{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7YGAOOPCXIHRXVL7WNSDXXNH7T","short_pith_number":"pith:7YGAOOPC","schema_version":"1.0","canonical_sha256":"fe0c0739e2ba0f1bd57fb3643bdda7fce71444c1f0754c38140d9ad88b8ed855","source":{"kind":"arxiv","id":"1705.07832","version":1},"attestation_state":"computed","paper":{"title":"Concrete Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Alex Kendall, Jiri Hron, Yarin Gal","submitted_at":"2017-05-22T16:25:02Z","abstract_excerpt":"Dropout is used as a practical tool to obtain uncertainty estimates in large vision models and reinforcement learning (RL) tasks. But to obtain well-calibrated uncertainty estimates, a grid-search over the dropout probabilities is necessary - a prohibitive operation with large models, and an impossible one with RL. We propose a new dropout variant which gives improved performance and better calibrated uncertainties. Relying on recent developments in Bayesian deep learning, we use a continuous relaxation of dropout's discrete masks. Together with a principled optimisation objective, this allows"},"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":"1705.07832","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-22T16:25:02Z","cross_cats_sorted":[],"title_canon_sha256":"3d7b5f5287766591a12b642d1b6e71e837336f527de617501f79591b81294181","abstract_canon_sha256":"daeac889424a1fdc8975d501431c842a19e109935ff72c3e318238842aa1207f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:04.459637Z","signature_b64":"OHIDoouEdEtVjNoTkkfxXbAZ0WeaMTD2862DmnzjORpEZQHC+PCUwPow5CSo17wVwPKy4YDWq4/345WI9h5MBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe0c0739e2ba0f1bd57fb3643bdda7fce71444c1f0754c38140d9ad88b8ed855","last_reissued_at":"2026-05-18T00:44:04.459002Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:04.459002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Concrete Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Alex Kendall, Jiri Hron, Yarin Gal","submitted_at":"2017-05-22T16:25:02Z","abstract_excerpt":"Dropout is used as a practical tool to obtain uncertainty estimates in large vision models and reinforcement learning (RL) tasks. But to obtain well-calibrated uncertainty estimates, a grid-search over the dropout probabilities is necessary - a prohibitive operation with large models, and an impossible one with RL. We propose a new dropout variant which gives improved performance and better calibrated uncertainties. Relying on recent developments in Bayesian deep learning, we use a continuous relaxation of dropout's discrete masks. Together with a principled optimisation objective, this allows"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07832","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":"1705.07832","created_at":"2026-05-18T00:44:04.459096+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07832v1","created_at":"2026-05-18T00:44:04.459096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07832","created_at":"2026-05-18T00:44:04.459096+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YGAOOPCXIHR","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YGAOOPCXIHRXVL7","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YGAOOPC","created_at":"2026-05-18T12:31:05.417338+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/7YGAOOPCXIHRXVL7WNSDXXNH7T","json":"https://pith.science/pith/7YGAOOPCXIHRXVL7WNSDXXNH7T.json","graph_json":"https://pith.science/api/pith-number/7YGAOOPCXIHRXVL7WNSDXXNH7T/graph.json","events_json":"https://pith.science/api/pith-number/7YGAOOPCXIHRXVL7WNSDXXNH7T/events.json","paper":"https://pith.science/paper/7YGAOOPC"},"agent_actions":{"view_html":"https://pith.science/pith/7YGAOOPCXIHRXVL7WNSDXXNH7T","download_json":"https://pith.science/pith/7YGAOOPCXIHRXVL7WNSDXXNH7T.json","view_paper":"https://pith.science/paper/7YGAOOPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07832&json=true","fetch_graph":"https://pith.science/api/pith-number/7YGAOOPCXIHRXVL7WNSDXXNH7T/graph.json","fetch_events":"https://pith.science/api/pith-number/7YGAOOPCXIHRXVL7WNSDXXNH7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YGAOOPCXIHRXVL7WNSDXXNH7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YGAOOPCXIHRXVL7WNSDXXNH7T/action/storage_attestation","attest_author":"https://pith.science/pith/7YGAOOPCXIHRXVL7WNSDXXNH7T/action/author_attestation","sign_citation":"https://pith.science/pith/7YGAOOPCXIHRXVL7WNSDXXNH7T/action/citation_signature","submit_replication":"https://pith.science/pith/7YGAOOPCXIHRXVL7WNSDXXNH7T/action/replication_record"}},"created_at":"2026-05-18T00:44:04.459096+00:00","updated_at":"2026-05-18T00:44:04.459096+00:00"}