{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MENRZROMZFJRNVPAENJYAGUNN2","short_pith_number":"pith:MENRZROM","canonical_record":{"source":{"id":"1810.04045","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-09T14:44:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bb9d7ec3feba9cff954077f3ac8b6c070eb6de38367dbacbb9bfac6ae0ea24af","abstract_canon_sha256":"5056ba8017a2519e021d877605d77d04fe11be35bc87740847fff127111f350b"},"schema_version":"1.0"},"canonical_sha256":"611b1cc5ccc95316d5e02353801a8d6eae72ba85e1298984b5189d53f352d6ea","source":{"kind":"arxiv","id":"1810.04045","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04045","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04045v3","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04045","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"pith_short_12","alias_value":"MENRZROMZFJR","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MENRZROMZFJRNVPA","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MENRZROM","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MENRZROMZFJRNVPAENJYAGUNN2","target":"record","payload":{"canonical_record":{"source":{"id":"1810.04045","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-09T14:44:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bb9d7ec3feba9cff954077f3ac8b6c070eb6de38367dbacbb9bfac6ae0ea24af","abstract_canon_sha256":"5056ba8017a2519e021d877605d77d04fe11be35bc87740847fff127111f350b"},"schema_version":"1.0"},"canonical_sha256":"611b1cc5ccc95316d5e02353801a8d6eae72ba85e1298984b5189d53f352d6ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:48.004388Z","signature_b64":"/L6ba+Ng8aHn80cZLdJXjDftV89O6Xblxp7khzfkrrNK5GTV2ffcTpqW3Kh93FSe/z44mYvZpkVt/hO/WBjxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"611b1cc5ccc95316d5e02353801a8d6eae72ba85e1298984b5189d53f352d6ea","last_reissued_at":"2026-05-17T23:44:48.003729Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:48.003729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.04045","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ihhlKQDPVxw1zdq0PkddAmnGHRIx7WNZg1JMp1ZkV7GmFhgEJ5vNXPAbrGFWg5S8LmGVgSqjfLj01zKZqSLIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T20:33:08.256602Z"},"content_sha256":"c287420fa81ecce030dc347910c660bcfab34ec76bd5ac260c5d335a9deddca1","schema_version":"1.0","event_id":"sha256:c287420fa81ecce030dc347910c660bcfab34ec76bd5ac260c5d335a9deddca1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MENRZROMZFJRNVPAENJYAGUNN2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dropout as a Structured Shrinkage Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Eric Nalisnick, Jos\\'e Miguel Hern\\'andez-Lobato, Padhraic Smyth","submitted_at":"2018-10-09T14:44:08Z","abstract_excerpt":"Dropout regularization of deep neural networks has been a mysterious yet effective tool to prevent overfitting. Explanations for its success range from the prevention of \"co-adapted\" weights to it being a form of cheap Bayesian inference. We propose a novel framework for understanding multiplicative noise in neural networks, considering continuous distributions as well as Bernoulli noise (i.e. dropout). We show that multiplicative noise induces structured shrinkage priors on a network's weights. We derive the equivalence through reparametrization properties of scale mixtures and without invoki"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04045","kind":"arxiv","version":3},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"80qt3on2oyZrQj9oPz3An2PNaoWH/C9k/0hHcdl7jvJLXZNTCmhNrtAZEeaZiwI2YbdmH9NcZhv/c8PGSFOVDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T20:33:08.257146Z"},"content_sha256":"8153b5233130789c878c641a1d858d06a9192c4ad3cf6908a2d7d695b68290ea","schema_version":"1.0","event_id":"sha256:8153b5233130789c878c641a1d858d06a9192c4ad3cf6908a2d7d695b68290ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MENRZROMZFJRNVPAENJYAGUNN2/bundle.json","state_url":"https://pith.science/pith/MENRZROMZFJRNVPAENJYAGUNN2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MENRZROMZFJRNVPAENJYAGUNN2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T20:33:08Z","links":{"resolver":"https://pith.science/pith/MENRZROMZFJRNVPAENJYAGUNN2","bundle":"https://pith.science/pith/MENRZROMZFJRNVPAENJYAGUNN2/bundle.json","state":"https://pith.science/pith/MENRZROMZFJRNVPAENJYAGUNN2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MENRZROMZFJRNVPAENJYAGUNN2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MENRZROMZFJRNVPAENJYAGUNN2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5056ba8017a2519e021d877605d77d04fe11be35bc87740847fff127111f350b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-09T14:44:08Z","title_canon_sha256":"bb9d7ec3feba9cff954077f3ac8b6c070eb6de38367dbacbb9bfac6ae0ea24af"},"schema_version":"1.0","source":{"id":"1810.04045","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04045","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04045v3","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04045","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"pith_short_12","alias_value":"MENRZROMZFJR","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MENRZROMZFJRNVPA","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MENRZROM","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:8153b5233130789c878c641a1d858d06a9192c4ad3cf6908a2d7d695b68290ea","target":"graph","created_at":"2026-05-17T23:44:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Dropout regularization of deep neural networks has been a mysterious yet effective tool to prevent overfitting. Explanations for its success range from the prevention of \"co-adapted\" weights to it being a form of cheap Bayesian inference. We propose a novel framework for understanding multiplicative noise in neural networks, considering continuous distributions as well as Bernoulli noise (i.e. dropout). We show that multiplicative noise induces structured shrinkage priors on a network's weights. We derive the equivalence through reparametrization properties of scale mixtures and without invoki","authors_text":"Eric Nalisnick, Jos\\'e Miguel Hern\\'andez-Lobato, Padhraic Smyth","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-09T14:44:08Z","title":"Dropout as a Structured Shrinkage Prior"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04045","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c287420fa81ecce030dc347910c660bcfab34ec76bd5ac260c5d335a9deddca1","target":"record","created_at":"2026-05-17T23:44:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5056ba8017a2519e021d877605d77d04fe11be35bc87740847fff127111f350b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-09T14:44:08Z","title_canon_sha256":"bb9d7ec3feba9cff954077f3ac8b6c070eb6de38367dbacbb9bfac6ae0ea24af"},"schema_version":"1.0","source":{"id":"1810.04045","kind":"arxiv","version":3}},"canonical_sha256":"611b1cc5ccc95316d5e02353801a8d6eae72ba85e1298984b5189d53f352d6ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"611b1cc5ccc95316d5e02353801a8d6eae72ba85e1298984b5189d53f352d6ea","first_computed_at":"2026-05-17T23:44:48.003729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:48.003729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/L6ba+Ng8aHn80cZLdJXjDftV89O6Xblxp7khzfkrrNK5GTV2ffcTpqW3Kh93FSe/z44mYvZpkVt/hO/WBjxAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:48.004388Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.04045","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c287420fa81ecce030dc347910c660bcfab34ec76bd5ac260c5d335a9deddca1","sha256:8153b5233130789c878c641a1d858d06a9192c4ad3cf6908a2d7d695b68290ea"],"state_sha256":"75049d3c6503929415243c01a2ac1e64961b73770c9e49daf94ba559dfee2a0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8xe527nTi+wUeIikVVvA+neq9Qbaaoy0PFJnBdCqhplpjbYKgd1y0T+WzfcqCKD4Ftn3IiTf9IES/jzGkBnkCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T20:33:08.259926Z","bundle_sha256":"432d05b494ee144fef4a11bc8dc81d06754249965c1f84bbd5f3e813913e4712"}}