{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GRMZN6A4ZA7TFVSTI4PTGP2CBG","short_pith_number":"pith:GRMZN6A4","schema_version":"1.0","canonical_sha256":"345996f81cc83f32d653471f333f4209ba9024d260b0c62c26b3918a3c773b89","source":{"kind":"arxiv","id":"1909.11507","version":2},"attestation_state":"computed","paper":{"title":"Regularising Deep Networks with Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Camuto, Chris Holmes, Matthew Willetts, Stephen Roberts","submitted_at":"2019-09-25T14:14:04Z","abstract_excerpt":"We develop a new method for regularising neural networks. We learn a probability distribution over the activations of all layers of the model and then insert imputed values into the network during training. We obtain a posterior for an arbitrary subset of activations conditioned on the remainder. This is a generalisation of data augmentation to the hidden layers of a network, and a form of data-aware dropout. We demonstrate that our training method leads to higher test accuracy and lower test-set cross-entropy for neural networks trained on CIFAR-10 and SVHN compared to standard regularisation"},"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":"1909.11507","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T14:14:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f0c55bb97ee1eb369ac5d478a6b0bd6847d650cdccb0705d05745783f366c47f","abstract_canon_sha256":"287685f53f80cd4287ae843fa7a2fc246ac95c63c07602a18d93d10848513dcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:22.366961Z","signature_b64":"w4YeTVLhSy2qGtnWkjPqAaIshrtjAI1dFKgtrbzPdmV3NLqEkfo1598UjvWKQI+hmnFaZKH0GNJtkZGluDbQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"345996f81cc83f32d653471f333f4209ba9024d260b0c62c26b3918a3c773b89","last_reissued_at":"2026-07-05T00:11:22.366608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:22.366608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regularising Deep Networks with Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Camuto, Chris Holmes, Matthew Willetts, Stephen Roberts","submitted_at":"2019-09-25T14:14:04Z","abstract_excerpt":"We develop a new method for regularising neural networks. We learn a probability distribution over the activations of all layers of the model and then insert imputed values into the network during training. We obtain a posterior for an arbitrary subset of activations conditioned on the remainder. This is a generalisation of data augmentation to the hidden layers of a network, and a form of data-aware dropout. We demonstrate that our training method leads to higher test accuracy and lower test-set cross-entropy for neural networks trained on CIFAR-10 and SVHN compared to standard regularisation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11507","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.11507/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":"1909.11507","created_at":"2026-07-05T00:11:22.366667+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.11507v2","created_at":"2026-07-05T00:11:22.366667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11507","created_at":"2026-07-05T00:11:22.366667+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRMZN6A4ZA7T","created_at":"2026-07-05T00:11:22.366667+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRMZN6A4ZA7TFVST","created_at":"2026-07-05T00:11:22.366667+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRMZN6A4","created_at":"2026-07-05T00:11:22.366667+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/GRMZN6A4ZA7TFVSTI4PTGP2CBG","json":"https://pith.science/pith/GRMZN6A4ZA7TFVSTI4PTGP2CBG.json","graph_json":"https://pith.science/api/pith-number/GRMZN6A4ZA7TFVSTI4PTGP2CBG/graph.json","events_json":"https://pith.science/api/pith-number/GRMZN6A4ZA7TFVSTI4PTGP2CBG/events.json","paper":"https://pith.science/paper/GRMZN6A4"},"agent_actions":{"view_html":"https://pith.science/pith/GRMZN6A4ZA7TFVSTI4PTGP2CBG","download_json":"https://pith.science/pith/GRMZN6A4ZA7TFVSTI4PTGP2CBG.json","view_paper":"https://pith.science/paper/GRMZN6A4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.11507&json=true","fetch_graph":"https://pith.science/api/pith-number/GRMZN6A4ZA7TFVSTI4PTGP2CBG/graph.json","fetch_events":"https://pith.science/api/pith-number/GRMZN6A4ZA7TFVSTI4PTGP2CBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRMZN6A4ZA7TFVSTI4PTGP2CBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRMZN6A4ZA7TFVSTI4PTGP2CBG/action/storage_attestation","attest_author":"https://pith.science/pith/GRMZN6A4ZA7TFVSTI4PTGP2CBG/action/author_attestation","sign_citation":"https://pith.science/pith/GRMZN6A4ZA7TFVSTI4PTGP2CBG/action/citation_signature","submit_replication":"https://pith.science/pith/GRMZN6A4ZA7TFVSTI4PTGP2CBG/action/replication_record"}},"created_at":"2026-07-05T00:11:22.366667+00:00","updated_at":"2026-07-05T00:11:22.366667+00:00"}