{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EPU7NHIDXDW6NMHDWR4LFVV4DZ","short_pith_number":"pith:EPU7NHID","canonical_record":{"source":{"id":"1802.04742","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-13T17:07:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b2c1a49a998cf16aa7fa6ca0ec66ac74ff51372249ae0300b10f314c247e9476","abstract_canon_sha256":"6218be6ca76b9ff96635196310aa2bf42c0f6328c481345a3034c102e1a49512"},"schema_version":"1.0"},"canonical_sha256":"23e9f69d03b8ede6b0e3b478b2d6bc1e7692737095358136672b558a7b52719c","source":{"kind":"arxiv","id":"1802.04742","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04742","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04742v2","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04742","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"EPU7NHIDXDW6","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EPU7NHIDXDW6NMHD","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EPU7NHID","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EPU7NHIDXDW6NMHDWR4LFVV4DZ","target":"record","payload":{"canonical_record":{"source":{"id":"1802.04742","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-13T17:07:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b2c1a49a998cf16aa7fa6ca0ec66ac74ff51372249ae0300b10f314c247e9476","abstract_canon_sha256":"6218be6ca76b9ff96635196310aa2bf42c0f6328c481345a3034c102e1a49512"},"schema_version":"1.0"},"canonical_sha256":"23e9f69d03b8ede6b0e3b478b2d6bc1e7692737095358136672b558a7b52719c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:04.948205Z","signature_b64":"WCFlR4OZqgxHUBPNSEuplDDp+YNY8znIGPdgZQoFGDQ9ZzZhjtoyxMlWtPvcBTjFeLSapJLqQ1qfucXnxgP0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23e9f69d03b8ede6b0e3b478b2d6bc1e7692737095358136672b558a7b52719c","last_reissued_at":"2026-05-18T00:15:04.947607Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:04.947607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.04742","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1NYkAzc9+Raio3hOHEqGZUMGpUQyZnKCH12akoJ6+ILf9V0Q9GDSxfbG/pCMNNRBfBtVuMsw2cFzKUb6XACaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T12:10:15.841767Z"},"content_sha256":"56a6cdaf5b9b1c50042af1b4a9d5442be3b1f3224a06954ace0905ad7f999cc0","schema_version":"1.0","event_id":"sha256:56a6cdaf5b9b1c50042af1b4a9d5442be3b1f3224a06954ace0905ad7f999cc0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EPU7NHIDXDW6NMHDWR4LFVV4DZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Auroop R. Ganguly, Evan Kodra, Jennifer Dy, Ramakrishna Nemani, Sangram Ganguly, Thomas Vandal","submitted_at":"2018-02-13T17:07:13Z","abstract_excerpt":"Deep Learning (DL) methods have been transforming computer vision with innovative adaptations to other domains including climate change. For DL to pervade Science and Engineering (S&E) applications where risk management is a core component, well-characterized uncertainty estimates must accompany predictions. However, S&E observations and model-simulations often follow heavily skewed distributions and are not well modeled with DL approaches, since they usually optimize a Gaussian, or Euclidean, likelihood loss. Recent developments in Bayesian Deep Learning (BDL), which attempts to capture uncer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04742","kind":"arxiv","version":2},"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":"2026-05-18T00:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"beurk3nTiOcDU0uoe+D23TJ2rFT5f2pDKTMzriNEAnuSgzcMeUsRArgYVdFzLKylfEiWbNYWRcUF41Ujnm5KAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T12:10:15.842118Z"},"content_sha256":"a20e718230aa3cf77e85edafce510f6cbca03b65c8feadecfac9894675df92f1","schema_version":"1.0","event_id":"sha256:a20e718230aa3cf77e85edafce510f6cbca03b65c8feadecfac9894675df92f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPU7NHIDXDW6NMHDWR4LFVV4DZ/bundle.json","state_url":"https://pith.science/pith/EPU7NHIDXDW6NMHDWR4LFVV4DZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPU7NHIDXDW6NMHDWR4LFVV4DZ/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":"2026-05-28T12:10:15Z","links":{"resolver":"https://pith.science/pith/EPU7NHIDXDW6NMHDWR4LFVV4DZ","bundle":"https://pith.science/pith/EPU7NHIDXDW6NMHDWR4LFVV4DZ/bundle.json","state":"https://pith.science/pith/EPU7NHIDXDW6NMHDWR4LFVV4DZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPU7NHIDXDW6NMHDWR4LFVV4DZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EPU7NHIDXDW6NMHDWR4LFVV4DZ","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":"6218be6ca76b9ff96635196310aa2bf42c0f6328c481345a3034c102e1a49512","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-13T17:07:13Z","title_canon_sha256":"b2c1a49a998cf16aa7fa6ca0ec66ac74ff51372249ae0300b10f314c247e9476"},"schema_version":"1.0","source":{"id":"1802.04742","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04742","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04742v2","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04742","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"EPU7NHIDXDW6","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EPU7NHIDXDW6NMHD","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EPU7NHID","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:a20e718230aa3cf77e85edafce510f6cbca03b65c8feadecfac9894675df92f1","target":"graph","created_at":"2026-05-18T00:15:04Z","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 (DL) methods have been transforming computer vision with innovative adaptations to other domains including climate change. For DL to pervade Science and Engineering (S&E) applications where risk management is a core component, well-characterized uncertainty estimates must accompany predictions. However, S&E observations and model-simulations often follow heavily skewed distributions and are not well modeled with DL approaches, since they usually optimize a Gaussian, or Euclidean, likelihood loss. Recent developments in Bayesian Deep Learning (BDL), which attempts to capture uncer","authors_text":"Auroop R. Ganguly, Evan Kodra, Jennifer Dy, Ramakrishna Nemani, Sangram Ganguly, Thomas Vandal","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-13T17:07:13Z","title":"Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04742","kind":"arxiv","version":2},"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":"sha256:56a6cdaf5b9b1c50042af1b4a9d5442be3b1f3224a06954ace0905ad7f999cc0","target":"record","created_at":"2026-05-18T00:15:04Z","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":"6218be6ca76b9ff96635196310aa2bf42c0f6328c481345a3034c102e1a49512","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-13T17:07:13Z","title_canon_sha256":"b2c1a49a998cf16aa7fa6ca0ec66ac74ff51372249ae0300b10f314c247e9476"},"schema_version":"1.0","source":{"id":"1802.04742","kind":"arxiv","version":2}},"canonical_sha256":"23e9f69d03b8ede6b0e3b478b2d6bc1e7692737095358136672b558a7b52719c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23e9f69d03b8ede6b0e3b478b2d6bc1e7692737095358136672b558a7b52719c","first_computed_at":"2026-05-18T00:15:04.947607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:04.947607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WCFlR4OZqgxHUBPNSEuplDDp+YNY8znIGPdgZQoFGDQ9ZzZhjtoyxMlWtPvcBTjFeLSapJLqQ1qfucXnxgP0CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:04.948205Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.04742","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56a6cdaf5b9b1c50042af1b4a9d5442be3b1f3224a06954ace0905ad7f999cc0","sha256:a20e718230aa3cf77e85edafce510f6cbca03b65c8feadecfac9894675df92f1"],"state_sha256":"0af9581391da4e7ce8127e894b2b53fdf125689917d9df5e5d881be593b1fa8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l2r0R4j92CxEICTlYWjqtDdztqK9S1vF7F5NkJ6wK4au7j1sHTnmAsqGyhsUuxYqErFlbu1OIajzfQEpqqSIDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T12:10:15.844135Z","bundle_sha256":"bdf537d4d9980649a1b90cf02fcc28a31c785068597e71cc8311c8053b1fa241"}}