{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YTKMWV662AJYQTBSBZZVXECMTX","short_pith_number":"pith:YTKMWV66","canonical_record":{"source":{"id":"1805.03901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-10T09:26:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"12173b62050de1e73a600f53315dda05260752d085c3846661ba2e77abec6ab3","abstract_canon_sha256":"e94c270d39fcbb73fb4897b86fa8fef94b70194b5ad717e4de0c2d2f4e3c1894"},"schema_version":"1.0"},"canonical_sha256":"c4d4cb57ded013884c320e735b904c9decc7fa3d7c57746945834a47300ccfdf","source":{"kind":"arxiv","id":"1805.03901","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03901","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03901v1","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03901","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"pith_short_12","alias_value":"YTKMWV662AJY","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YTKMWV662AJYQTBS","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YTKMWV66","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YTKMWV662AJYQTBSBZZVXECMTX","target":"record","payload":{"canonical_record":{"source":{"id":"1805.03901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-10T09:26:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"12173b62050de1e73a600f53315dda05260752d085c3846661ba2e77abec6ab3","abstract_canon_sha256":"e94c270d39fcbb73fb4897b86fa8fef94b70194b5ad717e4de0c2d2f4e3c1894"},"schema_version":"1.0"},"canonical_sha256":"c4d4cb57ded013884c320e735b904c9decc7fa3d7c57746945834a47300ccfdf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:16.409015Z","signature_b64":"K2CPimTI3xkMxctaU13f/BpCOOTpHemFnL5IYuNfsLsSUoXdxjXlOl2ddXUKSFPY5STgJWWstP0joC8JlRNXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4d4cb57ded013884c320e735b904c9decc7fa3d7c57746945834a47300ccfdf","last_reissued_at":"2026-05-18T00:16:16.408389Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:16.408389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.03901","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":"2026-05-18T00:16:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TqRhZpn+zRD2XcfqDpta6AIW0Cd7i2EHjqAplbkmBCc0unW6AO+uCCOFmHHVMUY8CnYbtTZT0xNEKEd8g7khAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T02:47:37.442985Z"},"content_sha256":"393e25624d925d42fc71c5323811931bfffff5ac5eae4b021923bc129d16f435","schema_version":"1.0","event_id":"sha256:393e25624d925d42fc71c5323811931bfffff5ac5eae4b021923bc129d16f435"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YTKMWV662AJYQTBSBZZVXECMTX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Loss-Calibrated Approximate Inference in Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adam D. Cobb, Stephen J. Roberts, Yarin Gal","submitted_at":"2018-05-10T09:26:03Z","abstract_excerpt":"Current approaches in approximate inference for Bayesian neural networks minimise the Kullback-Leibler divergence to approximate the true posterior over the weights. However, this approximation is without knowledge of the final application, and therefore cannot guarantee optimal predictions for a given task. To make more suitable task-specific approximations, we introduce a new loss-calibrated evidence lower bound for Bayesian neural networks in the context of supervised learning, informed by Bayesian decision theory. By introducing a lower bound that depends on a utility function, we ensure t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03901","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":""},"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":"2026-05-18T00:16:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rE8bkIuKwCc66cxg2lYKPuyRyrJBsHXPI0fKaShLhBrZHGrgR0BtMACb/3nH0SPyHR2Oe5CoZ6cfIMoB8bwhBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T02:47:37.443653Z"},"content_sha256":"c88716779ce16101f4eeda5b4b81e981fbda81f4d5ed9555baea2348b0b08363","schema_version":"1.0","event_id":"sha256:c88716779ce16101f4eeda5b4b81e981fbda81f4d5ed9555baea2348b0b08363"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YTKMWV662AJYQTBSBZZVXECMTX/bundle.json","state_url":"https://pith.science/pith/YTKMWV662AJYQTBSBZZVXECMTX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YTKMWV662AJYQTBSBZZVXECMTX/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":"2026-06-11T02:47:37Z","links":{"resolver":"https://pith.science/pith/YTKMWV662AJYQTBSBZZVXECMTX","bundle":"https://pith.science/pith/YTKMWV662AJYQTBSBZZVXECMTX/bundle.json","state":"https://pith.science/pith/YTKMWV662AJYQTBSBZZVXECMTX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YTKMWV662AJYQTBSBZZVXECMTX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YTKMWV662AJYQTBSBZZVXECMTX","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":"e94c270d39fcbb73fb4897b86fa8fef94b70194b5ad717e4de0c2d2f4e3c1894","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-10T09:26:03Z","title_canon_sha256":"12173b62050de1e73a600f53315dda05260752d085c3846661ba2e77abec6ab3"},"schema_version":"1.0","source":{"id":"1805.03901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03901","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03901v1","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03901","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"pith_short_12","alias_value":"YTKMWV662AJY","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YTKMWV662AJYQTBS","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YTKMWV66","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:c88716779ce16101f4eeda5b4b81e981fbda81f4d5ed9555baea2348b0b08363","target":"graph","created_at":"2026-05-18T00:16:16Z","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":"Current approaches in approximate inference for Bayesian neural networks minimise the Kullback-Leibler divergence to approximate the true posterior over the weights. However, this approximation is without knowledge of the final application, and therefore cannot guarantee optimal predictions for a given task. To make more suitable task-specific approximations, we introduce a new loss-calibrated evidence lower bound for Bayesian neural networks in the context of supervised learning, informed by Bayesian decision theory. By introducing a lower bound that depends on a utility function, we ensure t","authors_text":"Adam D. Cobb, Stephen J. Roberts, Yarin Gal","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-10T09:26:03Z","title":"Loss-Calibrated Approximate Inference in Bayesian Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03901","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":"sha256:393e25624d925d42fc71c5323811931bfffff5ac5eae4b021923bc129d16f435","target":"record","created_at":"2026-05-18T00:16:16Z","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":"e94c270d39fcbb73fb4897b86fa8fef94b70194b5ad717e4de0c2d2f4e3c1894","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-10T09:26:03Z","title_canon_sha256":"12173b62050de1e73a600f53315dda05260752d085c3846661ba2e77abec6ab3"},"schema_version":"1.0","source":{"id":"1805.03901","kind":"arxiv","version":1}},"canonical_sha256":"c4d4cb57ded013884c320e735b904c9decc7fa3d7c57746945834a47300ccfdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4d4cb57ded013884c320e735b904c9decc7fa3d7c57746945834a47300ccfdf","first_computed_at":"2026-05-18T00:16:16.408389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:16.408389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K2CPimTI3xkMxctaU13f/BpCOOTpHemFnL5IYuNfsLsSUoXdxjXlOl2ddXUKSFPY5STgJWWstP0joC8JlRNXAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:16.409015Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.03901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:393e25624d925d42fc71c5323811931bfffff5ac5eae4b021923bc129d16f435","sha256:c88716779ce16101f4eeda5b4b81e981fbda81f4d5ed9555baea2348b0b08363"],"state_sha256":"29e2ba714fe1394d1ba55264492905333393009e8dd6edc3ab91698b39be69e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iSgM6NlhjzbCNKRwVlQ1ZMzaeOTQihlNnlizNuMi2aMWC7Erd0MY5vmq+JSaCgwGRi/CoprntmFgOtUBqeu0Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T02:47:37.447660Z","bundle_sha256":"dd1660649e0f6842f5cf1b4f66bf07f80e8ea3e73c0c881f9d47d0abe1c223ae"}}