{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:SJTBUXVZF6B5WDGQYUJE6HPJLH","short_pith_number":"pith:SJTBUXVZ","canonical_record":{"source":{"id":"1507.05331","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-19T20:30:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cf6ebe736e8b9c5a238a12e615bd0f23620be9b91b1e7d5fd0da35f24397767a","abstract_canon_sha256":"4b4160ab93e9358c079eb3cd1e403d8e9a63976a8e6b43ed9fc88b092c6a77a3"},"schema_version":"1.0"},"canonical_sha256":"92661a5eb92f83db0cd0c5124f1de959fdbf96e857a02a773b47394c1ebf30c0","source":{"kind":"arxiv","id":"1507.05331","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.05331","created_at":"2026-05-18T01:36:37Z"},{"alias_kind":"arxiv_version","alias_value":"1507.05331v1","created_at":"2026-05-18T01:36:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.05331","created_at":"2026-05-18T01:36:37Z"},{"alias_kind":"pith_short_12","alias_value":"SJTBUXVZF6B5","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"SJTBUXVZF6B5WDGQ","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"SJTBUXVZ","created_at":"2026-05-18T12:29:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:SJTBUXVZF6B5WDGQYUJE6HPJLH","target":"record","payload":{"canonical_record":{"source":{"id":"1507.05331","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-19T20:30:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cf6ebe736e8b9c5a238a12e615bd0f23620be9b91b1e7d5fd0da35f24397767a","abstract_canon_sha256":"4b4160ab93e9358c079eb3cd1e403d8e9a63976a8e6b43ed9fc88b092c6a77a3"},"schema_version":"1.0"},"canonical_sha256":"92661a5eb92f83db0cd0c5124f1de959fdbf96e857a02a773b47394c1ebf30c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:37.178559Z","signature_b64":"YfTRsZbPr+GpIANBVlzZdyh5bgj8XXgd5jPP7uBsET+WcTGBPFZeit8GfkfhF9kqPi12cR1P8R+Tb0Uma76BBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92661a5eb92f83db0cd0c5124f1de959fdbf96e857a02a773b47394c1ebf30c0","last_reissued_at":"2026-05-18T01:36:37.177873Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:37.177873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.05331","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":"2026-05-18T01:36:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RGMJHJkrALQMmHfg+ofM+zjUXHYUVmsXdVaE+TmcAfd7pNS6QwoqC0+BAy+1GyqivBVJUPw8KFH6HHPGS/fPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:00:53.012461Z"},"content_sha256":"e7b55f0b6a90c022444f67c38c05ee3dd2a8df2d09b2e3f989086c947653f3fd","schema_version":"1.0","event_id":"sha256:e7b55f0b6a90c022444f67c38c05ee3dd2a8df2d09b2e3f989086c947653f3fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:SJTBUXVZF6B5WDGQYUJE6HPJLH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Adaptive Weight Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Daniela Korhammer, Justin Bayer, Maximilian Karl, Patrick van der Smagt","submitted_at":"2015-07-19T20:30:10Z","abstract_excerpt":"Marginalising out uncertain quantities within the internal representations or parameters of neural networks is of central importance for a wide range of learning techniques, such as empirical, variational or full Bayesian methods. We set out to generalise fast dropout (Wang & Manning, 2013) to cover a wider variety of noise processes in neural networks. This leads to an efficient calculation of the marginal likelihood and predictive distribution which evades sampling and the consequential increase in training time due to highly variant gradient estimates. This allows us to approximate variatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.05331","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:36:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EMB9HIYEPtGw+fE0ZnauhLw38JegkP9YV6Z+CP7SzpdbzVXKoQeR5wrEf1xbkFAnR/EfTT+EyW+Z6XEVzM99Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:00:53.012904Z"},"content_sha256":"dfc523a6bb7f7d424eee2ffea3778f02248b2b1cd0ca8355b6753a45f44a0108","schema_version":"1.0","event_id":"sha256:dfc523a6bb7f7d424eee2ffea3778f02248b2b1cd0ca8355b6753a45f44a0108"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJTBUXVZF6B5WDGQYUJE6HPJLH/bundle.json","state_url":"https://pith.science/pith/SJTBUXVZF6B5WDGQYUJE6HPJLH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJTBUXVZF6B5WDGQYUJE6HPJLH/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":"2026-05-30T14:00:53Z","links":{"resolver":"https://pith.science/pith/SJTBUXVZF6B5WDGQYUJE6HPJLH","bundle":"https://pith.science/pith/SJTBUXVZF6B5WDGQYUJE6HPJLH/bundle.json","state":"https://pith.science/pith/SJTBUXVZF6B5WDGQYUJE6HPJLH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJTBUXVZF6B5WDGQYUJE6HPJLH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:SJTBUXVZF6B5WDGQYUJE6HPJLH","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":"4b4160ab93e9358c079eb3cd1e403d8e9a63976a8e6b43ed9fc88b092c6a77a3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-19T20:30:10Z","title_canon_sha256":"cf6ebe736e8b9c5a238a12e615bd0f23620be9b91b1e7d5fd0da35f24397767a"},"schema_version":"1.0","source":{"id":"1507.05331","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.05331","created_at":"2026-05-18T01:36:37Z"},{"alias_kind":"arxiv_version","alias_value":"1507.05331v1","created_at":"2026-05-18T01:36:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.05331","created_at":"2026-05-18T01:36:37Z"},{"alias_kind":"pith_short_12","alias_value":"SJTBUXVZF6B5","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"SJTBUXVZF6B5WDGQ","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"SJTBUXVZ","created_at":"2026-05-18T12:29:42Z"}],"graph_snapshots":[{"event_id":"sha256:dfc523a6bb7f7d424eee2ffea3778f02248b2b1cd0ca8355b6753a45f44a0108","target":"graph","created_at":"2026-05-18T01:36:37Z","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":"Marginalising out uncertain quantities within the internal representations or parameters of neural networks is of central importance for a wide range of learning techniques, such as empirical, variational or full Bayesian methods. We set out to generalise fast dropout (Wang & Manning, 2013) to cover a wider variety of noise processes in neural networks. This leads to an efficient calculation of the marginal likelihood and predictive distribution which evades sampling and the consequential increase in training time due to highly variant gradient estimates. This allows us to approximate variatio","authors_text":"Daniela Korhammer, Justin Bayer, Maximilian Karl, Patrick van der Smagt","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-19T20:30:10Z","title":"Fast Adaptive Weight Noise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.05331","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:e7b55f0b6a90c022444f67c38c05ee3dd2a8df2d09b2e3f989086c947653f3fd","target":"record","created_at":"2026-05-18T01:36:37Z","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":"4b4160ab93e9358c079eb3cd1e403d8e9a63976a8e6b43ed9fc88b092c6a77a3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-19T20:30:10Z","title_canon_sha256":"cf6ebe736e8b9c5a238a12e615bd0f23620be9b91b1e7d5fd0da35f24397767a"},"schema_version":"1.0","source":{"id":"1507.05331","kind":"arxiv","version":1}},"canonical_sha256":"92661a5eb92f83db0cd0c5124f1de959fdbf96e857a02a773b47394c1ebf30c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92661a5eb92f83db0cd0c5124f1de959fdbf96e857a02a773b47394c1ebf30c0","first_computed_at":"2026-05-18T01:36:37.177873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:36:37.177873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YfTRsZbPr+GpIANBVlzZdyh5bgj8XXgd5jPP7uBsET+WcTGBPFZeit8GfkfhF9kqPi12cR1P8R+Tb0Uma76BBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:36:37.178559Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.05331","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7b55f0b6a90c022444f67c38c05ee3dd2a8df2d09b2e3f989086c947653f3fd","sha256:dfc523a6bb7f7d424eee2ffea3778f02248b2b1cd0ca8355b6753a45f44a0108"],"state_sha256":"4fddfe0693980034f9366f9601a1fd6842ef631e1e97f555f93c6f6dd38c9fd9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RGDwlvArV8/26fJGQyVUardkX5Je3WYWECGIn+5em2wGLMCwMg/RUx33OuCOh/IHMHKRM3TjcSB2lOkZ0ys9CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T14:00:53.016111Z","bundle_sha256":"710de4f3770f322ce196e76c998e1e1706bb585d06cd4752e1e606057e442334"}}