{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L3D3E6TOSRQPTBJAZQK5YNXOXP","short_pith_number":"pith:L3D3E6TO","schema_version":"1.0","canonical_sha256":"5ec7b27a6e9460f98520cc15dc36eebbe62ee3cafefeafe166406a485ee38d0d","source":{"kind":"arxiv","id":"2602.19126","version":2},"attestation_state":"computed","paper":{"title":"Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.PR","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Katerina Papagiannouli, Michele Caprio, Sayan Mukherjee, Siu Lun Chau","submitted_at":"2026-02-22T10:50:04Z","abstract_excerpt":"We propose a robust Bayesian formulation of random feature (RF) regression that accounts explicitly for prior and likelihood misspecification via Huber-style contamination sets. Starting from the classical equivalence between ridge-regularized RF training and Bayesian inference with Gaussian priors and likelihoods, we replace the single prior and likelihood with $\\epsilon$- and $\\eta$-contaminated credal sets, respectively, and perform inference using pessimistic generalized Bayesian updating. We derive explicit and tractable bounds for the resulting lower and upper posterior predictive densit"},"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":"2602.19126","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-22T10:50:04Z","cross_cats_sorted":["math.PR","math.ST","stat.TH"],"title_canon_sha256":"adaafdb4d8f1ac1311a6b625cd40d4c48b510148b7e0f54138e4b74cd9882e28","abstract_canon_sha256":"0641a13e3648bc5386fd51366fefacfd4695f8ffd519898318896668d735e6fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:05:05.005129Z","signature_b64":"aDEIx4ObmAZmgj0xeZgoTNSB62G6C0ZzEWfQMiEUsaU6/PX1VOjngFX8LkaXfx+CNBS5e47M0NBOSNoiVUuLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ec7b27a6e9460f98520cc15dc36eebbe62ee3cafefeafe166406a485ee38d0d","last_reissued_at":"2026-06-02T03:05:05.004612Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:05:05.004612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.PR","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Katerina Papagiannouli, Michele Caprio, Sayan Mukherjee, Siu Lun Chau","submitted_at":"2026-02-22T10:50:04Z","abstract_excerpt":"We propose a robust Bayesian formulation of random feature (RF) regression that accounts explicitly for prior and likelihood misspecification via Huber-style contamination sets. Starting from the classical equivalence between ridge-regularized RF training and Bayesian inference with Gaussian priors and likelihoods, we replace the single prior and likelihood with $\\epsilon$- and $\\eta$-contaminated credal sets, respectively, and perform inference using pessimistic generalized Bayesian updating. We derive explicit and tractable bounds for the resulting lower and upper posterior predictive densit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.19126","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/2602.19126/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":"2602.19126","created_at":"2026-06-02T03:05:05.004681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.19126v2","created_at":"2026-06-02T03:05:05.004681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.19126","created_at":"2026-06-02T03:05:05.004681+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3D3E6TOSRQP","created_at":"2026-06-02T03:05:05.004681+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3D3E6TOSRQPTBJA","created_at":"2026-06-02T03:05:05.004681+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3D3E6TO","created_at":"2026-06-02T03:05:05.004681+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/L3D3E6TOSRQPTBJAZQK5YNXOXP","json":"https://pith.science/pith/L3D3E6TOSRQPTBJAZQK5YNXOXP.json","graph_json":"https://pith.science/api/pith-number/L3D3E6TOSRQPTBJAZQK5YNXOXP/graph.json","events_json":"https://pith.science/api/pith-number/L3D3E6TOSRQPTBJAZQK5YNXOXP/events.json","paper":"https://pith.science/paper/L3D3E6TO"},"agent_actions":{"view_html":"https://pith.science/pith/L3D3E6TOSRQPTBJAZQK5YNXOXP","download_json":"https://pith.science/pith/L3D3E6TOSRQPTBJAZQK5YNXOXP.json","view_paper":"https://pith.science/paper/L3D3E6TO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.19126&json=true","fetch_graph":"https://pith.science/api/pith-number/L3D3E6TOSRQPTBJAZQK5YNXOXP/graph.json","fetch_events":"https://pith.science/api/pith-number/L3D3E6TOSRQPTBJAZQK5YNXOXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3D3E6TOSRQPTBJAZQK5YNXOXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3D3E6TOSRQPTBJAZQK5YNXOXP/action/storage_attestation","attest_author":"https://pith.science/pith/L3D3E6TOSRQPTBJAZQK5YNXOXP/action/author_attestation","sign_citation":"https://pith.science/pith/L3D3E6TOSRQPTBJAZQK5YNXOXP/action/citation_signature","submit_replication":"https://pith.science/pith/L3D3E6TOSRQPTBJAZQK5YNXOXP/action/replication_record"}},"created_at":"2026-06-02T03:05:05.004681+00:00","updated_at":"2026-06-02T03:05:05.004681+00:00"}