{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:K4FNHWG7RUIK3M4IBQPOYZZNV7","short_pith_number":"pith:K4FNHWG7","canonical_record":{"source":{"id":"1810.12278","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T17:46:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"321f51aa0598df8d3653419515d0c4ccc9e267e98d3d0bd86d19d5377a0766fa","abstract_canon_sha256":"927c8e6881fc76a22f2928f80ca0de54a974869b753d48309db2520c67fd8511"},"schema_version":"1.0"},"canonical_sha256":"570ad3d8df8d10adb3880c1eec672dafef2e5afbb74900355e1b4429adb2f828","source":{"kind":"arxiv","id":"1810.12278","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12278","created_at":"2026-05-17T23:51:14Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12278v2","created_at":"2026-05-17T23:51:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12278","created_at":"2026-05-17T23:51:14Z"},{"alias_kind":"pith_short_12","alias_value":"K4FNHWG7RUIK","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"K4FNHWG7RUIK3M4I","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"K4FNHWG7","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:K4FNHWG7RUIK3M4IBQPOYZZNV7","target":"record","payload":{"canonical_record":{"source":{"id":"1810.12278","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T17:46:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"321f51aa0598df8d3653419515d0c4ccc9e267e98d3d0bd86d19d5377a0766fa","abstract_canon_sha256":"927c8e6881fc76a22f2928f80ca0de54a974869b753d48309db2520c67fd8511"},"schema_version":"1.0"},"canonical_sha256":"570ad3d8df8d10adb3880c1eec672dafef2e5afbb74900355e1b4429adb2f828","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:14.088560Z","signature_b64":"zR5y8uqBDMUgJIdw36hEA9hRTX4eILJrQ/6HTdbanxb3ME3XahIkEu1LIxm98A99/thsryYffVtssEgdbaPkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"570ad3d8df8d10adb3880c1eec672dafef2e5afbb74900355e1b4429adb2f828","last_reissued_at":"2026-05-17T23:51:14.088039Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:14.088039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.12278","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":"2026-05-17T23:51:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lcUkZ5nMGRQcSCThuxGiVu4KuS2Uv/HLryQDnnlBaNCvZhniPFSbBT3g0XY85/J3HfLfD64qicAOrWJNPmx0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:57:29.561078Z"},"content_sha256":"c597d91b4fc92eee55c8980e6e8854f926318c8e86bffb60d17fa44f20cd619e","schema_version":"1.0","event_id":"sha256:c597d91b4fc92eee55c8980e6e8854f926318c8e86bffb60d17fa44f20cd619e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:K4FNHWG7RUIK3M4IBQPOYZZNV7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Principled Uncertainty Estimation for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ethan M. Rudd, Richard Harang","submitted_at":"2018-10-29T17:46:55Z","abstract_excerpt":"When the cost of misclassifying a sample is high, it is useful to have an accurate estimate of uncertainty in the prediction for that sample. There are also multiple types of uncertainty which are best estimated in different ways, for example, uncertainty that is intrinsic to the training set may be well-handled by a Bayesian approach, while uncertainty introduced by shifts between training and query distributions may be better-addressed by density/support estimation. In this paper, we examine three types of uncertainty: model capacity uncertainty, intrinsic data uncertainty, and open set unce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12278","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":"2026-05-17T23:51:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E/bnerS1AEM1jII2gVK5yCc4Cee+CU5eFk01qzEm5fENFyeX0yXQgvVsF0aiVSxnlLIYHmD+bCNCv7Q3JDTGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:57:29.561733Z"},"content_sha256":"6546d70748087491b5608d6eed70b1d4d0be4793dfb146ea954f5012bb2bf1f7","schema_version":"1.0","event_id":"sha256:6546d70748087491b5608d6eed70b1d4d0be4793dfb146ea954f5012bb2bf1f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K4FNHWG7RUIK3M4IBQPOYZZNV7/bundle.json","state_url":"https://pith.science/pith/K4FNHWG7RUIK3M4IBQPOYZZNV7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K4FNHWG7RUIK3M4IBQPOYZZNV7/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":"2026-05-27T14:57:29Z","links":{"resolver":"https://pith.science/pith/K4FNHWG7RUIK3M4IBQPOYZZNV7","bundle":"https://pith.science/pith/K4FNHWG7RUIK3M4IBQPOYZZNV7/bundle.json","state":"https://pith.science/pith/K4FNHWG7RUIK3M4IBQPOYZZNV7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K4FNHWG7RUIK3M4IBQPOYZZNV7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:K4FNHWG7RUIK3M4IBQPOYZZNV7","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":"927c8e6881fc76a22f2928f80ca0de54a974869b753d48309db2520c67fd8511","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T17:46:55Z","title_canon_sha256":"321f51aa0598df8d3653419515d0c4ccc9e267e98d3d0bd86d19d5377a0766fa"},"schema_version":"1.0","source":{"id":"1810.12278","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12278","created_at":"2026-05-17T23:51:14Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12278v2","created_at":"2026-05-17T23:51:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12278","created_at":"2026-05-17T23:51:14Z"},{"alias_kind":"pith_short_12","alias_value":"K4FNHWG7RUIK","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"K4FNHWG7RUIK3M4I","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"K4FNHWG7","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:6546d70748087491b5608d6eed70b1d4d0be4793dfb146ea954f5012bb2bf1f7","target":"graph","created_at":"2026-05-17T23:51:14Z","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":"When the cost of misclassifying a sample is high, it is useful to have an accurate estimate of uncertainty in the prediction for that sample. There are also multiple types of uncertainty which are best estimated in different ways, for example, uncertainty that is intrinsic to the training set may be well-handled by a Bayesian approach, while uncertainty introduced by shifts between training and query distributions may be better-addressed by density/support estimation. In this paper, we examine three types of uncertainty: model capacity uncertainty, intrinsic data uncertainty, and open set unce","authors_text":"Ethan M. Rudd, Richard Harang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T17:46:55Z","title":"Towards Principled Uncertainty Estimation for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12278","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:c597d91b4fc92eee55c8980e6e8854f926318c8e86bffb60d17fa44f20cd619e","target":"record","created_at":"2026-05-17T23:51:14Z","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":"927c8e6881fc76a22f2928f80ca0de54a974869b753d48309db2520c67fd8511","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T17:46:55Z","title_canon_sha256":"321f51aa0598df8d3653419515d0c4ccc9e267e98d3d0bd86d19d5377a0766fa"},"schema_version":"1.0","source":{"id":"1810.12278","kind":"arxiv","version":2}},"canonical_sha256":"570ad3d8df8d10adb3880c1eec672dafef2e5afbb74900355e1b4429adb2f828","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"570ad3d8df8d10adb3880c1eec672dafef2e5afbb74900355e1b4429adb2f828","first_computed_at":"2026-05-17T23:51:14.088039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:14.088039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zR5y8uqBDMUgJIdw36hEA9hRTX4eILJrQ/6HTdbanxb3ME3XahIkEu1LIxm98A99/thsryYffVtssEgdbaPkCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:14.088560Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.12278","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c597d91b4fc92eee55c8980e6e8854f926318c8e86bffb60d17fa44f20cd619e","sha256:6546d70748087491b5608d6eed70b1d4d0be4793dfb146ea954f5012bb2bf1f7"],"state_sha256":"e4bd67ebd56a55a01ded6c7554fa3787e4ef277e9af161bd23f184c2e8faa33a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hx7I/jtqrY0jQMVywYQEs4ZrWrjIfu4V1ZPpZ3UHiAIT0+vNlgVHYy25WC0VfQrn4VFgN9KlBVWCUG0JAFkoCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:57:29.565394Z","bundle_sha256":"650eea6101482740011e0f8963451c4b6740e0f216818e40cc660b4eb86bdaba"}}