{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:OMXMAGO7JMYLLGPWSMRCJQSOWA","short_pith_number":"pith:OMXMAGO7","canonical_record":{"source":{"id":"1706.00473","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-01T19:50:37Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"b525b71bcfa183d72821d6c27352aa1ad90bc123be2e7e0575fa06744c920bc7","abstract_canon_sha256":"e4b4b50197df7567019a11adeba9a4c6267154c93dd7eadac2b6ccce505dea06"},"schema_version":"1.0"},"canonical_sha256":"732ec019df4b30b599f6932224c24eb0211b5d35b6abbd92f731faf38f3bf344","source":{"kind":"arxiv","id":"1706.00473","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.00473","created_at":"2026-05-18T00:25:23Z"},{"alias_kind":"arxiv_version","alias_value":"1706.00473v4","created_at":"2026-05-18T00:25:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00473","created_at":"2026-05-18T00:25:23Z"},{"alias_kind":"pith_short_12","alias_value":"OMXMAGO7JMYL","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OMXMAGO7JMYLLGPW","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OMXMAGO7","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:OMXMAGO7JMYLLGPWSMRCJQSOWA","target":"record","payload":{"canonical_record":{"source":{"id":"1706.00473","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-01T19:50:37Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"b525b71bcfa183d72821d6c27352aa1ad90bc123be2e7e0575fa06744c920bc7","abstract_canon_sha256":"e4b4b50197df7567019a11adeba9a4c6267154c93dd7eadac2b6ccce505dea06"},"schema_version":"1.0"},"canonical_sha256":"732ec019df4b30b599f6932224c24eb0211b5d35b6abbd92f731faf38f3bf344","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:23.727865Z","signature_b64":"CuitjrpEc876f0cFpqVM2qLs3tVIJAAgrLUZB5iRAxo/A6XIzNJap0sLHkIga5ndQLACR4LLwlzThTRv7WlICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"732ec019df4b30b599f6932224c24eb0211b5d35b6abbd92f731faf38f3bf344","last_reissued_at":"2026-05-18T00:25:23.727246Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:23.727246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.00473","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:25:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2d9EPCPTHUu9tyO05sIm4qb8prbiTH/6qWFhd9arFkHcN7rbn/7oJIQtzrYULxSviQwbJeG02oWoBgQiAJ7EDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T18:43:14.633304Z"},"content_sha256":"1a817d4183aa2006c20d37fd2e82fe2a121660722ead5d35f7c0f5b5348d509b","schema_version":"1.0","event_id":"sha256:1a817d4183aa2006c20d37fd2e82fe2a121660722ead5d35f7c0f5b5348d509b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:OMXMAGO7JMYLLGPWSMRCJQSOWA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Learning: A Bayesian Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Nicholas Polson, Vadim Sokolov","submitted_at":"2017-06-01T19:50:37Z","abstract_excerpt":"Deep learning is a form of machine learning for nonlinear high dimensional pattern matching and prediction. By taking a Bayesian probabilistic perspective, we provide a number of insights into more efficient algorithms for optimisation and hyper-parameter tuning. Traditional high-dimensional data reduction techniques, such as principal component analysis (PCA), partial least squares (PLS), reduced rank regression (RRR), projection pursuit regression (PPR) are all shown to be shallow learners. Their deep learning counterparts exploit multiple deep layers of data reduction which provide predicti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00473","kind":"arxiv","version":4},"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":"2026-05-18T00:25:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V6yDndBGeVzHwx15OWdRYbmL72q23ttp8Hna8Us6CTu+Vd3EgOdn4oYSTin7dP4kmqT8G2ls5xznsmdLiHf2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T18:43:14.633664Z"},"content_sha256":"952eb29beaf11a093730031e0405d4cd6cd925e4e4faaf56d6fced3860b2dbf6","schema_version":"1.0","event_id":"sha256:952eb29beaf11a093730031e0405d4cd6cd925e4e4faaf56d6fced3860b2dbf6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OMXMAGO7JMYLLGPWSMRCJQSOWA/bundle.json","state_url":"https://pith.science/pith/OMXMAGO7JMYLLGPWSMRCJQSOWA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OMXMAGO7JMYLLGPWSMRCJQSOWA/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":"2026-06-01T18:43:14Z","links":{"resolver":"https://pith.science/pith/OMXMAGO7JMYLLGPWSMRCJQSOWA","bundle":"https://pith.science/pith/OMXMAGO7JMYLLGPWSMRCJQSOWA/bundle.json","state":"https://pith.science/pith/OMXMAGO7JMYLLGPWSMRCJQSOWA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OMXMAGO7JMYLLGPWSMRCJQSOWA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:OMXMAGO7JMYLLGPWSMRCJQSOWA","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":"e4b4b50197df7567019a11adeba9a4c6267154c93dd7eadac2b6ccce505dea06","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-01T19:50:37Z","title_canon_sha256":"b525b71bcfa183d72821d6c27352aa1ad90bc123be2e7e0575fa06744c920bc7"},"schema_version":"1.0","source":{"id":"1706.00473","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.00473","created_at":"2026-05-18T00:25:23Z"},{"alias_kind":"arxiv_version","alias_value":"1706.00473v4","created_at":"2026-05-18T00:25:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00473","created_at":"2026-05-18T00:25:23Z"},{"alias_kind":"pith_short_12","alias_value":"OMXMAGO7JMYL","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OMXMAGO7JMYLLGPW","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OMXMAGO7","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:952eb29beaf11a093730031e0405d4cd6cd925e4e4faaf56d6fced3860b2dbf6","target":"graph","created_at":"2026-05-18T00:25:23Z","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":"Deep learning is a form of machine learning for nonlinear high dimensional pattern matching and prediction. By taking a Bayesian probabilistic perspective, we provide a number of insights into more efficient algorithms for optimisation and hyper-parameter tuning. Traditional high-dimensional data reduction techniques, such as principal component analysis (PCA), partial least squares (PLS), reduced rank regression (RRR), projection pursuit regression (PPR) are all shown to be shallow learners. Their deep learning counterparts exploit multiple deep layers of data reduction which provide predicti","authors_text":"Nicholas Polson, Vadim Sokolov","cross_cats":["cs.LG","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-01T19:50:37Z","title":"Deep Learning: A Bayesian Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00473","kind":"arxiv","version":4},"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":"sha256:1a817d4183aa2006c20d37fd2e82fe2a121660722ead5d35f7c0f5b5348d509b","target":"record","created_at":"2026-05-18T00:25:23Z","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":"e4b4b50197df7567019a11adeba9a4c6267154c93dd7eadac2b6ccce505dea06","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-01T19:50:37Z","title_canon_sha256":"b525b71bcfa183d72821d6c27352aa1ad90bc123be2e7e0575fa06744c920bc7"},"schema_version":"1.0","source":{"id":"1706.00473","kind":"arxiv","version":4}},"canonical_sha256":"732ec019df4b30b599f6932224c24eb0211b5d35b6abbd92f731faf38f3bf344","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"732ec019df4b30b599f6932224c24eb0211b5d35b6abbd92f731faf38f3bf344","first_computed_at":"2026-05-18T00:25:23.727246Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:25:23.727246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CuitjrpEc876f0cFpqVM2qLs3tVIJAAgrLUZB5iRAxo/A6XIzNJap0sLHkIga5ndQLACR4LLwlzThTRv7WlICw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:25:23.727865Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.00473","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a817d4183aa2006c20d37fd2e82fe2a121660722ead5d35f7c0f5b5348d509b","sha256:952eb29beaf11a093730031e0405d4cd6cd925e4e4faaf56d6fced3860b2dbf6"],"state_sha256":"acefcb8aa586333a5df05e566f39a19c1fff7c33a13a3eb5dd73cbebfe60b6f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z1cESAquRXu3r3ATRa7DgropzI0om4/v9MdB7LhnDEzM0PjyMVqoiz8B1GRt0rwNxTXzdzz9U/cvkjlbChhMBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T18:43:14.635764Z","bundle_sha256":"f1efb919c380333ef64a9494600ce07ce63bc45b5ea715253407d8dc87964d95"}}