{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M7UOVAPVMOS3D7DYVQBI2LJQRR","short_pith_number":"pith:M7UOVAPV","schema_version":"1.0","canonical_sha256":"67e8ea81f563a5b1fc78ac028d2d308c737d6970e9aa4e4ad4816004d6112503","source":{"kind":"arxiv","id":"2412.04177","version":2},"attestation_state":"computed","paper":{"title":"Fixed-Mean Gaussian Processes for Post-hoc Bayesian Deep Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Hern\\'andez-Lobato, Luis A. Ortega, Sim\\'on Rodr\\'iguez-Santana","submitted_at":"2024-12-05T14:17:16Z","abstract_excerpt":"Recently, there has been an increasing interest in performing post-hoc uncertainty estimation about the predictions of pre-trained deep neural networks (DNNs). Given a pre-trained DNN via back-propagation, these methods enhance the original network by adding output confidence measures, such as error bars, without compromising its initial accuracy. In this context, we introduce a novel family of sparse variational Gaussian processes (GPs), where the posterior mean is fixed to any continuous function when using a universal kernel. Specifically, we fix the mean of this GP to the output of the pre"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.04177","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T14:17:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"86c78a126c71a7e2731f771d52644e1355ebed766ed571614c2188e930881a12","abstract_canon_sha256":"b4731c004f3d2de0d5743bd6c80cc4c3cfd88639f7d46e82abbe2a43a83ae358"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:45.528750Z","signature_b64":"fnpJb/81zICdAGbif1vuyFwHwRZp5Nk+JfnezN5gn+qsuRUlSq64LkkhFTf+ZZniAXGWKw7X/HnrCr3FDiISDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67e8ea81f563a5b1fc78ac028d2d308c737d6970e9aa4e4ad4816004d6112503","last_reissued_at":"2026-06-02T02:04:45.528250Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:45.528250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fixed-Mean Gaussian Processes for Post-hoc Bayesian Deep Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Hern\\'andez-Lobato, Luis A. Ortega, Sim\\'on Rodr\\'iguez-Santana","submitted_at":"2024-12-05T14:17:16Z","abstract_excerpt":"Recently, there has been an increasing interest in performing post-hoc uncertainty estimation about the predictions of pre-trained deep neural networks (DNNs). Given a pre-trained DNN via back-propagation, these methods enhance the original network by adding output confidence measures, such as error bars, without compromising its initial accuracy. In this context, we introduce a novel family of sparse variational Gaussian processes (GPs), where the posterior mean is fixed to any continuous function when using a universal kernel. Specifically, we fix the mean of this GP to the output of the pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04177","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/2412.04177/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.04177","created_at":"2026-06-02T02:04:45.528325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04177v2","created_at":"2026-06-02T02:04:45.528325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04177","created_at":"2026-06-02T02:04:45.528325+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7UOVAPVMOS3","created_at":"2026-06-02T02:04:45.528325+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7UOVAPVMOS3D7DY","created_at":"2026-06-02T02:04:45.528325+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7UOVAPV","created_at":"2026-06-02T02:04:45.528325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7UOVAPVMOS3D7DYVQBI2LJQRR","json":"https://pith.science/pith/M7UOVAPVMOS3D7DYVQBI2LJQRR.json","graph_json":"https://pith.science/api/pith-number/M7UOVAPVMOS3D7DYVQBI2LJQRR/graph.json","events_json":"https://pith.science/api/pith-number/M7UOVAPVMOS3D7DYVQBI2LJQRR/events.json","paper":"https://pith.science/paper/M7UOVAPV"},"agent_actions":{"view_html":"https://pith.science/pith/M7UOVAPVMOS3D7DYVQBI2LJQRR","download_json":"https://pith.science/pith/M7UOVAPVMOS3D7DYVQBI2LJQRR.json","view_paper":"https://pith.science/paper/M7UOVAPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04177&json=true","fetch_graph":"https://pith.science/api/pith-number/M7UOVAPVMOS3D7DYVQBI2LJQRR/graph.json","fetch_events":"https://pith.science/api/pith-number/M7UOVAPVMOS3D7DYVQBI2LJQRR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7UOVAPVMOS3D7DYVQBI2LJQRR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7UOVAPVMOS3D7DYVQBI2LJQRR/action/storage_attestation","attest_author":"https://pith.science/pith/M7UOVAPVMOS3D7DYVQBI2LJQRR/action/author_attestation","sign_citation":"https://pith.science/pith/M7UOVAPVMOS3D7DYVQBI2LJQRR/action/citation_signature","submit_replication":"https://pith.science/pith/M7UOVAPVMOS3D7DYVQBI2LJQRR/action/replication_record"}},"created_at":"2026-06-02T02:04:45.528325+00:00","updated_at":"2026-06-02T02:04:45.528325+00:00"}