{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CNENOAYUGXNH7YH5AV6YLLKQ3D","short_pith_number":"pith:CNENOAYU","schema_version":"1.0","canonical_sha256":"1348d7031435da7fe0fd057d85ad50d8db6dca0bef33c35b89a6a945a8beee10","source":{"kind":"arxiv","id":"1802.04893","version":2},"attestation_state":"computed","paper":{"title":"Uncertainty Estimation via Stochastic Batch Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrei Atanov, Arsenii Ashukha, Dmitry Molchanov, Dmitry Vetrov, Kirill Neklyudov","submitted_at":"2018-02-13T23:22:16Z","abstract_excerpt":"In this work, we investigate Batch Normalization technique and propose its probabilistic interpretation. We propose a probabilistic model and show that Batch Normalization maximazes the lower bound of its marginalized log-likelihood. Then, according to the new probabilistic model, we design an algorithm which acts consistently during train and test. However, inference becomes computationally inefficient. To reduce memory and computational cost, we propose Stochastic Batch Normalization -- an efficient approximation of proper inference procedure. This method provides us with a scalable uncertai"},"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":"1802.04893","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-13T23:22:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"60b5a284cbf025e8735c792ff6a023a9e56fb2141a12031b685b1f182e3cf926","abstract_canon_sha256":"2584b44f481f444409dfe8ec17e8db99a2c2ba33e9a1b357d5105644e6df8efe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:29.842042Z","signature_b64":"8DF66eGBfgXw8giIggd11FjpYNO8FrpywFpZAzau3xL72s8cAK+sLBRRHkM8v7F8zCL1/fGMjWu4bNCCCcNSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1348d7031435da7fe0fd057d85ad50d8db6dca0bef33c35b89a6a945a8beee10","last_reissued_at":"2026-05-18T00:20:29.841478Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:29.841478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty Estimation via Stochastic Batch Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrei Atanov, Arsenii Ashukha, Dmitry Molchanov, Dmitry Vetrov, Kirill Neklyudov","submitted_at":"2018-02-13T23:22:16Z","abstract_excerpt":"In this work, we investigate Batch Normalization technique and propose its probabilistic interpretation. We propose a probabilistic model and show that Batch Normalization maximazes the lower bound of its marginalized log-likelihood. Then, according to the new probabilistic model, we design an algorithm which acts consistently during train and test. However, inference becomes computationally inefficient. To reduce memory and computational cost, we propose Stochastic Batch Normalization -- an efficient approximation of proper inference procedure. This method provides us with a scalable uncertai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04893","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1802.04893","created_at":"2026-05-18T00:20:29.841559+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04893v2","created_at":"2026-05-18T00:20:29.841559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04893","created_at":"2026-05-18T00:20:29.841559+00:00"},{"alias_kind":"pith_short_12","alias_value":"CNENOAYUGXNH","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CNENOAYUGXNH7YH5","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CNENOAYU","created_at":"2026-05-18T12:32:16.446611+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/CNENOAYUGXNH7YH5AV6YLLKQ3D","json":"https://pith.science/pith/CNENOAYUGXNH7YH5AV6YLLKQ3D.json","graph_json":"https://pith.science/api/pith-number/CNENOAYUGXNH7YH5AV6YLLKQ3D/graph.json","events_json":"https://pith.science/api/pith-number/CNENOAYUGXNH7YH5AV6YLLKQ3D/events.json","paper":"https://pith.science/paper/CNENOAYU"},"agent_actions":{"view_html":"https://pith.science/pith/CNENOAYUGXNH7YH5AV6YLLKQ3D","download_json":"https://pith.science/pith/CNENOAYUGXNH7YH5AV6YLLKQ3D.json","view_paper":"https://pith.science/paper/CNENOAYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04893&json=true","fetch_graph":"https://pith.science/api/pith-number/CNENOAYUGXNH7YH5AV6YLLKQ3D/graph.json","fetch_events":"https://pith.science/api/pith-number/CNENOAYUGXNH7YH5AV6YLLKQ3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CNENOAYUGXNH7YH5AV6YLLKQ3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CNENOAYUGXNH7YH5AV6YLLKQ3D/action/storage_attestation","attest_author":"https://pith.science/pith/CNENOAYUGXNH7YH5AV6YLLKQ3D/action/author_attestation","sign_citation":"https://pith.science/pith/CNENOAYUGXNH7YH5AV6YLLKQ3D/action/citation_signature","submit_replication":"https://pith.science/pith/CNENOAYUGXNH7YH5AV6YLLKQ3D/action/replication_record"}},"created_at":"2026-05-18T00:20:29.841559+00:00","updated_at":"2026-05-18T00:20:29.841559+00:00"}