{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:C3XFMGLEOTVD3RANTT3VDP4KHY","short_pith_number":"pith:C3XFMGLE","canonical_record":{"source":{"id":"1506.02157","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-06T14:42:06Z","cross_cats_sorted":[],"title_canon_sha256":"e14718b54d24b47b503b0beab74b942d87c080566e01ebc9cbcd8422ffac37e6","abstract_canon_sha256":"47cff63c43e986445709ef2f782a0f586b131cf4c6765c712a36572e61e7c109"},"schema_version":"1.0"},"canonical_sha256":"16ee56196474ea3dc40d9cf751bf8a3e3a072423dbb5e7b6f183dd1d95ae0a1d","source":{"kind":"arxiv","id":"1506.02157","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02157","created_at":"2026-05-18T01:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02157v5","created_at":"2026-05-18T01:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02157","created_at":"2026-05-18T01:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"C3XFMGLEOTVD","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"C3XFMGLEOTVD3RAN","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"C3XFMGLE","created_at":"2026-05-18T12:29:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:C3XFMGLEOTVD3RANTT3VDP4KHY","target":"record","payload":{"canonical_record":{"source":{"id":"1506.02157","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-06T14:42:06Z","cross_cats_sorted":[],"title_canon_sha256":"e14718b54d24b47b503b0beab74b942d87c080566e01ebc9cbcd8422ffac37e6","abstract_canon_sha256":"47cff63c43e986445709ef2f782a0f586b131cf4c6765c712a36572e61e7c109"},"schema_version":"1.0"},"canonical_sha256":"16ee56196474ea3dc40d9cf751bf8a3e3a072423dbb5e7b6f183dd1d95ae0a1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:44.833402Z","signature_b64":"Pmie7+NQ7COVMWjapioqqh7fMPMqnOZoS/SZUOlq6p5JamdJHoVOIiuGrImLcwePN8zTK9f3/pTVkjXcj9zCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16ee56196474ea3dc40d9cf751bf8a3e3a072423dbb5e7b6f183dd1d95ae0a1d","last_reissued_at":"2026-05-18T01:13:44.832842Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:44.832842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.02157","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TD3pC4HUmWI8lOnpv3WHZwL8Dv4oY1F3VO6uw3UXVkn1pq7r0HhvkaR1vU08irvx0DJOyTaAwYQD11+AWZiPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T22:26:42.858797Z"},"content_sha256":"fe9ec522d990a9b1a53a487f7e2179b3c57b71d9870a9621d381e7d679d03c13","schema_version":"1.0","event_id":"sha256:fe9ec522d990a9b1a53a487f7e2179b3c57b71d9870a9621d381e7d679d03c13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:C3XFMGLEOTVD3RANTT3VDP4KHY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dropout as a Bayesian Approximation: Appendix","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Yarin Gal, Zoubin Ghahramani","submitted_at":"2015-06-06T14:42:06Z","abstract_excerpt":"We show that a neural network with arbitrary depth and non-linearities, with dropout applied before every weight layer, is mathematically equivalent to an approximation to a well known Bayesian model. This interpretation might offer an explanation to some of dropout's key properties, such as its robustness to over-fitting. Our interpretation allows us to reason about uncertainty in deep learning, and allows the introduction of the Bayesian machinery into existing deep learning frameworks in a principled way.\n  This document is an appendix for the main paper \"Dropout as a Bayesian Approximation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02157","kind":"arxiv","version":5},"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":"2026-05-18T01:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IzSWfQK+V020OrTeg7AzMDupEgG2AmYOGIXjcCfsMZyrwTXv9dtlqmqxdt9JXADoQGDH+1gWRPWurqa7DC0kDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T22:26:42.859562Z"},"content_sha256":"a05a67dc2468137b2a50425a46d01616acc6dbc04e2ef4adfa32c877bee084ce","schema_version":"1.0","event_id":"sha256:a05a67dc2468137b2a50425a46d01616acc6dbc04e2ef4adfa32c877bee084ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C3XFMGLEOTVD3RANTT3VDP4KHY/bundle.json","state_url":"https://pith.science/pith/C3XFMGLEOTVD3RANTT3VDP4KHY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C3XFMGLEOTVD3RANTT3VDP4KHY/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":"2026-06-10T22:26:42Z","links":{"resolver":"https://pith.science/pith/C3XFMGLEOTVD3RANTT3VDP4KHY","bundle":"https://pith.science/pith/C3XFMGLEOTVD3RANTT3VDP4KHY/bundle.json","state":"https://pith.science/pith/C3XFMGLEOTVD3RANTT3VDP4KHY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C3XFMGLEOTVD3RANTT3VDP4KHY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:C3XFMGLEOTVD3RANTT3VDP4KHY","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":"47cff63c43e986445709ef2f782a0f586b131cf4c6765c712a36572e61e7c109","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-06T14:42:06Z","title_canon_sha256":"e14718b54d24b47b503b0beab74b942d87c080566e01ebc9cbcd8422ffac37e6"},"schema_version":"1.0","source":{"id":"1506.02157","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02157","created_at":"2026-05-18T01:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02157v5","created_at":"2026-05-18T01:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02157","created_at":"2026-05-18T01:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"C3XFMGLEOTVD","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"C3XFMGLEOTVD3RAN","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"C3XFMGLE","created_at":"2026-05-18T12:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:a05a67dc2468137b2a50425a46d01616acc6dbc04e2ef4adfa32c877bee084ce","target":"graph","created_at":"2026-05-18T01:13:44Z","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":"We show that a neural network with arbitrary depth and non-linearities, with dropout applied before every weight layer, is mathematically equivalent to an approximation to a well known Bayesian model. This interpretation might offer an explanation to some of dropout's key properties, such as its robustness to over-fitting. Our interpretation allows us to reason about uncertainty in deep learning, and allows the introduction of the Bayesian machinery into existing deep learning frameworks in a principled way.\n  This document is an appendix for the main paper \"Dropout as a Bayesian Approximation","authors_text":"Yarin Gal, Zoubin Ghahramani","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-06T14:42:06Z","title":"Dropout as a Bayesian Approximation: Appendix"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02157","kind":"arxiv","version":5},"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:fe9ec522d990a9b1a53a487f7e2179b3c57b71d9870a9621d381e7d679d03c13","target":"record","created_at":"2026-05-18T01:13:44Z","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":"47cff63c43e986445709ef2f782a0f586b131cf4c6765c712a36572e61e7c109","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-06T14:42:06Z","title_canon_sha256":"e14718b54d24b47b503b0beab74b942d87c080566e01ebc9cbcd8422ffac37e6"},"schema_version":"1.0","source":{"id":"1506.02157","kind":"arxiv","version":5}},"canonical_sha256":"16ee56196474ea3dc40d9cf751bf8a3e3a072423dbb5e7b6f183dd1d95ae0a1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16ee56196474ea3dc40d9cf751bf8a3e3a072423dbb5e7b6f183dd1d95ae0a1d","first_computed_at":"2026-05-18T01:13:44.832842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:13:44.832842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pmie7+NQ7COVMWjapioqqh7fMPMqnOZoS/SZUOlq6p5JamdJHoVOIiuGrImLcwePN8zTK9f3/pTVkjXcj9zCDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:13:44.833402Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.02157","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe9ec522d990a9b1a53a487f7e2179b3c57b71d9870a9621d381e7d679d03c13","sha256:a05a67dc2468137b2a50425a46d01616acc6dbc04e2ef4adfa32c877bee084ce"],"state_sha256":"2dd75740c0c8ee2d4be2ca6e32e687c06d1d49f87670b92572dd340afc526042"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yzJ9c0ftc9wFPGUsQGmZ7RqJV/QjW8rnEg4Avxo5rpZZQVNWkmdAJ0LDcHYbK0G3L2yh1P5XH23Mi7RlbTWXDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T22:26:42.863769Z","bundle_sha256":"5aed27b405b37229cf27e1d41dff8dbbbdbbc82ec021d8f5012e55902d6134e5"}}