{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3LXU4WOXYBU3SZJW3WY6ACBMG5","short_pith_number":"pith:3LXU4WOX","canonical_record":{"source":{"id":"1703.04977","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-15T07:27:12Z","cross_cats_sorted":[],"title_canon_sha256":"467eb61183d148039a2e9aaa6762a4d9d24c983b6f829f7e7f13b3a989dd747f","abstract_canon_sha256":"e848489f6eb368466a58a452b5293dd65c885088bd689ddc6a22f3cd74faa4ac"},"schema_version":"1.0"},"canonical_sha256":"daef4e59d7c069b96536ddb1e0082c377d357f81552c71af9ad40c4dc715c5d8","source":{"kind":"arxiv","id":"1703.04977","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.04977","created_at":"2026-05-18T00:33:39Z"},{"alias_kind":"arxiv_version","alias_value":"1703.04977v2","created_at":"2026-05-18T00:33:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04977","created_at":"2026-05-18T00:33:39Z"},{"alias_kind":"pith_short_12","alias_value":"3LXU4WOXYBU3","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3LXU4WOXYBU3SZJW","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3LXU4WOX","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3LXU4WOXYBU3SZJW3WY6ACBMG5","target":"record","payload":{"canonical_record":{"source":{"id":"1703.04977","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-15T07:27:12Z","cross_cats_sorted":[],"title_canon_sha256":"467eb61183d148039a2e9aaa6762a4d9d24c983b6f829f7e7f13b3a989dd747f","abstract_canon_sha256":"e848489f6eb368466a58a452b5293dd65c885088bd689ddc6a22f3cd74faa4ac"},"schema_version":"1.0"},"canonical_sha256":"daef4e59d7c069b96536ddb1e0082c377d357f81552c71af9ad40c4dc715c5d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:39.352371Z","signature_b64":"Vh9KOedjww18FZPhE/g2G42gIb5j05QovcJR3HeUU8FPrQfO/9tr7GLj4b3LkShOzRVLOQDv0Ni5kskJNHf4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"daef4e59d7c069b96536ddb1e0082c377d357f81552c71af9ad40c4dc715c5d8","last_reissued_at":"2026-05-18T00:33:39.351708Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:39.351708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.04977","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":"2026-05-18T00:33:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PoYPpaBfFCzOB8QrmcHIEYxokc35cKhHBBWB8ZqJH/EjgiVLlwg2uA3C1TXv/fMl9DwNe1PgKdqtA3vn8BtKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T06:47:49.459346Z"},"content_sha256":"2de224a3e70f0a26c95e36daa1f922ff2d1bd0cc904bf90fb959361517f18ab3","schema_version":"1.0","event_id":"sha256:2de224a3e70f0a26c95e36daa1f922ff2d1bd0cc904bf90fb959361517f18ab3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3LXU4WOXYBU3SZJW3WY6ACBMG5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Kendall, Yarin Gal","submitted_at":"2017-03-15T07:27:12Z","abstract_excerpt":"There are two major types of uncertainty one can model. Aleatoric uncertainty captures noise inherent in the observations. On the other hand, epistemic uncertainty accounts for uncertainty in the model -- uncertainty which can be explained away given enough data. Traditionally it has been difficult to model epistemic uncertainty in computer vision, but with new Bayesian deep learning tools this is now possible. We study the benefits of modeling epistemic vs. aleatoric uncertainty in Bayesian deep learning models for vision tasks. For this we present a Bayesian deep learning framework combining"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04977","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":"2026-05-18T00:33:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HRPBfNGhB+NjGJX8aaekI63hqTEg8i+fD3cVD/mwjcrTUjd7IO9hYvKn30CI4GKZyFbYvCf9IiCn+P/2y4HwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T06:47:49.460036Z"},"content_sha256":"42d1c3317e3f9393c792168ebbf79d1f17e3235d11dbb10431508ae91f0e5af0","schema_version":"1.0","event_id":"sha256:42d1c3317e3f9393c792168ebbf79d1f17e3235d11dbb10431508ae91f0e5af0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3LXU4WOXYBU3SZJW3WY6ACBMG5/bundle.json","state_url":"https://pith.science/pith/3LXU4WOXYBU3SZJW3WY6ACBMG5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3LXU4WOXYBU3SZJW3WY6ACBMG5/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":"2026-06-11T06:47:49Z","links":{"resolver":"https://pith.science/pith/3LXU4WOXYBU3SZJW3WY6ACBMG5","bundle":"https://pith.science/pith/3LXU4WOXYBU3SZJW3WY6ACBMG5/bundle.json","state":"https://pith.science/pith/3LXU4WOXYBU3SZJW3WY6ACBMG5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3LXU4WOXYBU3SZJW3WY6ACBMG5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3LXU4WOXYBU3SZJW3WY6ACBMG5","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":"e848489f6eb368466a58a452b5293dd65c885088bd689ddc6a22f3cd74faa4ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-15T07:27:12Z","title_canon_sha256":"467eb61183d148039a2e9aaa6762a4d9d24c983b6f829f7e7f13b3a989dd747f"},"schema_version":"1.0","source":{"id":"1703.04977","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.04977","created_at":"2026-05-18T00:33:39Z"},{"alias_kind":"arxiv_version","alias_value":"1703.04977v2","created_at":"2026-05-18T00:33:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04977","created_at":"2026-05-18T00:33:39Z"},{"alias_kind":"pith_short_12","alias_value":"3LXU4WOXYBU3","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3LXU4WOXYBU3SZJW","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3LXU4WOX","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:42d1c3317e3f9393c792168ebbf79d1f17e3235d11dbb10431508ae91f0e5af0","target":"graph","created_at":"2026-05-18T00:33:39Z","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":"There are two major types of uncertainty one can model. Aleatoric uncertainty captures noise inherent in the observations. On the other hand, epistemic uncertainty accounts for uncertainty in the model -- uncertainty which can be explained away given enough data. Traditionally it has been difficult to model epistemic uncertainty in computer vision, but with new Bayesian deep learning tools this is now possible. We study the benefits of modeling epistemic vs. aleatoric uncertainty in Bayesian deep learning models for vision tasks. For this we present a Bayesian deep learning framework combining","authors_text":"Alex Kendall, Yarin Gal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-15T07:27:12Z","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04977","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":"sha256:2de224a3e70f0a26c95e36daa1f922ff2d1bd0cc904bf90fb959361517f18ab3","target":"record","created_at":"2026-05-18T00:33:39Z","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":"e848489f6eb368466a58a452b5293dd65c885088bd689ddc6a22f3cd74faa4ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-15T07:27:12Z","title_canon_sha256":"467eb61183d148039a2e9aaa6762a4d9d24c983b6f829f7e7f13b3a989dd747f"},"schema_version":"1.0","source":{"id":"1703.04977","kind":"arxiv","version":2}},"canonical_sha256":"daef4e59d7c069b96536ddb1e0082c377d357f81552c71af9ad40c4dc715c5d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"daef4e59d7c069b96536ddb1e0082c377d357f81552c71af9ad40c4dc715c5d8","first_computed_at":"2026-05-18T00:33:39.351708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:33:39.351708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vh9KOedjww18FZPhE/g2G42gIb5j05QovcJR3HeUU8FPrQfO/9tr7GLj4b3LkShOzRVLOQDv0Ni5kskJNHf4Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:33:39.352371Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.04977","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2de224a3e70f0a26c95e36daa1f922ff2d1bd0cc904bf90fb959361517f18ab3","sha256:42d1c3317e3f9393c792168ebbf79d1f17e3235d11dbb10431508ae91f0e5af0"],"state_sha256":"9ee874128067d773902717a0be35997250af1668f370be9e83a9c94584bf117b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YR/afnPg+NdT4Uyw868FwuCDi6UTlXZEuHvfmE4/bCRwNt3Jq/F8OkbqsH0iE6tqe8gsNGiwfPEpxKIozVWrBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T06:47:49.463835Z","bundle_sha256":"4a5f2bd95f435a5d1ae1a99a93a0fed2fc1922f86f48fce71e8d11045606eaac"}}