"},"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":"2412.16462","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-21T03:28:07Z","cross_cats_sorted":["physics.comp-ph","stat.ML"],"title_canon_sha256":"7aa4c0e4cf531155e75c06dedf333c37c33ad0a83ee281d26dee929db6876875","abstract_canon_sha256":"6d9f6889ca0af2028be00db0b8ac15e10fefd86aa5117aeb4e07745653480e21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:10.297401Z","signature_b64":"R9thVj4ne0UQo+7NhPCunzeyzs7bSPF+fXcpHr1qDSQ33WCWTAovbrHBg26kzRiOds6a9ss99wP0Xq8k59QeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7c68d4931721be040c222bf93ee620750f88bcd179a7568a8823c822fb22cfe","last_reissued_at":"2026-07-05T09:53:10.296760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:10.296760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Condensed Stein Variational Gradient Descent for Uncertainty Quantification of Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.comp-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cosmin Safta, Govinda Anantha Padmanabha, Nikolaos Bouklas, Reese E. Jones","submitted_at":"2024-12-21T03:28:07Z","abstract_excerpt":"We propose a Stein variational gradient descent method to concurrently sparsify, train, and provide uncertainty quantification of a complexly parameterized model such as a neural network. It employs a graph reconciliation and condensation process to reduce complexity and increase similarity in the Stein ensemble of parameterizations. Therefore, the proposed condensed Stein variational gradient (cSVGD) method provides uncertainty quantification on parameters, not just outputs. Furthermore, the parameter reduction speeds up the convergence of the Stein gradient descent as it reduces the combinat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16462","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/2412.16462/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":"2412.16462","created_at":"2026-07-05T09:53:10.296826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16462v1","created_at":"2026-07-05T09:53:10.296826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16462","created_at":"2026-07-05T09:53:10.296826+00:00"},{"alias_kind":"pith_short_12","alias_value":"47DI2SJROIN6","created_at":"2026-07-05T09:53:10.296826+00:00"},{"alias_kind":"pith_short_16","alias_value":"47DI2SJROIN6AQGC","created_at":"2026-07-05T09:53:10.296826+00:00"},{"alias_kind":"pith_short_8","alias_value":"47DI2SJR","created_at":"2026-07-05T09:53:10.296826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02991","citing_title":"Physics Augmented Machine Learning Discovery of Composition-Dependent Constitutive Laws for 3D Printed Digital Materials","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/47DI2SJROIN6AQGCEK7ZH3TCA5","json":"https://pith.science/pith/47DI2SJROIN6AQGCEK7ZH3TCA5.json","graph_json":"https://pith.science/api/pith-number/47DI2SJROIN6AQGCEK7ZH3TCA5/graph.json","events_json":"https://pith.science/api/pith-number/47DI2SJROIN6AQGCEK7ZH3TCA5/events.json","paper":"https://pith.science/paper/47DI2SJR"},"agent_actions":{"view_html":"https://pith.science/pith/47DI2SJROIN6AQGCEK7ZH3TCA5","download_json":"https://pith.science/pith/47DI2SJROIN6AQGCEK7ZH3TCA5.json","view_paper":"https://pith.science/paper/47DI2SJR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16462&json=true","fetch_graph":"https://pith.science/api/pith-number/47DI2SJROIN6AQGCEK7ZH3TCA5/graph.json","fetch_events":"https://pith.science/api/pith-number/47DI2SJROIN6AQGCEK7ZH3TCA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47DI2SJROIN6AQGCEK7ZH3TCA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47DI2SJROIN6AQGCEK7ZH3TCA5/action/storage_attestation","attest_author":"https://pith.science/pith/47DI2SJROIN6AQGCEK7ZH3TCA5/action/author_attestation","sign_citation":"https://pith.science/pith/47DI2SJROIN6AQGCEK7ZH3TCA5/action/citation_signature","submit_replication":"https://pith.science/pith/47DI2SJROIN6AQGCEK7ZH3TCA5/action/replication_record"}},"created_at":"2026-07-05T09:53:10.296826+00:00","updated_at":"2026-07-05T09:53:10.296826+00:00"}