{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ETTK32TXQA57FXMQVC2Q5OBCG6","short_pith_number":"pith:ETTK32TX","schema_version":"1.0","canonical_sha256":"24e6adea77803bf2dd90a8b50eb822378b7793e9fc1010557ca73982b356c83b","source":{"kind":"arxiv","id":"2102.06559","version":4},"attestation_state":"computed","paper":{"title":"Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"David Duvenaud, Ricky T.Q. Chen, Winnie Xu, Xuechen Li","submitted_at":"2021-02-12T14:48:58Z","abstract_excerpt":"We perform scalable approximate inference in continuous-depth Bayesian neural networks. In this model class, uncertainty about separate weights in each layer gives hidden units that follow a stochastic differential equation. We demonstrate gradient-based stochastic variational inference in this infinite-parameter setting, producing arbitrarily-flexible approximate posteriors. We also derive a novel gradient estimator that approaches zero variance as the approximate posterior over weights approaches the true posterior. This approach brings continuous-depth Bayesian neural nets to a competitive "},"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":"2102.06559","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-02-12T14:48:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2c4e6a5d1cc947634e34167cb4e57dfae7dc91435fd340a3a6b455bf1436c2d2","abstract_canon_sha256":"7079375a6490d5eedcefc4c6e5bdc5f1ad2622fbfe95447d5c7a0b259c47787c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:25.822687Z","signature_b64":"ilYN85EIqXpAJuxf/9cVdJFlqljh7H+9zp3k7jGkTNzontzdzGQw9TsBcUANt1HBwuJi+SiDsPe26XopfFVqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24e6adea77803bf2dd90a8b50eb822378b7793e9fc1010557ca73982b356c83b","last_reissued_at":"2026-07-05T03:52:25.822242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:25.822242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"David Duvenaud, Ricky T.Q. Chen, Winnie Xu, Xuechen Li","submitted_at":"2021-02-12T14:48:58Z","abstract_excerpt":"We perform scalable approximate inference in continuous-depth Bayesian neural networks. In this model class, uncertainty about separate weights in each layer gives hidden units that follow a stochastic differential equation. We demonstrate gradient-based stochastic variational inference in this infinite-parameter setting, producing arbitrarily-flexible approximate posteriors. We also derive a novel gradient estimator that approaches zero variance as the approximate posterior over weights approaches the true posterior. This approach brings continuous-depth Bayesian neural nets to a competitive "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.06559","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/2102.06559/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":"2102.06559","created_at":"2026-07-05T03:52:25.822302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.06559v4","created_at":"2026-07-05T03:52:25.822302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.06559","created_at":"2026-07-05T03:52:25.822302+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETTK32TXQA57","created_at":"2026-07-05T03:52:25.822302+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETTK32TXQA57FXMQ","created_at":"2026-07-05T03:52:25.822302+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETTK32TX","created_at":"2026-07-05T03:52:25.822302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.06190","citing_title":"Characteristic Sensitivity Ensembles for Inference of Hidden Dynamics from Marginal Observations","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ETTK32TXQA57FXMQVC2Q5OBCG6","json":"https://pith.science/pith/ETTK32TXQA57FXMQVC2Q5OBCG6.json","graph_json":"https://pith.science/api/pith-number/ETTK32TXQA57FXMQVC2Q5OBCG6/graph.json","events_json":"https://pith.science/api/pith-number/ETTK32TXQA57FXMQVC2Q5OBCG6/events.json","paper":"https://pith.science/paper/ETTK32TX"},"agent_actions":{"view_html":"https://pith.science/pith/ETTK32TXQA57FXMQVC2Q5OBCG6","download_json":"https://pith.science/pith/ETTK32TXQA57FXMQVC2Q5OBCG6.json","view_paper":"https://pith.science/paper/ETTK32TX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.06559&json=true","fetch_graph":"https://pith.science/api/pith-number/ETTK32TXQA57FXMQVC2Q5OBCG6/graph.json","fetch_events":"https://pith.science/api/pith-number/ETTK32TXQA57FXMQVC2Q5OBCG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETTK32TXQA57FXMQVC2Q5OBCG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETTK32TXQA57FXMQVC2Q5OBCG6/action/storage_attestation","attest_author":"https://pith.science/pith/ETTK32TXQA57FXMQVC2Q5OBCG6/action/author_attestation","sign_citation":"https://pith.science/pith/ETTK32TXQA57FXMQVC2Q5OBCG6/action/citation_signature","submit_replication":"https://pith.science/pith/ETTK32TXQA57FXMQVC2Q5OBCG6/action/replication_record"}},"created_at":"2026-07-05T03:52:25.822302+00:00","updated_at":"2026-07-05T03:52:25.822302+00:00"}