{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WOCITBWEFHK3LWSEO3BR2IJIET","short_pith_number":"pith:WOCITBWE","schema_version":"1.0","canonical_sha256":"b3848986c429d5b5da4476c31d212824c7ca994372a992190229e56c148d3f83","source":{"kind":"arxiv","id":"1904.06330","version":1},"attestation_state":"computed","paper":{"title":"Reliable Prediction Errors for Deep Neural Networks Using Test-Time Dropout","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Bender, Isidro Cortes-Ciriano","submitted_at":"2019-04-12T17:18:08Z","abstract_excerpt":"While the use of deep learning in drug discovery is gaining increasing attention, the lack of methods to compute reliable errors in prediction for Neural Networks prevents their application to guide decision making in domains where identifying unreliable predictions is essential, e.g. precision medicine. Here, we present a framework to compute reliable errors in prediction for Neural Networks using Test-Time Dropout and Conformal Prediction. Specifically, the algorithm consists of training a single Neural Network using dropout, and then applying it N times to both the validation and test sets,"},"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":"1904.06330","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-04-12T17:18:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1fce23560524295a5f0cd2965368c8b810f6a404644fe46840eb9f739e9f54dc","abstract_canon_sha256":"6a15ccc86d69733e33ebfbc6ca79cd2540c7f54eea1ccf85b9329fa458708728"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:41.834885Z","signature_b64":"wsxyB7FvoarA4czY9jvCWdQ4xdZdx8M6IPkZinEhZTQRBiJuuXwHzJT2Tnhgbmp4gdwiJncOCv+xnZ804wQDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3848986c429d5b5da4476c31d212824c7ca994372a992190229e56c148d3f83","last_reissued_at":"2026-05-17T23:42:41.834182Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:41.834182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliable Prediction Errors for Deep Neural Networks Using Test-Time Dropout","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Bender, Isidro Cortes-Ciriano","submitted_at":"2019-04-12T17:18:08Z","abstract_excerpt":"While the use of deep learning in drug discovery is gaining increasing attention, the lack of methods to compute reliable errors in prediction for Neural Networks prevents their application to guide decision making in domains where identifying unreliable predictions is essential, e.g. precision medicine. Here, we present a framework to compute reliable errors in prediction for Neural Networks using Test-Time Dropout and Conformal Prediction. Specifically, the algorithm consists of training a single Neural Network using dropout, and then applying it N times to both the validation and test sets,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06330","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":""},"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":"1904.06330","created_at":"2026-05-17T23:42:41.834289+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.06330v1","created_at":"2026-05-17T23:42:41.834289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06330","created_at":"2026-05-17T23:42:41.834289+00:00"},{"alias_kind":"pith_short_12","alias_value":"WOCITBWEFHK3","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WOCITBWEFHK3LWSE","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WOCITBWE","created_at":"2026-05-18T12:33:30.264802+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/WOCITBWEFHK3LWSEO3BR2IJIET","json":"https://pith.science/pith/WOCITBWEFHK3LWSEO3BR2IJIET.json","graph_json":"https://pith.science/api/pith-number/WOCITBWEFHK3LWSEO3BR2IJIET/graph.json","events_json":"https://pith.science/api/pith-number/WOCITBWEFHK3LWSEO3BR2IJIET/events.json","paper":"https://pith.science/paper/WOCITBWE"},"agent_actions":{"view_html":"https://pith.science/pith/WOCITBWEFHK3LWSEO3BR2IJIET","download_json":"https://pith.science/pith/WOCITBWEFHK3LWSEO3BR2IJIET.json","view_paper":"https://pith.science/paper/WOCITBWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.06330&json=true","fetch_graph":"https://pith.science/api/pith-number/WOCITBWEFHK3LWSEO3BR2IJIET/graph.json","fetch_events":"https://pith.science/api/pith-number/WOCITBWEFHK3LWSEO3BR2IJIET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WOCITBWEFHK3LWSEO3BR2IJIET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WOCITBWEFHK3LWSEO3BR2IJIET/action/storage_attestation","attest_author":"https://pith.science/pith/WOCITBWEFHK3LWSEO3BR2IJIET/action/author_attestation","sign_citation":"https://pith.science/pith/WOCITBWEFHK3LWSEO3BR2IJIET/action/citation_signature","submit_replication":"https://pith.science/pith/WOCITBWEFHK3LWSEO3BR2IJIET/action/replication_record"}},"created_at":"2026-05-17T23:42:41.834289+00:00","updated_at":"2026-05-17T23:42:41.834289+00:00"}