{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GO5Y77R6Q567NTX2OMAEEPMFDD","short_pith_number":"pith:GO5Y77R6","canonical_record":{"source":{"id":"2002.05155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T18:57:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"248946e85b620a1b4b6a3760ba5203561abd23b47af409d59c2568d7232d6b6c","abstract_canon_sha256":"cc3b80942edf11a86a6fc5a986512a3e88d411d87f750ddcdb7e61bc044d52a0"},"schema_version":"1.0"},"canonical_sha256":"33bb8ffe3e877df6cefa7300423d8518efc4a5cbb376655ed8100d4eaa92c3da","source":{"kind":"arxiv","id":"2002.05155","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.05155","created_at":"2026-07-05T00:40:21Z"},{"alias_kind":"arxiv_version","alias_value":"2002.05155v1","created_at":"2026-07-05T00:40:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05155","created_at":"2026-07-05T00:40:21Z"},{"alias_kind":"pith_short_12","alias_value":"GO5Y77R6Q567","created_at":"2026-07-05T00:40:21Z"},{"alias_kind":"pith_short_16","alias_value":"GO5Y77R6Q567NTX2","created_at":"2026-07-05T00:40:21Z"},{"alias_kind":"pith_short_8","alias_value":"GO5Y77R6","created_at":"2026-07-05T00:40:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GO5Y77R6Q567NTX2OMAEEPMFDD","target":"record","payload":{"canonical_record":{"source":{"id":"2002.05155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T18:57:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"248946e85b620a1b4b6a3760ba5203561abd23b47af409d59c2568d7232d6b6c","abstract_canon_sha256":"cc3b80942edf11a86a6fc5a986512a3e88d411d87f750ddcdb7e61bc044d52a0"},"schema_version":"1.0"},"canonical_sha256":"33bb8ffe3e877df6cefa7300423d8518efc4a5cbb376655ed8100d4eaa92c3da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:21.724938Z","signature_b64":"863WIDka2RPVMzOb4APfwwswrqd8rtrUYYuJMjHfP3JAX05TSn51bmL11KoWHHIMfc9xZ/vIPDorpgBo2y5LDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33bb8ffe3e877df6cefa7300423d8518efc4a5cbb376655ed8100d4eaa92c3da","last_reissued_at":"2026-07-05T00:40:21.724473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:21.724473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.05155","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:40:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aDS0V3mAC3+AdIh0raemm3tyb5ztTSIUVHQvIHqVwbFWK6ZgJ3pD6WX7bcv8FlmngJuxkwpAI5JIBwIJYB5BCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:03:06.153644Z"},"content_sha256":"80c8ff8efffd27f480099330a02f6958ca4fad5977a892d16bbf961e5dab854a","schema_version":"1.0","event_id":"sha256:80c8ff8efffd27f480099330a02f6958ca4fad5977a892d16bbf961e5dab854a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GO5Y77R6Q567NTX2OMAEEPMFDD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learnable Bernoulli Dropout for Bayesian Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mingyuan Zhou, Randy Ardywibowo, Shahin Boluki, Siamak Zamani Dadaneh, Xiaoning Qian","submitted_at":"2020-02-12T18:57:14Z","abstract_excerpt":"In this work, we propose learnable Bernoulli dropout (LBD), a new model-agnostic dropout scheme that considers the dropout rates as parameters jointly optimized with other model parameters. By probabilistic modeling of Bernoulli dropout, our method enables more robust prediction and uncertainty quantification in deep models. Especially, when combined with variational auto-encoders (VAEs), LBD enables flexible semi-implicit posterior representations, leading to new semi-implicit VAE~(SIVAE) models. We solve the optimization for training with respect to the dropout parameters using Augment-REINF"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05155","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.05155/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:40:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xDr6k8NLTtc6lJrJOlh3rA33YHDP/4EZks6s3txeCx8uVax6QJdZ8GsFJmGqqbgY5DzPLdOC35LqbmFnTEuvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:03:06.155019Z"},"content_sha256":"b75cd3a935cb9bf22a8f47cbcc6b06b12a8444b70317cd1a39207df05cbd5735","schema_version":"1.0","event_id":"sha256:b75cd3a935cb9bf22a8f47cbcc6b06b12a8444b70317cd1a39207df05cbd5735"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GO5Y77R6Q567NTX2OMAEEPMFDD/bundle.json","state_url":"https://pith.science/pith/GO5Y77R6Q567NTX2OMAEEPMFDD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GO5Y77R6Q567NTX2OMAEEPMFDD/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":"2026-08-10T21:03:06Z","links":{"resolver":"https://pith.science/pith/GO5Y77R6Q567NTX2OMAEEPMFDD","bundle":"https://pith.science/pith/GO5Y77R6Q567NTX2OMAEEPMFDD/bundle.json","state":"https://pith.science/pith/GO5Y77R6Q567NTX2OMAEEPMFDD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GO5Y77R6Q567NTX2OMAEEPMFDD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GO5Y77R6Q567NTX2OMAEEPMFDD","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":"cc3b80942edf11a86a6fc5a986512a3e88d411d87f750ddcdb7e61bc044d52a0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T18:57:14Z","title_canon_sha256":"248946e85b620a1b4b6a3760ba5203561abd23b47af409d59c2568d7232d6b6c"},"schema_version":"1.0","source":{"id":"2002.05155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.05155","created_at":"2026-07-05T00:40:21Z"},{"alias_kind":"arxiv_version","alias_value":"2002.05155v1","created_at":"2026-07-05T00:40:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05155","created_at":"2026-07-05T00:40:21Z"},{"alias_kind":"pith_short_12","alias_value":"GO5Y77R6Q567","created_at":"2026-07-05T00:40:21Z"},{"alias_kind":"pith_short_16","alias_value":"GO5Y77R6Q567NTX2","created_at":"2026-07-05T00:40:21Z"},{"alias_kind":"pith_short_8","alias_value":"GO5Y77R6","created_at":"2026-07-05T00:40:21Z"}],"graph_snapshots":[{"event_id":"sha256:b75cd3a935cb9bf22a8f47cbcc6b06b12a8444b70317cd1a39207df05cbd5735","target":"graph","created_at":"2026-07-05T00:40:21Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2002.05155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we propose learnable Bernoulli dropout (LBD), a new model-agnostic dropout scheme that considers the dropout rates as parameters jointly optimized with other model parameters. By probabilistic modeling of Bernoulli dropout, our method enables more robust prediction and uncertainty quantification in deep models. Especially, when combined with variational auto-encoders (VAEs), LBD enables flexible semi-implicit posterior representations, leading to new semi-implicit VAE~(SIVAE) models. We solve the optimization for training with respect to the dropout parameters using Augment-REINF","authors_text":"Mingyuan Zhou, Randy Ardywibowo, Shahin Boluki, Siamak Zamani Dadaneh, Xiaoning Qian","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T18:57:14Z","title":"Learnable Bernoulli Dropout for Bayesian Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05155","kind":"arxiv","version":1},"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":"sha256:80c8ff8efffd27f480099330a02f6958ca4fad5977a892d16bbf961e5dab854a","target":"record","created_at":"2026-07-05T00:40:21Z","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":"cc3b80942edf11a86a6fc5a986512a3e88d411d87f750ddcdb7e61bc044d52a0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T18:57:14Z","title_canon_sha256":"248946e85b620a1b4b6a3760ba5203561abd23b47af409d59c2568d7232d6b6c"},"schema_version":"1.0","source":{"id":"2002.05155","kind":"arxiv","version":1}},"canonical_sha256":"33bb8ffe3e877df6cefa7300423d8518efc4a5cbb376655ed8100d4eaa92c3da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33bb8ffe3e877df6cefa7300423d8518efc4a5cbb376655ed8100d4eaa92c3da","first_computed_at":"2026-07-05T00:40:21.724473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:40:21.724473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"863WIDka2RPVMzOb4APfwwswrqd8rtrUYYuJMjHfP3JAX05TSn51bmL11KoWHHIMfc9xZ/vIPDorpgBo2y5LDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:40:21.724938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.05155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80c8ff8efffd27f480099330a02f6958ca4fad5977a892d16bbf961e5dab854a","sha256:b75cd3a935cb9bf22a8f47cbcc6b06b12a8444b70317cd1a39207df05cbd5735"],"state_sha256":"6fdc398b9a2006e4ef17f8e02f7bca804cdcef796e2a5ce8d2fb8ecc1ee08f3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q9+6Xc7eTOdrSyWEss71oj4M0u7+2ntqAP3ObtT9i1d6F792AiqSS60BA5ao2YEUYfYmYJ3qgXp2mGTrKx8BDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T21:03:06.160455Z","bundle_sha256":"e279fa9490f4be588bb10f580c16e4891168d83c73818d616f270186a6f9a3d4"}}