{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QKVT4RKO4R3P4F2V4W2VOTJH7Y","short_pith_number":"pith:QKVT4RKO","schema_version":"1.0","canonical_sha256":"82ab3e454ee476fe1755e5b5574d27fe3b025d4874ab9ba054042b612deb036b","source":{"kind":"arxiv","id":"2111.05953","version":1},"attestation_state":"computed","paper":{"title":"Robust Learning via Ensemble Density Propagation in Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","math.PR"],"primary_cat":"cs.LG","authors_text":"Dimah Dera, Ghulam Rasool, Giuseppina Carannante, Lyudmila Mihaylova, Nidhal C. Bouaynaya","submitted_at":"2021-11-10T21:26:08Z","abstract_excerpt":"Learning in uncertain, noisy, or adversarial environments is a challenging task for deep neural networks (DNNs). We propose a new theoretically grounded and efficient approach for robust learning that builds upon Bayesian estimation and Variational Inference. We formulate the problem of density propagation through layers of a DNN and solve it using an Ensemble Density Propagation (EnDP) scheme. The EnDP approach allows us to propagate moments of the variational probability distribution across the layers of a Bayesian DNN, enabling the estimation of the mean and covariance of the predictive dis"},"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":"2111.05953","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-10T21:26:08Z","cross_cats_sorted":["cs.AI","cs.CV","math.PR"],"title_canon_sha256":"078eb5af997248e159e03fddcac57f9cfb1371c927e93064aa208259a93f414e","abstract_canon_sha256":"389c7600789e24cfa6b4fcc2d763a84ad5bea5660515dd139428ee4097627082"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:56.528957Z","signature_b64":"1qw420ENJynBijdr6SeVyZrw7V6AagxQUGrnGyWFMOtsC5UwIgDzRcPtabjL+poy5n0w9CbmcLs5OyAUYmIMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82ab3e454ee476fe1755e5b5574d27fe3b025d4874ab9ba054042b612deb036b","last_reissued_at":"2026-07-05T03:30:56.528510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:56.528510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Learning via Ensemble Density Propagation in Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","math.PR"],"primary_cat":"cs.LG","authors_text":"Dimah Dera, Ghulam Rasool, Giuseppina Carannante, Lyudmila Mihaylova, Nidhal C. Bouaynaya","submitted_at":"2021-11-10T21:26:08Z","abstract_excerpt":"Learning in uncertain, noisy, or adversarial environments is a challenging task for deep neural networks (DNNs). We propose a new theoretically grounded and efficient approach for robust learning that builds upon Bayesian estimation and Variational Inference. We formulate the problem of density propagation through layers of a DNN and solve it using an Ensemble Density Propagation (EnDP) scheme. The EnDP approach allows us to propagate moments of the variational probability distribution across the layers of a Bayesian DNN, enabling the estimation of the mean and covariance of the predictive dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05953","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/2111.05953/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":"2111.05953","created_at":"2026-07-05T03:30:56.528568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.05953v1","created_at":"2026-07-05T03:30:56.528568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05953","created_at":"2026-07-05T03:30:56.528568+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKVT4RKO4R3P","created_at":"2026-07-05T03:30:56.528568+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKVT4RKO4R3P4F2V","created_at":"2026-07-05T03:30:56.528568+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKVT4RKO","created_at":"2026-07-05T03:30:56.528568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QKVT4RKO4R3P4F2V4W2VOTJH7Y","json":"https://pith.science/pith/QKVT4RKO4R3P4F2V4W2VOTJH7Y.json","graph_json":"https://pith.science/api/pith-number/QKVT4RKO4R3P4F2V4W2VOTJH7Y/graph.json","events_json":"https://pith.science/api/pith-number/QKVT4RKO4R3P4F2V4W2VOTJH7Y/events.json","paper":"https://pith.science/paper/QKVT4RKO"},"agent_actions":{"view_html":"https://pith.science/pith/QKVT4RKO4R3P4F2V4W2VOTJH7Y","download_json":"https://pith.science/pith/QKVT4RKO4R3P4F2V4W2VOTJH7Y.json","view_paper":"https://pith.science/paper/QKVT4RKO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.05953&json=true","fetch_graph":"https://pith.science/api/pith-number/QKVT4RKO4R3P4F2V4W2VOTJH7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/QKVT4RKO4R3P4F2V4W2VOTJH7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKVT4RKO4R3P4F2V4W2VOTJH7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKVT4RKO4R3P4F2V4W2VOTJH7Y/action/storage_attestation","attest_author":"https://pith.science/pith/QKVT4RKO4R3P4F2V4W2VOTJH7Y/action/author_attestation","sign_citation":"https://pith.science/pith/QKVT4RKO4R3P4F2V4W2VOTJH7Y/action/citation_signature","submit_replication":"https://pith.science/pith/QKVT4RKO4R3P4F2V4W2VOTJH7Y/action/replication_record"}},"created_at":"2026-07-05T03:30:56.528568+00:00","updated_at":"2026-07-05T03:30:56.528568+00:00"}