{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:YJQDLFIOLGRJGPBFWGXHUQKMCQ","short_pith_number":"pith:YJQDLFIO","canonical_record":{"source":{"id":"1506.02158","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-06T14:43:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6754fb552c4aa1a7f81025dc3eb30249e7047df0ddbfd2ce5042a0db86a354c2","abstract_canon_sha256":"25a028048580c260c9fdf16c2511c2edfed6107ea9d3577bc68f9e3100a5a588"},"schema_version":"1.0"},"canonical_sha256":"c26035950e59a2933c25b1ae7a414c140a4a994095c5bd5a2780baa2a19f91b2","source":{"kind":"arxiv","id":"1506.02158","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02158","created_at":"2026-05-18T01:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02158v6","created_at":"2026-05-18T01:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02158","created_at":"2026-05-18T01:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"YJQDLFIOLGRJ","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"YJQDLFIOLGRJGPBF","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"YJQDLFIO","created_at":"2026-05-18T12:29:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:YJQDLFIOLGRJGPBFWGXHUQKMCQ","target":"record","payload":{"canonical_record":{"source":{"id":"1506.02158","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-06T14:43:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6754fb552c4aa1a7f81025dc3eb30249e7047df0ddbfd2ce5042a0db86a354c2","abstract_canon_sha256":"25a028048580c260c9fdf16c2511c2edfed6107ea9d3577bc68f9e3100a5a588"},"schema_version":"1.0"},"canonical_sha256":"c26035950e59a2933c25b1ae7a414c140a4a994095c5bd5a2780baa2a19f91b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:22:48.413015Z","signature_b64":"AfbwBiakIJDYmw2KgRcU+ZfwYaiyHJ16H3x7Y04XrtQRZu9YBM+LSar935rQPWW7m7lMtPeFjkX6mgl3rdL4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c26035950e59a2933c25b1ae7a414c140a4a994095c5bd5a2780baa2a19f91b2","last_reissued_at":"2026-05-18T01:22:48.412471Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:22:48.412471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.02158","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":"2026-05-18T01:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NhDH/30M1ZHw5jUfN9s74IM+sueeuQh6Oh7knHOg9XoLxSGk6Ey2Dpc/tUSm0Xg8kfl75Ke1wrGNk4Fh2Og3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:48:01.359757Z"},"content_sha256":"172de1ca744502282e013e300eca722ea2495cd995da5746caf78fe3db2711da","schema_version":"1.0","event_id":"sha256:172de1ca744502282e013e300eca722ea2495cd995da5746caf78fe3db2711da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:YJQDLFIOLGRJGPBFWGXHUQKMCQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference","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":"2015-06-06T14:43:40Z","abstract_excerpt":"Convolutional neural networks (CNNs) work well on large datasets. But labelled data is hard to collect, and in some applications larger amounts of data are not available. The problem then is how to use CNNs with small data -- as CNNs overfit quickly. We present an efficient Bayesian CNN, offering better robustness to over-fitting on small data than traditional approaches. This is by placing a probability distribution over the CNN's kernels. We approximate our model's intractable posterior with Bernoulli variational distributions, requiring no additional model parameters.\n  On the theoretical s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02158","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":"2026-05-18T01:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0jME4LSWMq2fOZgdB6d76pNfjG7Hd9myLDN66stVhXhHYQ4J2RXizSjkdseqs91aKfABv3+eUxTglUHBsWbvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:48:01.360343Z"},"content_sha256":"a6b01c6acda2122617c93564cf65864fdb6b78a131b7ae3c37b80235e8b75bf4","schema_version":"1.0","event_id":"sha256:a6b01c6acda2122617c93564cf65864fdb6b78a131b7ae3c37b80235e8b75bf4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YJQDLFIOLGRJGPBFWGXHUQKMCQ/bundle.json","state_url":"https://pith.science/pith/YJQDLFIOLGRJGPBFWGXHUQKMCQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YJQDLFIOLGRJGPBFWGXHUQKMCQ/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":"2026-05-25T23:48:01Z","links":{"resolver":"https://pith.science/pith/YJQDLFIOLGRJGPBFWGXHUQKMCQ","bundle":"https://pith.science/pith/YJQDLFIOLGRJGPBFWGXHUQKMCQ/bundle.json","state":"https://pith.science/pith/YJQDLFIOLGRJGPBFWGXHUQKMCQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YJQDLFIOLGRJGPBFWGXHUQKMCQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:YJQDLFIOLGRJGPBFWGXHUQKMCQ","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":"25a028048580c260c9fdf16c2511c2edfed6107ea9d3577bc68f9e3100a5a588","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-06T14:43:40Z","title_canon_sha256":"6754fb552c4aa1a7f81025dc3eb30249e7047df0ddbfd2ce5042a0db86a354c2"},"schema_version":"1.0","source":{"id":"1506.02158","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02158","created_at":"2026-05-18T01:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02158v6","created_at":"2026-05-18T01:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02158","created_at":"2026-05-18T01:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"YJQDLFIOLGRJ","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"YJQDLFIOLGRJGPBF","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"YJQDLFIO","created_at":"2026-05-18T12:29:50Z"}],"graph_snapshots":[{"event_id":"sha256:a6b01c6acda2122617c93564cf65864fdb6b78a131b7ae3c37b80235e8b75bf4","target":"graph","created_at":"2026-05-18T01:22:48Z","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":"Convolutional neural networks (CNNs) work well on large datasets. But labelled data is hard to collect, and in some applications larger amounts of data are not available. The problem then is how to use CNNs with small data -- as CNNs overfit quickly. We present an efficient Bayesian CNN, offering better robustness to over-fitting on small data than traditional approaches. This is by placing a probability distribution over the CNN's kernels. We approximate our model's intractable posterior with Bernoulli variational distributions, requiring no additional model parameters.\n  On the theoretical s","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":"2015-06-06T14:43:40Z","title":"Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02158","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":"sha256:172de1ca744502282e013e300eca722ea2495cd995da5746caf78fe3db2711da","target":"record","created_at":"2026-05-18T01:22:48Z","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":"25a028048580c260c9fdf16c2511c2edfed6107ea9d3577bc68f9e3100a5a588","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-06T14:43:40Z","title_canon_sha256":"6754fb552c4aa1a7f81025dc3eb30249e7047df0ddbfd2ce5042a0db86a354c2"},"schema_version":"1.0","source":{"id":"1506.02158","kind":"arxiv","version":6}},"canonical_sha256":"c26035950e59a2933c25b1ae7a414c140a4a994095c5bd5a2780baa2a19f91b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c26035950e59a2933c25b1ae7a414c140a4a994095c5bd5a2780baa2a19f91b2","first_computed_at":"2026-05-18T01:22:48.412471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:22:48.412471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AfbwBiakIJDYmw2KgRcU+ZfwYaiyHJ16H3x7Y04XrtQRZu9YBM+LSar935rQPWW7m7lMtPeFjkX6mgl3rdL4Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:22:48.413015Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.02158","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:172de1ca744502282e013e300eca722ea2495cd995da5746caf78fe3db2711da","sha256:a6b01c6acda2122617c93564cf65864fdb6b78a131b7ae3c37b80235e8b75bf4"],"state_sha256":"1983c700a182968e82530429d42a78cffb4d5da55edcd2236b02d1837bade30d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SZufakX53whvYxPqWf5/9q/QSqlbkFFeQORpIzcCvAEFMg+g2z6mETheh1eyjMCZgH1knsiyNxcbwnGUTeOGDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:48:01.363635Z","bundle_sha256":"f4ea247e3098c8dd60860b06a40823c8a8350eb8a5fd36b14c3be9ac19f3fc02"}}