{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JVBKWYMJYAZHVFDTWRU36HZGN5","short_pith_number":"pith:JVBKWYMJ","canonical_record":{"source":{"id":"1811.07533","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T07:31:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2ccf34b7935ec3b6f801979564b335208406bf96c3caf4dba0493d6a53567160","abstract_canon_sha256":"50c17b883d696343ecb78ecf85d7371f710a164c38859d8eb1ea466b605bccfa"},"schema_version":"1.0"},"canonical_sha256":"4d42ab6189c0327a9473b469bf1f266f79bef5c48687c61941c11f378b3e60de","source":{"kind":"arxiv","id":"1811.07533","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.07533","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"arxiv_version","alias_value":"1811.07533v3","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07533","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"pith_short_12","alias_value":"JVBKWYMJYAZH","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JVBKWYMJYAZHVFDT","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JVBKWYMJ","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JVBKWYMJYAZHVFDTWRU36HZGN5","target":"record","payload":{"canonical_record":{"source":{"id":"1811.07533","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T07:31:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2ccf34b7935ec3b6f801979564b335208406bf96c3caf4dba0493d6a53567160","abstract_canon_sha256":"50c17b883d696343ecb78ecf85d7371f710a164c38859d8eb1ea466b605bccfa"},"schema_version":"1.0"},"canonical_sha256":"4d42ab6189c0327a9473b469bf1f266f79bef5c48687c61941c11f378b3e60de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:27.379983Z","signature_b64":"yoXUSGEejCbVdWwBAcKjO72OixRR1enXYSRDg/B3tz99ej3rSZzafOZaZRJDK/KFBPHM8+Z/qZYSXk3TmcIACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d42ab6189c0327a9473b469bf1f266f79bef5c48687c61941c11f378b3e60de","last_reissued_at":"2026-05-17T23:49:27.379482Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:27.379482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.07533","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:49:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1YSHK9s88aVPNXHmjRyzUh0y9g4yXFWbOAOvobPhNlkbWsZhrQT2o6tB789IRlJtreOt3my3Mr3p5NNxfytiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T19:46:15.153571Z"},"content_sha256":"72abfe0b40ea594515b095081af2414f19a63412d21b12af4c2e7ff70bb1002e","schema_version":"1.0","event_id":"sha256:72abfe0b40ea594515b095081af2414f19a63412d21b12af4c2e7ff70bb1002e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JVBKWYMJYAZHVFDTWRU36HZGN5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational Bayesian Dropout with a Hierarchical Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dong Gong, Lei Zhang, Qinfeng Shi, Wenyong Dong, Yuhang Liu","submitted_at":"2018-11-19T07:31:46Z","abstract_excerpt":"Variational dropout (VD) is a generalization of Gaussian dropout, which aims at inferring the posterior of network weights based on a log-uniform prior on them to learn these weights as well as dropout rate simultaneously. The log-uniform prior not only interprets the regularization capacity of Gaussian dropout in network training, but also underpins the inference of such posterior. However, the log-uniform prior is an improper prior (i.e., its integral is infinite) which causes the inference of posterior to be ill-posed, thus restricting the regularization performance of VD. To address this p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07533","kind":"arxiv","version":3},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:49:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kHXSQHu9Y9k0TBggArlvj2QmY5NyiuuBUoCvwYvopWovEejwLsy+E1RWzEaXNgJt7JNaf3ym8LHLhJuIgNCEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T19:46:15.154288Z"},"content_sha256":"b27d401460acb2b91760c903f6d49ee01000d550240c9e895425170f70d52cb5","schema_version":"1.0","event_id":"sha256:b27d401460acb2b91760c903f6d49ee01000d550240c9e895425170f70d52cb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JVBKWYMJYAZHVFDTWRU36HZGN5/bundle.json","state_url":"https://pith.science/pith/JVBKWYMJYAZHVFDTWRU36HZGN5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JVBKWYMJYAZHVFDTWRU36HZGN5/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":"2026-06-08T19:46:15Z","links":{"resolver":"https://pith.science/pith/JVBKWYMJYAZHVFDTWRU36HZGN5","bundle":"https://pith.science/pith/JVBKWYMJYAZHVFDTWRU36HZGN5/bundle.json","state":"https://pith.science/pith/JVBKWYMJYAZHVFDTWRU36HZGN5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JVBKWYMJYAZHVFDTWRU36HZGN5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JVBKWYMJYAZHVFDTWRU36HZGN5","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":"50c17b883d696343ecb78ecf85d7371f710a164c38859d8eb1ea466b605bccfa","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T07:31:46Z","title_canon_sha256":"2ccf34b7935ec3b6f801979564b335208406bf96c3caf4dba0493d6a53567160"},"schema_version":"1.0","source":{"id":"1811.07533","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.07533","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"arxiv_version","alias_value":"1811.07533v3","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07533","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"pith_short_12","alias_value":"JVBKWYMJYAZH","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JVBKWYMJYAZHVFDT","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JVBKWYMJ","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:b27d401460acb2b91760c903f6d49ee01000d550240c9e895425170f70d52cb5","target":"graph","created_at":"2026-05-17T23:49:27Z","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"},"paper":{"abstract_excerpt":"Variational dropout (VD) is a generalization of Gaussian dropout, which aims at inferring the posterior of network weights based on a log-uniform prior on them to learn these weights as well as dropout rate simultaneously. The log-uniform prior not only interprets the regularization capacity of Gaussian dropout in network training, but also underpins the inference of such posterior. However, the log-uniform prior is an improper prior (i.e., its integral is infinite) which causes the inference of posterior to be ill-posed, thus restricting the regularization performance of VD. To address this p","authors_text":"Dong Gong, Lei Zhang, Qinfeng Shi, Wenyong Dong, Yuhang Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T07:31:46Z","title":"Variational Bayesian Dropout with a Hierarchical Prior"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07533","kind":"arxiv","version":3},"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":"sha256:72abfe0b40ea594515b095081af2414f19a63412d21b12af4c2e7ff70bb1002e","target":"record","created_at":"2026-05-17T23:49:27Z","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":"50c17b883d696343ecb78ecf85d7371f710a164c38859d8eb1ea466b605bccfa","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T07:31:46Z","title_canon_sha256":"2ccf34b7935ec3b6f801979564b335208406bf96c3caf4dba0493d6a53567160"},"schema_version":"1.0","source":{"id":"1811.07533","kind":"arxiv","version":3}},"canonical_sha256":"4d42ab6189c0327a9473b469bf1f266f79bef5c48687c61941c11f378b3e60de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d42ab6189c0327a9473b469bf1f266f79bef5c48687c61941c11f378b3e60de","first_computed_at":"2026-05-17T23:49:27.379482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:27.379482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yoXUSGEejCbVdWwBAcKjO72OixRR1enXYSRDg/B3tz99ej3rSZzafOZaZRJDK/KFBPHM8+Z/qZYSXk3TmcIACA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:27.379983Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.07533","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72abfe0b40ea594515b095081af2414f19a63412d21b12af4c2e7ff70bb1002e","sha256:b27d401460acb2b91760c903f6d49ee01000d550240c9e895425170f70d52cb5"],"state_sha256":"a236f7cfa8c3c9193bb91d19433bd80968327acbcc2e195b6f1376f17c842f66"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vZpi7H63TqsUy54bTCxmJs+9z4byQR8g4rj3syZ3t+NdP8HkrPU98XX9qi0XrFoybLYpiPoZ9Y20NoPqN5PSDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T19:46:15.159092Z","bundle_sha256":"2551758c0bd26e66e7e7b60531b86670d61d8c1413e1302efc04ff1ead6c23bf"}}