{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5FVBCHPQADTHCFPZX4SN6GNKA3","short_pith_number":"pith:5FVBCHPQ","canonical_record":{"source":{"id":"2206.07795","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T20:16:32Z","cross_cats_sorted":["cs.CV","eess.IV"],"title_canon_sha256":"5ec0e306a8444eaebfc9819b30c4c4d1f1feaec2dde796d09a63940720d3713d","abstract_canon_sha256":"04fdc3c261312f05b9b5fe1084b6efffba4c1b0cce1542d3074a6d313715272c"},"schema_version":"1.0"},"canonical_sha256":"e96a111df000e67115f9bf24df19aa06d7d7f41b268d3c436663ec5a69f146e8","source":{"kind":"arxiv","id":"2206.07795","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07795","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07795v1","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07795","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"pith_short_12","alias_value":"5FVBCHPQADTH","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"pith_short_16","alias_value":"5FVBCHPQADTHCFPZ","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"pith_short_8","alias_value":"5FVBCHPQ","created_at":"2026-07-05T04:32:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5FVBCHPQADTHCFPZX4SN6GNKA3","target":"record","payload":{"canonical_record":{"source":{"id":"2206.07795","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T20:16:32Z","cross_cats_sorted":["cs.CV","eess.IV"],"title_canon_sha256":"5ec0e306a8444eaebfc9819b30c4c4d1f1feaec2dde796d09a63940720d3713d","abstract_canon_sha256":"04fdc3c261312f05b9b5fe1084b6efffba4c1b0cce1542d3074a6d313715272c"},"schema_version":"1.0"},"canonical_sha256":"e96a111df000e67115f9bf24df19aa06d7d7f41b268d3c436663ec5a69f146e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:18.297850Z","signature_b64":"MXjjxAq5vwumiIfJlSGqQwqt3F9kVyCDZhI1RdWb0ZY8x8vtWbr0JQa3ZEu9MntZiBuGzbszs54F2rLLb8arAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e96a111df000e67115f9bf24df19aa06d7d7f41b268d3c436663ec5a69f146e8","last_reissued_at":"2026-07-05T04:32:18.297392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:18.297392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.07795","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:32:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wXVdirAxRvxp++HdvTWIp8RIEDixVIyny4pFFdMO3oUwKffVtXHjp302YYsAtNjq2Y5km/KfMVrRr3fYcQiODA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T07:47:15.397536Z"},"content_sha256":"4e45a4dba5d447968fd1763c08b19f5f0977c9cc3341d6ba55a935047b258c3a","schema_version":"1.0","event_id":"sha256:4e45a4dba5d447968fd1763c08b19f5f0977c9cc3341d6ba55a935047b258c3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5FVBCHPQADTHCFPZX4SN6GNKA3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Calibrated Model Uncertainty in Deep Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV","eess.IV"],"primary_cat":"cs.LG","authors_text":"Allan Tucker, Biraja Ghoshal","submitted_at":"2022-06-15T20:16:32Z","abstract_excerpt":"Estimated uncertainty by approximate posteriors in Bayesian neural networks are prone to miscalibration, which leads to overconfident predictions in critical tasks that have a clear asymmetric cost or significant losses. Here, we extend the approximate inference for the loss-calibrated Bayesian framework to dropweights based Bayesian neural networks by maximising expected utility over a model posterior to calibrate uncertainty in deep learning. Furthermore, we show that decisions informed by loss-calibrated uncertainty can improve diagnostic performance to a greater extent than straightforward"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07795","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.07795/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T04:32:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wa6l10RqvQtBQ1wp6zHn4SSfdR7v1+rIzj7MZN7bc0ohfF2RBs07AMc2BpN6UqX0REG3T6uFFutjWP5ci1I7CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T07:47:15.398478Z"},"content_sha256":"4b787e0fcc876ed315cb61b3487854198026c2128892c46476d93e224db6f6af","schema_version":"1.0","event_id":"sha256:4b787e0fcc876ed315cb61b3487854198026c2128892c46476d93e224db6f6af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5FVBCHPQADTHCFPZX4SN6GNKA3/bundle.json","state_url":"https://pith.science/pith/5FVBCHPQADTHCFPZX4SN6GNKA3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5FVBCHPQADTHCFPZX4SN6GNKA3/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":"2026-08-13T07:47:15Z","links":{"resolver":"https://pith.science/pith/5FVBCHPQADTHCFPZX4SN6GNKA3","bundle":"https://pith.science/pith/5FVBCHPQADTHCFPZX4SN6GNKA3/bundle.json","state":"https://pith.science/pith/5FVBCHPQADTHCFPZX4SN6GNKA3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5FVBCHPQADTHCFPZX4SN6GNKA3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5FVBCHPQADTHCFPZX4SN6GNKA3","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":"04fdc3c261312f05b9b5fe1084b6efffba4c1b0cce1542d3074a6d313715272c","cross_cats_sorted":["cs.CV","eess.IV"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T20:16:32Z","title_canon_sha256":"5ec0e306a8444eaebfc9819b30c4c4d1f1feaec2dde796d09a63940720d3713d"},"schema_version":"1.0","source":{"id":"2206.07795","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07795","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07795v1","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07795","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"pith_short_12","alias_value":"5FVBCHPQADTH","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"pith_short_16","alias_value":"5FVBCHPQADTHCFPZ","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"pith_short_8","alias_value":"5FVBCHPQ","created_at":"2026-07-05T04:32:18Z"}],"graph_snapshots":[{"event_id":"sha256:4b787e0fcc876ed315cb61b3487854198026c2128892c46476d93e224db6f6af","target":"graph","created_at":"2026-07-05T04:32:18Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2206.07795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Estimated uncertainty by approximate posteriors in Bayesian neural networks are prone to miscalibration, which leads to overconfident predictions in critical tasks that have a clear asymmetric cost or significant losses. Here, we extend the approximate inference for the loss-calibrated Bayesian framework to dropweights based Bayesian neural networks by maximising expected utility over a model posterior to calibrate uncertainty in deep learning. Furthermore, we show that decisions informed by loss-calibrated uncertainty can improve diagnostic performance to a greater extent than straightforward","authors_text":"Allan Tucker, Biraja Ghoshal","cross_cats":["cs.CV","eess.IV"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T20:16:32Z","title":"On Calibrated Model Uncertainty in Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07795","kind":"arxiv","version":1},"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":"sha256:4e45a4dba5d447968fd1763c08b19f5f0977c9cc3341d6ba55a935047b258c3a","target":"record","created_at":"2026-07-05T04:32:18Z","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":"04fdc3c261312f05b9b5fe1084b6efffba4c1b0cce1542d3074a6d313715272c","cross_cats_sorted":["cs.CV","eess.IV"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T20:16:32Z","title_canon_sha256":"5ec0e306a8444eaebfc9819b30c4c4d1f1feaec2dde796d09a63940720d3713d"},"schema_version":"1.0","source":{"id":"2206.07795","kind":"arxiv","version":1}},"canonical_sha256":"e96a111df000e67115f9bf24df19aa06d7d7f41b268d3c436663ec5a69f146e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e96a111df000e67115f9bf24df19aa06d7d7f41b268d3c436663ec5a69f146e8","first_computed_at":"2026-07-05T04:32:18.297392Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:18.297392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MXjjxAq5vwumiIfJlSGqQwqt3F9kVyCDZhI1RdWb0ZY8x8vtWbr0JQa3ZEu9MntZiBuGzbszs54F2rLLb8arAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:18.297850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.07795","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e45a4dba5d447968fd1763c08b19f5f0977c9cc3341d6ba55a935047b258c3a","sha256:4b787e0fcc876ed315cb61b3487854198026c2128892c46476d93e224db6f6af"],"state_sha256":"85675945b32eb0b905315cc79669c7645f34c16e07ddec757c27e5a9c1855830"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t/jkqWXljrIIqnjYe8BqlszO/uqg3rTiBwNEp5H/SeKuCifhI3404b+hRvmITZasiD3gF/kv+LQqwahp5ZEHCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T07:47:15.441266Z","bundle_sha256":"c54a510b0cbd4e287ba9188c82a730423f831644c22b31686024d89e8a46f0f0"}}