{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:BONXDRYCSMUXFNDCYTM6TNI5AQ","short_pith_number":"pith:BONXDRYC","canonical_record":{"source":{"id":"2207.13167","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-07-26T19:45:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe5cbaffece4d6259e3c2aba7a0e4f5fa2ee194707d0526db7205606893be2a7","abstract_canon_sha256":"b8251fa208aa8613d3ed9bfdc48aab6d5791fb35e2c2e4e601b85ee246caa98f"},"schema_version":"1.0"},"canonical_sha256":"0b9b71c702932972b462c4d9e9b51d0434b34cbc55657a9480213611358c7027","source":{"kind":"arxiv","id":"2207.13167","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.13167","created_at":"2026-07-05T04:44:03Z"},{"alias_kind":"arxiv_version","alias_value":"2207.13167v1","created_at":"2026-07-05T04:44:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13167","created_at":"2026-07-05T04:44:03Z"},{"alias_kind":"pith_short_12","alias_value":"BONXDRYCSMUX","created_at":"2026-07-05T04:44:03Z"},{"alias_kind":"pith_short_16","alias_value":"BONXDRYCSMUXFNDC","created_at":"2026-07-05T04:44:03Z"},{"alias_kind":"pith_short_8","alias_value":"BONXDRYC","created_at":"2026-07-05T04:44:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:BONXDRYCSMUXFNDCYTM6TNI5AQ","target":"record","payload":{"canonical_record":{"source":{"id":"2207.13167","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-07-26T19:45:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe5cbaffece4d6259e3c2aba7a0e4f5fa2ee194707d0526db7205606893be2a7","abstract_canon_sha256":"b8251fa208aa8613d3ed9bfdc48aab6d5791fb35e2c2e4e601b85ee246caa98f"},"schema_version":"1.0"},"canonical_sha256":"0b9b71c702932972b462c4d9e9b51d0434b34cbc55657a9480213611358c7027","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:03.630801Z","signature_b64":"Xa71ONgKTPwL1Rww0BwyiGGJlOz9eVkZbesIJ0p1oajfCyjdNY2VUkwFhbjk/l2VOtZ4fw7LXL9YrNusyyLKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b9b71c702932972b462c4d9e9b51d0434b34cbc55657a9480213611358c7027","last_reissued_at":"2026-07-05T04:44:03.630410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:03.630410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.13167","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":"2026-07-05T04:44:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"URQkl+iasuJ2IcGgCoH+8J39AdLqfgijNzjx+qv+eyjkqHL4cBPQi+WrVdOiVzYd115bjfhAINmYvv45cBE5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:39:05.234804Z"},"content_sha256":"9a9391667d1eff2a2811f30fb9e6ab0c23dce677f711a695f39d33a5cd5af52d","schema_version":"1.0","event_id":"sha256:9a9391667d1eff2a2811f30fb9e6ab0c23dce677f711a695f39d33a5cd5af52d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:BONXDRYCSMUXFNDCYTM6TNI5AQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"One Simple Trick to Fix Your Bayesian Neural Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ksawery Smoczy\\'nski, Marek Cygan, Philip Smolenski-Jensen, Piotr Tempczyk","submitted_at":"2022-07-26T19:45:36Z","abstract_excerpt":"One of the most popular estimation methods in Bayesian neural networks (BNN) is mean-field variational inference (MFVI). In this work, we show that neural networks with ReLU activation function induce posteriors, that are hard to fit with MFVI. We provide a theoretical justification for this phenomenon, study it empirically, and report the results of a series of experiments to investigate the effect of activation function on the calibration of BNNs. We find that using Leaky ReLU activations leads to more Gaussian-like weight posteriors and achieves a lower expected calibration error (ECE) than"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13167","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/2207.13167/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":"2026-07-05T04:44:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UvsJQI39I1bS+Ii/nd/MmCPJGm4Ga0sLRxa8oXB81YZd6k0cbf5syNwkDKH9Wm+cKJMYRZ7B8CskjEd4zjRnCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:39:05.235183Z"},"content_sha256":"8d650b9632b5e23f14e071ce28d478529a2da85a036919e34fa4689087061e64","schema_version":"1.0","event_id":"sha256:8d650b9632b5e23f14e071ce28d478529a2da85a036919e34fa4689087061e64"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BONXDRYCSMUXFNDCYTM6TNI5AQ/bundle.json","state_url":"https://pith.science/pith/BONXDRYCSMUXFNDCYTM6TNI5AQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BONXDRYCSMUXFNDCYTM6TNI5AQ/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":"2026-07-06T18:39:05Z","links":{"resolver":"https://pith.science/pith/BONXDRYCSMUXFNDCYTM6TNI5AQ","bundle":"https://pith.science/pith/BONXDRYCSMUXFNDCYTM6TNI5AQ/bundle.json","state":"https://pith.science/pith/BONXDRYCSMUXFNDCYTM6TNI5AQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BONXDRYCSMUXFNDCYTM6TNI5AQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BONXDRYCSMUXFNDCYTM6TNI5AQ","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":"b8251fa208aa8613d3ed9bfdc48aab6d5791fb35e2c2e4e601b85ee246caa98f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-07-26T19:45:36Z","title_canon_sha256":"fe5cbaffece4d6259e3c2aba7a0e4f5fa2ee194707d0526db7205606893be2a7"},"schema_version":"1.0","source":{"id":"2207.13167","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.13167","created_at":"2026-07-05T04:44:03Z"},{"alias_kind":"arxiv_version","alias_value":"2207.13167v1","created_at":"2026-07-05T04:44:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13167","created_at":"2026-07-05T04:44:03Z"},{"alias_kind":"pith_short_12","alias_value":"BONXDRYCSMUX","created_at":"2026-07-05T04:44:03Z"},{"alias_kind":"pith_short_16","alias_value":"BONXDRYCSMUXFNDC","created_at":"2026-07-05T04:44:03Z"},{"alias_kind":"pith_short_8","alias_value":"BONXDRYC","created_at":"2026-07-05T04:44:03Z"}],"graph_snapshots":[{"event_id":"sha256:8d650b9632b5e23f14e071ce28d478529a2da85a036919e34fa4689087061e64","target":"graph","created_at":"2026-07-05T04:44:03Z","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/2207.13167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the most popular estimation methods in Bayesian neural networks (BNN) is mean-field variational inference (MFVI). In this work, we show that neural networks with ReLU activation function induce posteriors, that are hard to fit with MFVI. We provide a theoretical justification for this phenomenon, study it empirically, and report the results of a series of experiments to investigate the effect of activation function on the calibration of BNNs. We find that using Leaky ReLU activations leads to more Gaussian-like weight posteriors and achieves a lower expected calibration error (ECE) than","authors_text":"Ksawery Smoczy\\'nski, Marek Cygan, Philip Smolenski-Jensen, Piotr Tempczyk","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-07-26T19:45:36Z","title":"One Simple Trick to Fix Your Bayesian Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13167","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":"sha256:9a9391667d1eff2a2811f30fb9e6ab0c23dce677f711a695f39d33a5cd5af52d","target":"record","created_at":"2026-07-05T04:44:03Z","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":"b8251fa208aa8613d3ed9bfdc48aab6d5791fb35e2c2e4e601b85ee246caa98f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-07-26T19:45:36Z","title_canon_sha256":"fe5cbaffece4d6259e3c2aba7a0e4f5fa2ee194707d0526db7205606893be2a7"},"schema_version":"1.0","source":{"id":"2207.13167","kind":"arxiv","version":1}},"canonical_sha256":"0b9b71c702932972b462c4d9e9b51d0434b34cbc55657a9480213611358c7027","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b9b71c702932972b462c4d9e9b51d0434b34cbc55657a9480213611358c7027","first_computed_at":"2026-07-05T04:44:03.630410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:44:03.630410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xa71ONgKTPwL1Rww0BwyiGGJlOz9eVkZbesIJ0p1oajfCyjdNY2VUkwFhbjk/l2VOtZ4fw7LXL9YrNusyyLKDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:44:03.630801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.13167","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a9391667d1eff2a2811f30fb9e6ab0c23dce677f711a695f39d33a5cd5af52d","sha256:8d650b9632b5e23f14e071ce28d478529a2da85a036919e34fa4689087061e64"],"state_sha256":"95b9b56228e91740f111ada51f75f90b7856e198479f442f80fb517ecfe592a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k5o5ui1IHIj+SL1QlU3E0ipgP9qr46c5JeA07CAA3G40nMyNWoMpjRSgdAC60OCjaDAV3LjPedUqS7bCyB4ADQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:39:05.237214Z","bundle_sha256":"84206144646af5b67c90029378ef3cfbb44dc841fdb6034164dad176cf07b2e2"}}