{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CCVOGS6BZT5KQ7V7GHT5VGHEU5","short_pith_number":"pith:CCVOGS6B","schema_version":"1.0","canonical_sha256":"10aae34bc1ccfaa87ebf31e7da98e4a75601d422665fe92051e5b57b45f46d48","source":{"kind":"arxiv","id":"2408.03746","version":1},"attestation_state":"computed","paper":{"title":"Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Delu Zeng, Jian Xu, John Paisley, Junmei Yang, Min Chen, Shigui Li, Zhiqi Lin","submitted_at":"2024-08-07T12:59:58Z","abstract_excerpt":"Bayesian Last Layer (BLL) models focus solely on uncertainty in the output layer of neural networks, demonstrating comparable performance to more complex Bayesian models. However, the use of Gaussian priors for last layer weights in Bayesian Last Layer (BLL) models limits their expressive capacity when faced with non-Gaussian, outlier-rich, or high-dimensional datasets. To address this shortfall, we introduce a novel approach that combines diffusion techniques and implicit priors for variational learning of Bayesian last layer weights. This method leverages implicit distributions for modeling "},"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":"2408.03746","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-07T12:59:58Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"7eec68247aa297ae385b832e3a4e50c63c87e84f9ca6f308a75faf2b27bf9ba5","abstract_canon_sha256":"6ad3aedcf918cfce34901538844a6acce2486ffaccdd91de0f8bc062de221a5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:10.513713Z","signature_b64":"OZB03mhyNeDMQ/wUKNLbmviBBfUK6SIDQGIijsnzQQeCBxGJSCZY2E8AfHjmGxs1xBPsH9c2u6YHdC6656mBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10aae34bc1ccfaa87ebf31e7da98e4a75601d422665fe92051e5b57b45f46d48","last_reissued_at":"2026-07-05T08:53:10.513155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:10.513155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Delu Zeng, Jian Xu, John Paisley, Junmei Yang, Min Chen, Shigui Li, Zhiqi Lin","submitted_at":"2024-08-07T12:59:58Z","abstract_excerpt":"Bayesian Last Layer (BLL) models focus solely on uncertainty in the output layer of neural networks, demonstrating comparable performance to more complex Bayesian models. However, the use of Gaussian priors for last layer weights in Bayesian Last Layer (BLL) models limits their expressive capacity when faced with non-Gaussian, outlier-rich, or high-dimensional datasets. To address this shortfall, we introduce a novel approach that combines diffusion techniques and implicit priors for variational learning of Bayesian last layer weights. This method leverages implicit distributions for modeling "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03746","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/2408.03746/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":"2408.03746","created_at":"2026-07-05T08:53:10.513217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.03746v1","created_at":"2026-07-05T08:53:10.513217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03746","created_at":"2026-07-05T08:53:10.513217+00:00"},{"alias_kind":"pith_short_12","alias_value":"CCVOGS6BZT5K","created_at":"2026-07-05T08:53:10.513217+00:00"},{"alias_kind":"pith_short_16","alias_value":"CCVOGS6BZT5KQ7V7","created_at":"2026-07-05T08:53:10.513217+00:00"},{"alias_kind":"pith_short_8","alias_value":"CCVOGS6B","created_at":"2026-07-05T08:53:10.513217+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/CCVOGS6BZT5KQ7V7GHT5VGHEU5","json":"https://pith.science/pith/CCVOGS6BZT5KQ7V7GHT5VGHEU5.json","graph_json":"https://pith.science/api/pith-number/CCVOGS6BZT5KQ7V7GHT5VGHEU5/graph.json","events_json":"https://pith.science/api/pith-number/CCVOGS6BZT5KQ7V7GHT5VGHEU5/events.json","paper":"https://pith.science/paper/CCVOGS6B"},"agent_actions":{"view_html":"https://pith.science/pith/CCVOGS6BZT5KQ7V7GHT5VGHEU5","download_json":"https://pith.science/pith/CCVOGS6BZT5KQ7V7GHT5VGHEU5.json","view_paper":"https://pith.science/paper/CCVOGS6B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.03746&json=true","fetch_graph":"https://pith.science/api/pith-number/CCVOGS6BZT5KQ7V7GHT5VGHEU5/graph.json","fetch_events":"https://pith.science/api/pith-number/CCVOGS6BZT5KQ7V7GHT5VGHEU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CCVOGS6BZT5KQ7V7GHT5VGHEU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CCVOGS6BZT5KQ7V7GHT5VGHEU5/action/storage_attestation","attest_author":"https://pith.science/pith/CCVOGS6BZT5KQ7V7GHT5VGHEU5/action/author_attestation","sign_citation":"https://pith.science/pith/CCVOGS6BZT5KQ7V7GHT5VGHEU5/action/citation_signature","submit_replication":"https://pith.science/pith/CCVOGS6BZT5KQ7V7GHT5VGHEU5/action/replication_record"}},"created_at":"2026-07-05T08:53:10.513217+00:00","updated_at":"2026-07-05T08:53:10.513217+00:00"}