{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RB3GLOASQDXR5DFW2TDBHWAA3M","short_pith_number":"pith:RB3GLOAS","canonical_record":{"source":{"id":"1811.12565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-30T01:12:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1a18c11c43fecde541adfca3d047a05bd4452dbace00a2f866ca50a2cb0205eb","abstract_canon_sha256":"c97415c83dafd3f49204da62f07aa3dae485cb97538cb579ffea829469da26d0"},"schema_version":"1.0"},"canonical_sha256":"887665b81280ef1e8cb6d4c613d800db0419a0e2f7a1b0151417fe47150b5ff9","source":{"kind":"arxiv","id":"1811.12565","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.12565","created_at":"2026-05-17T23:59:29Z"},{"alias_kind":"arxiv_version","alias_value":"1811.12565v1","created_at":"2026-05-17T23:59:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12565","created_at":"2026-05-17T23:59:29Z"},{"alias_kind":"pith_short_12","alias_value":"RB3GLOASQDXR","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RB3GLOASQDXR5DFW","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RB3GLOAS","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RB3GLOASQDXR5DFW2TDBHWAA3M","target":"record","payload":{"canonical_record":{"source":{"id":"1811.12565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-30T01:12:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1a18c11c43fecde541adfca3d047a05bd4452dbace00a2f866ca50a2cb0205eb","abstract_canon_sha256":"c97415c83dafd3f49204da62f07aa3dae485cb97538cb579ffea829469da26d0"},"schema_version":"1.0"},"canonical_sha256":"887665b81280ef1e8cb6d4c613d800db0419a0e2f7a1b0151417fe47150b5ff9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:29.263073Z","signature_b64":"LDas8idliDa4eb3mn3fgj68G3x4gJ82MM5mlgJFySHaZr34sqtUHQ5fUNAn9vWqmu3jh4Um1YwiIhcHviO+rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"887665b81280ef1e8cb6d4c613d800db0419a0e2f7a1b0151417fe47150b5ff9","last_reissued_at":"2026-05-17T23:59:29.262370Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:29.262370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.12565","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":"2026-05-17T23:59:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"enkTRghgtNxKaKEMz0ufUm2au6sqFfYYV+54dZJZODrKak2D/02htBDtMNw4UbOGMVBqbzBjzGPJgwWYE2M8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T03:34:01.838188Z"},"content_sha256":"83ee41013bd2513552a91e8576a99f148f8815f0645ec761df587444e897e31e","schema_version":"1.0","event_id":"sha256:83ee41013bd2513552a91e8576a99f148f8815f0645ec761df587444e897e31e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RB3GLOASQDXR5DFW2TDBHWAA3M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Eigenvalue Corrected Noisy Natural Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guodong Zhang, Juhan Bae, Roger Grosse","submitted_at":"2018-11-30T01:12:51Z","abstract_excerpt":"Variational Bayesian neural networks combine the flexibility of deep learning with Bayesian uncertainty estimation. However, inference procedures for flexible variational posteriors are computationally expensive. A recently proposed method, noisy natural gradient, is a surprisingly simple method to fit expressive posteriors by adding weight noise to regular natural gradient updates. Noisy K-FAC is an instance of noisy natural gradient that fits a matrix-variate Gaussian posterior with minor changes to ordinary K-FAC. Nevertheless, a matrix-variate Gaussian posterior does not capture an accurat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12565","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":"2026-05-17T23:59:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VWeRBrkuvGFiXd2NIijA9b9N60SCRlUBonWpPia36AdgrLQ4KMZu0vfOmyeeujoVj6YthWYnQIVXuEfDp+w6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T03:34:01.838549Z"},"content_sha256":"ae98df63372313500f89bb7cc28c281e592945997aa6727daa4e626f0073fb1c","schema_version":"1.0","event_id":"sha256:ae98df63372313500f89bb7cc28c281e592945997aa6727daa4e626f0073fb1c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RB3GLOASQDXR5DFW2TDBHWAA3M/bundle.json","state_url":"https://pith.science/pith/RB3GLOASQDXR5DFW2TDBHWAA3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RB3GLOASQDXR5DFW2TDBHWAA3M/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":"2026-06-30T03:34:01Z","links":{"resolver":"https://pith.science/pith/RB3GLOASQDXR5DFW2TDBHWAA3M","bundle":"https://pith.science/pith/RB3GLOASQDXR5DFW2TDBHWAA3M/bundle.json","state":"https://pith.science/pith/RB3GLOASQDXR5DFW2TDBHWAA3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RB3GLOASQDXR5DFW2TDBHWAA3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RB3GLOASQDXR5DFW2TDBHWAA3M","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":"c97415c83dafd3f49204da62f07aa3dae485cb97538cb579ffea829469da26d0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-30T01:12:51Z","title_canon_sha256":"1a18c11c43fecde541adfca3d047a05bd4452dbace00a2f866ca50a2cb0205eb"},"schema_version":"1.0","source":{"id":"1811.12565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.12565","created_at":"2026-05-17T23:59:29Z"},{"alias_kind":"arxiv_version","alias_value":"1811.12565v1","created_at":"2026-05-17T23:59:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12565","created_at":"2026-05-17T23:59:29Z"},{"alias_kind":"pith_short_12","alias_value":"RB3GLOASQDXR","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RB3GLOASQDXR5DFW","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RB3GLOAS","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:ae98df63372313500f89bb7cc28c281e592945997aa6727daa4e626f0073fb1c","target":"graph","created_at":"2026-05-17T23:59:29Z","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 Bayesian neural networks combine the flexibility of deep learning with Bayesian uncertainty estimation. However, inference procedures for flexible variational posteriors are computationally expensive. A recently proposed method, noisy natural gradient, is a surprisingly simple method to fit expressive posteriors by adding weight noise to regular natural gradient updates. Noisy K-FAC is an instance of noisy natural gradient that fits a matrix-variate Gaussian posterior with minor changes to ordinary K-FAC. Nevertheless, a matrix-variate Gaussian posterior does not capture an accurat","authors_text":"Guodong Zhang, Juhan Bae, Roger Grosse","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-30T01:12:51Z","title":"Eigenvalue Corrected Noisy Natural Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12565","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":"sha256:83ee41013bd2513552a91e8576a99f148f8815f0645ec761df587444e897e31e","target":"record","created_at":"2026-05-17T23:59:29Z","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":"c97415c83dafd3f49204da62f07aa3dae485cb97538cb579ffea829469da26d0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-30T01:12:51Z","title_canon_sha256":"1a18c11c43fecde541adfca3d047a05bd4452dbace00a2f866ca50a2cb0205eb"},"schema_version":"1.0","source":{"id":"1811.12565","kind":"arxiv","version":1}},"canonical_sha256":"887665b81280ef1e8cb6d4c613d800db0419a0e2f7a1b0151417fe47150b5ff9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"887665b81280ef1e8cb6d4c613d800db0419a0e2f7a1b0151417fe47150b5ff9","first_computed_at":"2026-05-17T23:59:29.262370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:29.262370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LDas8idliDa4eb3mn3fgj68G3x4gJ82MM5mlgJFySHaZr34sqtUHQ5fUNAn9vWqmu3jh4Um1YwiIhcHviO+rDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:29.263073Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.12565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83ee41013bd2513552a91e8576a99f148f8815f0645ec761df587444e897e31e","sha256:ae98df63372313500f89bb7cc28c281e592945997aa6727daa4e626f0073fb1c"],"state_sha256":"f21edd370f4a96a639e858771621f4ce1b46a6a101eba6cddcab0e488a40781a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"InRqwCdKyRIZX83vKRN2YBiRFqSKnLu2uhQoDC+3Wow8lv9obBGvUmzJSeDVemLc4UcSvjQSR3XFRFeLtc32Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T03:34:01.840384Z","bundle_sha256":"2f37d861cbcafdf75696c142d0a8df2e1b896fcbf11cf9f89082d550984cb1f5"}}