{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OTRFW245II4TR3JV5F6HTJMDZW","short_pith_number":"pith:OTRFW245","schema_version":"1.0","canonical_sha256":"74e25b6b9d423938ed35e97c79a583cd8d91a8f9204f43f670ce723d68c25ea4","source":{"kind":"arxiv","id":"2403.19381","version":2},"attestation_state":"computed","paper":{"title":"On Uncertainty Quantification for Near-Bayes Optimal Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chris Holmes, Ziyu Wang","submitted_at":"2024-03-28T12:42:25Z","abstract_excerpt":"Bayesian modelling allows for the quantification of predictive uncertainty which is crucial in safety-critical applications. Yet for many machine learning (ML) algorithms, it is difficult to construct or implement their Bayesian counterpart. In this work we present a promising approach to address this challenge, based on the hypothesis that commonly used ML algorithms are efficient across a wide variety of tasks and may thus be near Bayes-optimal w.r.t. an unknown task distribution. We prove that it is possible to recover the Bayesian posterior defined by the task distribution, which is unknow"},"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":"2403.19381","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-03-28T12:42:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"14e11d4ca75b4c22d31c37f1880e7873267ff61e09d1948dfb8a474eef41d022","abstract_canon_sha256":"df6f2480e8afa08fda57edc15c6d999914a64ad7e628e2e4e70022467db5be72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:04.537573Z","signature_b64":"VfXsCC3t2nXlV8784cxMx221vnKAgeE3iaEnG42eqv8de8bnu5Xz12TI2LiPXPb1rJYY6FLmMr0SiYcuyNvACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74e25b6b9d423938ed35e97c79a583cd8d91a8f9204f43f670ce723d68c25ea4","last_reissued_at":"2026-07-05T09:23:04.537130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:04.537130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Uncertainty Quantification for Near-Bayes Optimal Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chris Holmes, Ziyu Wang","submitted_at":"2024-03-28T12:42:25Z","abstract_excerpt":"Bayesian modelling allows for the quantification of predictive uncertainty which is crucial in safety-critical applications. Yet for many machine learning (ML) algorithms, it is difficult to construct or implement their Bayesian counterpart. In this work we present a promising approach to address this challenge, based on the hypothesis that commonly used ML algorithms are efficient across a wide variety of tasks and may thus be near Bayes-optimal w.r.t. an unknown task distribution. We prove that it is possible to recover the Bayesian posterior defined by the task distribution, which is unknow"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19381","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/2403.19381/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":"2403.19381","created_at":"2026-07-05T09:23:04.537186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19381v2","created_at":"2026-07-05T09:23:04.537186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19381","created_at":"2026-07-05T09:23:04.537186+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTRFW245II4T","created_at":"2026-07-05T09:23:04.537186+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTRFW245II4TR3JV","created_at":"2026-07-05T09:23:04.537186+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTRFW245","created_at":"2026-07-05T09:23:04.537186+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11168","citing_title":"Variational predictive resampling","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11168","citing_title":"Variational predictive resampling","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTRFW245II4TR3JV5F6HTJMDZW","json":"https://pith.science/pith/OTRFW245II4TR3JV5F6HTJMDZW.json","graph_json":"https://pith.science/api/pith-number/OTRFW245II4TR3JV5F6HTJMDZW/graph.json","events_json":"https://pith.science/api/pith-number/OTRFW245II4TR3JV5F6HTJMDZW/events.json","paper":"https://pith.science/paper/OTRFW245"},"agent_actions":{"view_html":"https://pith.science/pith/OTRFW245II4TR3JV5F6HTJMDZW","download_json":"https://pith.science/pith/OTRFW245II4TR3JV5F6HTJMDZW.json","view_paper":"https://pith.science/paper/OTRFW245","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19381&json=true","fetch_graph":"https://pith.science/api/pith-number/OTRFW245II4TR3JV5F6HTJMDZW/graph.json","fetch_events":"https://pith.science/api/pith-number/OTRFW245II4TR3JV5F6HTJMDZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTRFW245II4TR3JV5F6HTJMDZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTRFW245II4TR3JV5F6HTJMDZW/action/storage_attestation","attest_author":"https://pith.science/pith/OTRFW245II4TR3JV5F6HTJMDZW/action/author_attestation","sign_citation":"https://pith.science/pith/OTRFW245II4TR3JV5F6HTJMDZW/action/citation_signature","submit_replication":"https://pith.science/pith/OTRFW245II4TR3JV5F6HTJMDZW/action/replication_record"}},"created_at":"2026-07-05T09:23:04.537186+00:00","updated_at":"2026-07-05T09:23:04.537186+00:00"}