{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:GE26DYUMMUVKZSK7RGIWDAXH57","short_pith_number":"pith:GE26DYUM","canonical_record":{"source":{"id":"1506.02142","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-06T12:30:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"09571a420eb15afd0e2965bbc6324e492878ace5914bee473ad6f7e0d8c78849","abstract_canon_sha256":"b369f0d0620082dfed9001286e75baf86c048744b4b7d7423f209bbd23514638"},"schema_version":"1.0"},"canonical_sha256":"3135e1e28c652aacc95f89916182e7efcc11357748453db7643f7dd1b07a07b7","source":{"kind":"arxiv","id":"1506.02142","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02142","created_at":"2026-05-18T01:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02142v6","created_at":"2026-05-18T01:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02142","created_at":"2026-05-18T01:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"GE26DYUMMUVK","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"GE26DYUMMUVKZSK7","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"GE26DYUM","created_at":"2026-05-18T12:29:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:GE26DYUMMUVKZSK7RGIWDAXH57","target":"record","payload":{"canonical_record":{"source":{"id":"1506.02142","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-06T12:30:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"09571a420eb15afd0e2965bbc6324e492878ace5914bee473ad6f7e0d8c78849","abstract_canon_sha256":"b369f0d0620082dfed9001286e75baf86c048744b4b7d7423f209bbd23514638"},"schema_version":"1.0"},"canonical_sha256":"3135e1e28c652aacc95f89916182e7efcc11357748453db7643f7dd1b07a07b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:20.454999Z","signature_b64":"/ohUwPmVfieurgJZC+XE0Xmq+6MY96RkUbOeCQ3CbHuP08p3sKPvQ7gLJv37BRy3+HPRJB/J0E2wEZmOgXiRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3135e1e28c652aacc95f89916182e7efcc11357748453db7643f7dd1b07a07b7","last_reissued_at":"2026-05-18T01:03:20.454109Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:20.454109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.02142","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:03:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RCy3VyE6cadrNS5V4CCWYYmtk0zkNIrsQNbcKz9iz4KHCEmzFfoQOqd4u6YOIi9E61d9Z0YvdL2ilnKgGuh8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T13:10:56.105982Z"},"content_sha256":"714866a258571b802f81bd9221d19cbe7287d4086e2d08646e809f29a04a43a2","schema_version":"1.0","event_id":"sha256:714866a258571b802f81bd9221d19cbe7287d4086e2d08646e809f29a04a43a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:GE26DYUMMUVKZSK7RGIWDAXH57","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Yarin Gal, Zoubin Ghahramani","submitted_at":"2015-06-06T12:30:43Z","abstract_excerpt":"Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with a prohibitive computational cost. In this paper we develop a new theoretical framework casting dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes. A direct result of this theory gives us tools to model uncertainty with dropout NNs -- extracting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02142","kind":"arxiv","version":6},"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":"2026-05-18T01:03:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ncRIsx2tX+RdS6HsCBJp9AasDUazTKhzbc0QWw2Yek5AGetfFZxI4YoRy0s4lgyNRRaiJ74hDmWsexhpoXB3Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T13:10:56.106742Z"},"content_sha256":"23ed9ab2f79953ac6247ab3196a66f1c380a56b83f92ac8c3fb09ee40f13fabd","schema_version":"1.0","event_id":"sha256:23ed9ab2f79953ac6247ab3196a66f1c380a56b83f92ac8c3fb09ee40f13fabd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GE26DYUMMUVKZSK7RGIWDAXH57/bundle.json","state_url":"https://pith.science/pith/GE26DYUMMUVKZSK7RGIWDAXH57/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GE26DYUMMUVKZSK7RGIWDAXH57/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":"2026-06-10T13:10:56Z","links":{"resolver":"https://pith.science/pith/GE26DYUMMUVKZSK7RGIWDAXH57","bundle":"https://pith.science/pith/GE26DYUMMUVKZSK7RGIWDAXH57/bundle.json","state":"https://pith.science/pith/GE26DYUMMUVKZSK7RGIWDAXH57/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GE26DYUMMUVKZSK7RGIWDAXH57/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:GE26DYUMMUVKZSK7RGIWDAXH57","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":"b369f0d0620082dfed9001286e75baf86c048744b4b7d7423f209bbd23514638","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-06T12:30:43Z","title_canon_sha256":"09571a420eb15afd0e2965bbc6324e492878ace5914bee473ad6f7e0d8c78849"},"schema_version":"1.0","source":{"id":"1506.02142","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02142","created_at":"2026-05-18T01:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02142v6","created_at":"2026-05-18T01:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02142","created_at":"2026-05-18T01:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"GE26DYUMMUVK","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"GE26DYUMMUVKZSK7","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"GE26DYUM","created_at":"2026-05-18T12:29:22Z"}],"graph_snapshots":[{"event_id":"sha256:23ed9ab2f79953ac6247ab3196a66f1c380a56b83f92ac8c3fb09ee40f13fabd","target":"graph","created_at":"2026-05-18T01:03:20Z","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 tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with a prohibitive computational cost. In this paper we develop a new theoretical framework casting dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes. A direct result of this theory gives us tools to model uncertainty with dropout NNs -- extracting","authors_text":"Yarin Gal, Zoubin Ghahramani","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-06T12:30:43Z","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02142","kind":"arxiv","version":6},"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":"sha256:714866a258571b802f81bd9221d19cbe7287d4086e2d08646e809f29a04a43a2","target":"record","created_at":"2026-05-18T01:03:20Z","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":"b369f0d0620082dfed9001286e75baf86c048744b4b7d7423f209bbd23514638","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-06T12:30:43Z","title_canon_sha256":"09571a420eb15afd0e2965bbc6324e492878ace5914bee473ad6f7e0d8c78849"},"schema_version":"1.0","source":{"id":"1506.02142","kind":"arxiv","version":6}},"canonical_sha256":"3135e1e28c652aacc95f89916182e7efcc11357748453db7643f7dd1b07a07b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3135e1e28c652aacc95f89916182e7efcc11357748453db7643f7dd1b07a07b7","first_computed_at":"2026-05-18T01:03:20.454109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:20.454109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/ohUwPmVfieurgJZC+XE0Xmq+6MY96RkUbOeCQ3CbHuP08p3sKPvQ7gLJv37BRy3+HPRJB/J0E2wEZmOgXiRCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:20.454999Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.02142","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:714866a258571b802f81bd9221d19cbe7287d4086e2d08646e809f29a04a43a2","sha256:23ed9ab2f79953ac6247ab3196a66f1c380a56b83f92ac8c3fb09ee40f13fabd"],"state_sha256":"735636d6d8088c330a8e7b8ebf1d6ed8bf24b692aa5b1d3e3e7dbf09497ad125"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WuHwxPqNmcMVmXrgKCgaUdhaDDSkU+I8CNvQcVLQtXCDcRWPXztT2LCu0c6mtyFDd4EeRL+yhBhVmW4d5YBaBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T13:10:56.111869Z","bundle_sha256":"0bcd1c04ae2d28755189391b847755fc4080c20b28c893f57932c6ea892ffe27"}}