{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LGENHXX5KQNY5I7O6SWKSGPX2N","short_pith_number":"pith:LGENHXX5","canonical_record":{"source":{"id":"2606.16214","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T04:44:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"de05d2c8964f8f5bbb10f5404fe7ba11a3ea2f067b50b3141efb49a143a770db","abstract_canon_sha256":"7fbed5d3b972eb6f6fb2026b0f685e84426a3eee004eba6f9d6382db50b06fbc"},"schema_version":"1.0"},"canonical_sha256":"5988d3defd541b8ea3eef4aca919f7d36d63b764a4708390844f326c7f2c1f6b","source":{"kind":"arxiv","id":"2606.16214","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.16214","created_at":"2026-06-19T16:11:37Z"},{"alias_kind":"arxiv_version","alias_value":"2606.16214v2","created_at":"2026-06-19T16:11:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.16214","created_at":"2026-06-19T16:11:37Z"},{"alias_kind":"pith_short_12","alias_value":"LGENHXX5KQNY","created_at":"2026-06-19T16:11:37Z"},{"alias_kind":"pith_short_16","alias_value":"LGENHXX5KQNY5I7O","created_at":"2026-06-19T16:11:37Z"},{"alias_kind":"pith_short_8","alias_value":"LGENHXX5","created_at":"2026-06-19T16:11:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LGENHXX5KQNY5I7O6SWKSGPX2N","target":"record","payload":{"canonical_record":{"source":{"id":"2606.16214","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T04:44:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"de05d2c8964f8f5bbb10f5404fe7ba11a3ea2f067b50b3141efb49a143a770db","abstract_canon_sha256":"7fbed5d3b972eb6f6fb2026b0f685e84426a3eee004eba6f9d6382db50b06fbc"},"schema_version":"1.0"},"canonical_sha256":"5988d3defd541b8ea3eef4aca919f7d36d63b764a4708390844f326c7f2c1f6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:37.978880Z","signature_b64":"Zkfq5hOPOtzfZlKPj+Xsp3mWBfasM5sxqPJEeKPg/BCN6Wz5ABwo1bF19Pu+m9R8EYBguAcjk9iusgLl8fHdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5988d3defd541b8ea3eef4aca919f7d36d63b764a4708390844f326c7f2c1f6b","last_reissued_at":"2026-06-19T16:11:37.978534Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:37.978534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.16214","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":"2026-06-19T16:11:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eP+0iA1I9cwQ/b53FcPSuJn2WoSMNyNEMsBaqW+rZmft6pcpyEGdkks8gEZmScLEuYxAwe944nj25eXzMpBKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T11:52:30.809690Z"},"content_sha256":"3251cdcbcf78ea3809dec0a5ed1c9279d6e4e6a1f1dd6aad6e59e3c84ff3bada","schema_version":"1.0","event_id":"sha256:3251cdcbcf78ea3809dec0a5ed1c9279d6e4e6a1f1dd6aad6e59e3c84ff3bada"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LGENHXX5KQNY5I7O6SWKSGPX2N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Leon de Andrade, Marcus Rohrbach, Thomas M\\\"ollenhoff, Tobias Jan Wieczorek","submitted_at":"2026-06-15T04:44:46Z","abstract_excerpt":"Modern deep learning models remain notoriously prone to overconfidence, limiting their reliability in high-stakes applications. Bayesian methods aim to counter this by learning a distribution over model parameters, and recent advances now make this feasible for large-scale architectures at costs comparable to AdamW. However, a challenge remains at test time: predictions must be averaged across many forward passes with weights sampled from the posterior, which is prohibitively expensive. Variance propagation offers an efficient alternative, computing layer-wise analytical approximations of unce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.16214","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.16214/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":"2026-06-19T16:11:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M+mxQVNj+KcYa+7UPMF7lbb/Fj55iqUOteMs/IXFDtxLyw1LCFTgeNm9ZTGh2khADRbBTe34e8XnBIRJVdhLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T11:52:30.810063Z"},"content_sha256":"673f8275cbce8a9caacdf0c4937e41eee13329ea8eb0555e96ef160e02468182","schema_version":"1.0","event_id":"sha256:673f8275cbce8a9caacdf0c4937e41eee13329ea8eb0555e96ef160e02468182"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LGENHXX5KQNY5I7O6SWKSGPX2N/bundle.json","state_url":"https://pith.science/pith/LGENHXX5KQNY5I7O6SWKSGPX2N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LGENHXX5KQNY5I7O6SWKSGPX2N/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":"2026-07-03T11:52:30Z","links":{"resolver":"https://pith.science/pith/LGENHXX5KQNY5I7O6SWKSGPX2N","bundle":"https://pith.science/pith/LGENHXX5KQNY5I7O6SWKSGPX2N/bundle.json","state":"https://pith.science/pith/LGENHXX5KQNY5I7O6SWKSGPX2N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LGENHXX5KQNY5I7O6SWKSGPX2N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LGENHXX5KQNY5I7O6SWKSGPX2N","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":"7fbed5d3b972eb6f6fb2026b0f685e84426a3eee004eba6f9d6382db50b06fbc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T04:44:46Z","title_canon_sha256":"de05d2c8964f8f5bbb10f5404fe7ba11a3ea2f067b50b3141efb49a143a770db"},"schema_version":"1.0","source":{"id":"2606.16214","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.16214","created_at":"2026-06-19T16:11:37Z"},{"alias_kind":"arxiv_version","alias_value":"2606.16214v2","created_at":"2026-06-19T16:11:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.16214","created_at":"2026-06-19T16:11:37Z"},{"alias_kind":"pith_short_12","alias_value":"LGENHXX5KQNY","created_at":"2026-06-19T16:11:37Z"},{"alias_kind":"pith_short_16","alias_value":"LGENHXX5KQNY5I7O","created_at":"2026-06-19T16:11:37Z"},{"alias_kind":"pith_short_8","alias_value":"LGENHXX5","created_at":"2026-06-19T16:11:37Z"}],"graph_snapshots":[{"event_id":"sha256:673f8275cbce8a9caacdf0c4937e41eee13329ea8eb0555e96ef160e02468182","target":"graph","created_at":"2026-06-19T16:11:37Z","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/2606.16214/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern deep learning models remain notoriously prone to overconfidence, limiting their reliability in high-stakes applications. Bayesian methods aim to counter this by learning a distribution over model parameters, and recent advances now make this feasible for large-scale architectures at costs comparable to AdamW. However, a challenge remains at test time: predictions must be averaged across many forward passes with weights sampled from the posterior, which is prohibitively expensive. Variance propagation offers an efficient alternative, computing layer-wise analytical approximations of unce","authors_text":"Leon de Andrade, Marcus Rohrbach, Thomas M\\\"ollenhoff, Tobias Jan Wieczorek","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T04:44:46Z","title":"Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.16214","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":"sha256:3251cdcbcf78ea3809dec0a5ed1c9279d6e4e6a1f1dd6aad6e59e3c84ff3bada","target":"record","created_at":"2026-06-19T16:11:37Z","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":"7fbed5d3b972eb6f6fb2026b0f685e84426a3eee004eba6f9d6382db50b06fbc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T04:44:46Z","title_canon_sha256":"de05d2c8964f8f5bbb10f5404fe7ba11a3ea2f067b50b3141efb49a143a770db"},"schema_version":"1.0","source":{"id":"2606.16214","kind":"arxiv","version":2}},"canonical_sha256":"5988d3defd541b8ea3eef4aca919f7d36d63b764a4708390844f326c7f2c1f6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5988d3defd541b8ea3eef4aca919f7d36d63b764a4708390844f326c7f2c1f6b","first_computed_at":"2026-06-19T16:11:37.978534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:37.978534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zkfq5hOPOtzfZlKPj+Xsp3mWBfasM5sxqPJEeKPg/BCN6Wz5ABwo1bF19Pu+m9R8EYBguAcjk9iusgLl8fHdBQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:37.978880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.16214","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3251cdcbcf78ea3809dec0a5ed1c9279d6e4e6a1f1dd6aad6e59e3c84ff3bada","sha256:673f8275cbce8a9caacdf0c4937e41eee13329ea8eb0555e96ef160e02468182"],"state_sha256":"83e1357599dd2f33100fb3724e8c66ce1f29a0e54daa7750dd2c0572d006ea2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oaaMEzV3VmfJeFwu1EWsU33DXgcgxWwtiOggmtKq5dg+pEdWTKTyJyoTeTL00Pu5RBYy1cuj+SbheSRI+NFhAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T11:52:30.812055Z","bundle_sha256":"843c7db6e6c829f35984dcf80f1f20f03a31aaf9b03ca96aae81a19e78544684"}}