{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QDPTJYRZG55744EL3DK4SC4XOX","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":"bbb91f2f5c677185d6de44bd873d9fa415e00049d7efda50c43945f485970d4a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-05T10:43:20Z","title_canon_sha256":"dc7e997693f3b3f0b71691b92c9f5c56f21e88a268e85e90392b89bab6d5c5b4"},"schema_version":"1.0","source":{"id":"1906.01930","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.01930","created_at":"2026-07-05T01:20:10Z"},{"alias_kind":"arxiv_version","alias_value":"1906.01930v3","created_at":"2026-07-05T01:20:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01930","created_at":"2026-07-05T01:20:10Z"},{"alias_kind":"pith_short_12","alias_value":"QDPTJYRZG557","created_at":"2026-07-05T01:20:10Z"},{"alias_kind":"pith_short_16","alias_value":"QDPTJYRZG55744EL","created_at":"2026-07-05T01:20:10Z"},{"alias_kind":"pith_short_8","alias_value":"QDPTJYRZ","created_at":"2026-07-05T01:20:10Z"}],"graph_snapshots":[{"event_id":"sha256:f4fa90025646d701576fda581adabd3f9d0339d298592759ead640cc3d587aad","target":"graph","created_at":"2026-07-05T01:20:10Z","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/1906.01930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks (DNN) and Gaussian processes (GP) are two powerful models with several theoretical connections relating them, but the relationship between their training methods is not well understood. In this paper, we show that certain Gaussian posterior approximations for Bayesian DNNs are equivalent to GP posteriors. This enables us to relate solutions and iterations of a deep-learning algorithm to GP inference. As a result, we can obtain a GP kernel and a nonlinear feature map while training a DNN. Surprisingly, the resulting kernel is the neural tangent kernel. We show kernels obtai","authors_text":"Alexander Immer, Ehsan Abedi, Maciej Korzepa, Mohammad Emtiyaz Khan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-05T10:43:20Z","title":"Approximate Inference Turns Deep Networks into Gaussian Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01930","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":"sha256:4a581863fb3cc7d04d095b52ebe44d949546815994213f44dd0509d1ff4977e7","target":"record","created_at":"2026-07-05T01:20:10Z","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":"bbb91f2f5c677185d6de44bd873d9fa415e00049d7efda50c43945f485970d4a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-05T10:43:20Z","title_canon_sha256":"dc7e997693f3b3f0b71691b92c9f5c56f21e88a268e85e90392b89bab6d5c5b4"},"schema_version":"1.0","source":{"id":"1906.01930","kind":"arxiv","version":3}},"canonical_sha256":"80df34e239377bfe708bd8d5c90b9775d7f3b6dcb17198f000815e6a263ebb80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80df34e239377bfe708bd8d5c90b9775d7f3b6dcb17198f000815e6a263ebb80","first_computed_at":"2026-07-05T01:20:10.918441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:20:10.918441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O4Ss/cCoPwoOX5hseAKL+TICLNa6i+jZREAxZGxZAaIGk/4aD0oifBH45N7yd8xO9J6P9sEXwWvKj1Cg3qM1CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:20:10.918897Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.01930","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a581863fb3cc7d04d095b52ebe44d949546815994213f44dd0509d1ff4977e7","sha256:f4fa90025646d701576fda581adabd3f9d0339d298592759ead640cc3d587aad"],"state_sha256":"4195dca3b73938f2da012750b2528d7c3aa8fdb3f266e4d50fffa18956d496f1"}