{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GVLB3NLMSMPNFL5BJMDJIBCGW4","short_pith_number":"pith:GVLB3NLM","schema_version":"1.0","canonical_sha256":"35561db56c931ed2afa14b06940446b707ed399c0b6fece0d31f60513036bd09","source":{"kind":"arxiv","id":"2008.10546","version":1},"attestation_state":"computed","paper":{"title":"SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chao Zhang, Jimeng Sun, Lingkai Kong","submitted_at":"2020-08-24T16:33:54Z","abstract_excerpt":"Uncertainty quantification is a fundamental yet unsolved problem for deep learning. The Bayesian framework provides a principled way of uncertainty estimation but is often not scalable to modern deep neural nets (DNNs) that have a large number of parameters. Non-Bayesian methods are simple to implement but often conflate different sources of uncertainties and require huge computing resources. We propose a new method for quantifying uncertainties of DNNs from a dynamical system perspective. The core of our method is to view DNN transformations as state evolution of a stochastic dynamical system"},"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":"2008.10546","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-24T16:33:54Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6b953679423c6b1bf362e12732cd069c0b13da1c785dc84935ae42487f7c0e4c","abstract_canon_sha256":"62c6cca266a1d9a24ce6692a05ebaecd2d13a8517992bf8f26f141558ed4142e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:29:25.405437Z","signature_b64":"0vBpYrMVYnrRxo6kYJ7IBPcSOLMG7OA2tdUyAsn3Tnnsq465X38WL8Xm0ZHFk3w9NlPlpd1aoTVz2DP8uVueAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35561db56c931ed2afa14b06940446b707ed399c0b6fece0d31f60513036bd09","last_reissued_at":"2026-07-05T01:29:25.404981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:29:25.404981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chao Zhang, Jimeng Sun, Lingkai Kong","submitted_at":"2020-08-24T16:33:54Z","abstract_excerpt":"Uncertainty quantification is a fundamental yet unsolved problem for deep learning. The Bayesian framework provides a principled way of uncertainty estimation but is often not scalable to modern deep neural nets (DNNs) that have a large number of parameters. Non-Bayesian methods are simple to implement but often conflate different sources of uncertainties and require huge computing resources. We propose a new method for quantifying uncertainties of DNNs from a dynamical system perspective. The core of our method is to view DNN transformations as state evolution of a stochastic dynamical system"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.10546","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/2008.10546/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":"2008.10546","created_at":"2026-07-05T01:29:25.405044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.10546v1","created_at":"2026-07-05T01:29:25.405044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.10546","created_at":"2026-07-05T01:29:25.405044+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVLB3NLMSMPN","created_at":"2026-07-05T01:29:25.405044+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVLB3NLMSMPNFL5B","created_at":"2026-07-05T01:29:25.405044+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVLB3NLM","created_at":"2026-07-05T01:29:25.405044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07330","citing_title":"Hypergraph Neural Stochastic Diffusion: An SDE Framework for Uncertainty Estimation","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.26061","citing_title":"Neuronal Stochastic Attention Circuit (NSAC) for Probabilistic Representation Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16078","citing_title":"A numerical study into neural network surrogate model performance for uncertainty propagation","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVLB3NLMSMPNFL5BJMDJIBCGW4","json":"https://pith.science/pith/GVLB3NLMSMPNFL5BJMDJIBCGW4.json","graph_json":"https://pith.science/api/pith-number/GVLB3NLMSMPNFL5BJMDJIBCGW4/graph.json","events_json":"https://pith.science/api/pith-number/GVLB3NLMSMPNFL5BJMDJIBCGW4/events.json","paper":"https://pith.science/paper/GVLB3NLM"},"agent_actions":{"view_html":"https://pith.science/pith/GVLB3NLMSMPNFL5BJMDJIBCGW4","download_json":"https://pith.science/pith/GVLB3NLMSMPNFL5BJMDJIBCGW4.json","view_paper":"https://pith.science/paper/GVLB3NLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.10546&json=true","fetch_graph":"https://pith.science/api/pith-number/GVLB3NLMSMPNFL5BJMDJIBCGW4/graph.json","fetch_events":"https://pith.science/api/pith-number/GVLB3NLMSMPNFL5BJMDJIBCGW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVLB3NLMSMPNFL5BJMDJIBCGW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVLB3NLMSMPNFL5BJMDJIBCGW4/action/storage_attestation","attest_author":"https://pith.science/pith/GVLB3NLMSMPNFL5BJMDJIBCGW4/action/author_attestation","sign_citation":"https://pith.science/pith/GVLB3NLMSMPNFL5BJMDJIBCGW4/action/citation_signature","submit_replication":"https://pith.science/pith/GVLB3NLMSMPNFL5BJMDJIBCGW4/action/replication_record"}},"created_at":"2026-07-05T01:29:25.405044+00:00","updated_at":"2026-07-05T01:29:25.405044+00:00"}