{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:MCMC5EB4SIGMTPTOYJG72HQHP6","short_pith_number":"pith:MCMC5EB4","schema_version":"1.0","canonical_sha256":"60982e903c920cc9be6ec24dfd1e077f9e322982c674ef28a87c9353111d0656","source":{"kind":"arxiv","id":"1712.08645","version":2},"attestation_state":"computed","paper":{"title":"Dropout Feature Ranking for Deep Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anna Goldenberg, Chun-Hao Chang, Ladislav Rampasek","submitted_at":"2017-12-22T20:25:31Z","abstract_excerpt":"Deep neural networks (DNNs) achieve state-of-the-art results in a variety of domains. Unfortunately, DNNs are notorious for their non-interpretability, and thus limit their applicability in hypothesis-driven domains such as biology and healthcare. Moreover, in the resource-constraint setting, it is critical to design tests relying on fewer more informative features leading to high accuracy performance within reasonable budget. We aim to close this gap by proposing a new general feature ranking method for deep learning. We show that our simple yet effective method performs on par or compares fa"},"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":"1712.08645","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-22T20:25:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d038d7cf79dfabcbe0f6c43f8efaf4c86d999a018562eb9f04ec71fd503b4039","abstract_canon_sha256":"9b87b378c82b01b62d00539f062d63a8111276854966c681672d2d166b70bb8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:40.431536Z","signature_b64":"746g0geLIUlYFJ8AkIUBzE40I52ANp5XJbcj5aOMuDDwnXKZxdaceMaZ8KGAfaCtDu3PrCK5B8Zbx9e0NseuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60982e903c920cc9be6ec24dfd1e077f9e322982c674ef28a87c9353111d0656","last_reissued_at":"2026-05-18T00:21:40.430767Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:40.430767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dropout Feature Ranking for Deep Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anna Goldenberg, Chun-Hao Chang, Ladislav Rampasek","submitted_at":"2017-12-22T20:25:31Z","abstract_excerpt":"Deep neural networks (DNNs) achieve state-of-the-art results in a variety of domains. Unfortunately, DNNs are notorious for their non-interpretability, and thus limit their applicability in hypothesis-driven domains such as biology and healthcare. Moreover, in the resource-constraint setting, it is critical to design tests relying on fewer more informative features leading to high accuracy performance within reasonable budget. We aim to close this gap by proposing a new general feature ranking method for deep learning. We show that our simple yet effective method performs on par or compares fa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.08645","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":"1712.08645","created_at":"2026-05-18T00:21:40.430901+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.08645v2","created_at":"2026-05-18T00:21:40.430901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.08645","created_at":"2026-05-18T00:21:40.430901+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCMC5EB4SIGM","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCMC5EB4SIGMTPTO","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCMC5EB4","created_at":"2026-05-18T12:31:31.346846+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/MCMC5EB4SIGMTPTOYJG72HQHP6","json":"https://pith.science/pith/MCMC5EB4SIGMTPTOYJG72HQHP6.json","graph_json":"https://pith.science/api/pith-number/MCMC5EB4SIGMTPTOYJG72HQHP6/graph.json","events_json":"https://pith.science/api/pith-number/MCMC5EB4SIGMTPTOYJG72HQHP6/events.json","paper":"https://pith.science/paper/MCMC5EB4"},"agent_actions":{"view_html":"https://pith.science/pith/MCMC5EB4SIGMTPTOYJG72HQHP6","download_json":"https://pith.science/pith/MCMC5EB4SIGMTPTOYJG72HQHP6.json","view_paper":"https://pith.science/paper/MCMC5EB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.08645&json=true","fetch_graph":"https://pith.science/api/pith-number/MCMC5EB4SIGMTPTOYJG72HQHP6/graph.json","fetch_events":"https://pith.science/api/pith-number/MCMC5EB4SIGMTPTOYJG72HQHP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCMC5EB4SIGMTPTOYJG72HQHP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCMC5EB4SIGMTPTOYJG72HQHP6/action/storage_attestation","attest_author":"https://pith.science/pith/MCMC5EB4SIGMTPTOYJG72HQHP6/action/author_attestation","sign_citation":"https://pith.science/pith/MCMC5EB4SIGMTPTOYJG72HQHP6/action/citation_signature","submit_replication":"https://pith.science/pith/MCMC5EB4SIGMTPTOYJG72HQHP6/action/replication_record"}},"created_at":"2026-05-18T00:21:40.430901+00:00","updated_at":"2026-05-18T00:21:40.430901+00:00"}