{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QVHAWP3LVRB7C3WHUQ7NDUURWB","short_pith_number":"pith:QVHAWP3L","schema_version":"1.0","canonical_sha256":"854e0b3f6bac43f16ec7a43ed1d291b0773e898e857137d7ef18850cc1bd689f","source":{"kind":"arxiv","id":"1801.06230","version":1},"attestation_state":"computed","paper":{"title":"Overpruning in Variational Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Brian Trippe, Richard Turner","submitted_at":"2018-01-18T20:33:26Z","abstract_excerpt":"The motivations for using variational inference (VI) in neural networks differ significantly from those in latent variable models. This has a counter-intuitive consequence; more expressive variational approximations can provide significantly worse predictions as compared to those with less expressive families. In this work we make two contributions. First, we identify a cause of this performance gap, variational over-pruning. Second, we introduce a theoretically grounded explanation for this phenomenon. Our perspective sheds light on several related published results and provides intuition int"},"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":"1801.06230","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-18T20:33:26Z","cross_cats_sorted":[],"title_canon_sha256":"35104e8fc2d38590b9c5e3f6ef92c0bd6fe1e51d6b92537fa03bf0f4854665fa","abstract_canon_sha256":"b4d904962057f9854fffb9cf5ddd02ab92db474cd6433217cf48aec5292ac577"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:33.081387Z","signature_b64":"kijAABjVFN2GAjX/V1JGeAf5VDe6uR0l5VRxnKil8zd2k4L27BTvH0TXo+vpUjSJeVJPIbWfPdnbytYJU61NCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"854e0b3f6bac43f16ec7a43ed1d291b0773e898e857137d7ef18850cc1bd689f","last_reissued_at":"2026-05-18T00:25:33.080691Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:33.080691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overpruning in Variational Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Brian Trippe, Richard Turner","submitted_at":"2018-01-18T20:33:26Z","abstract_excerpt":"The motivations for using variational inference (VI) in neural networks differ significantly from those in latent variable models. This has a counter-intuitive consequence; more expressive variational approximations can provide significantly worse predictions as compared to those with less expressive families. In this work we make two contributions. First, we identify a cause of this performance gap, variational over-pruning. Second, we introduce a theoretically grounded explanation for this phenomenon. Our perspective sheds light on several related published results and provides intuition int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.06230","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":""},"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":"1801.06230","created_at":"2026-05-18T00:25:33.080798+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.06230v1","created_at":"2026-05-18T00:25:33.080798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.06230","created_at":"2026-05-18T00:25:33.080798+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVHAWP3LVRB7","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVHAWP3LVRB7C3WH","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVHAWP3L","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.09591","citing_title":"Variational Visual Question Answering for Uncertainty-Aware Selective Prediction","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVHAWP3LVRB7C3WHUQ7NDUURWB","json":"https://pith.science/pith/QVHAWP3LVRB7C3WHUQ7NDUURWB.json","graph_json":"https://pith.science/api/pith-number/QVHAWP3LVRB7C3WHUQ7NDUURWB/graph.json","events_json":"https://pith.science/api/pith-number/QVHAWP3LVRB7C3WHUQ7NDUURWB/events.json","paper":"https://pith.science/paper/QVHAWP3L"},"agent_actions":{"view_html":"https://pith.science/pith/QVHAWP3LVRB7C3WHUQ7NDUURWB","download_json":"https://pith.science/pith/QVHAWP3LVRB7C3WHUQ7NDUURWB.json","view_paper":"https://pith.science/paper/QVHAWP3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.06230&json=true","fetch_graph":"https://pith.science/api/pith-number/QVHAWP3LVRB7C3WHUQ7NDUURWB/graph.json","fetch_events":"https://pith.science/api/pith-number/QVHAWP3LVRB7C3WHUQ7NDUURWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVHAWP3LVRB7C3WHUQ7NDUURWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVHAWP3LVRB7C3WHUQ7NDUURWB/action/storage_attestation","attest_author":"https://pith.science/pith/QVHAWP3LVRB7C3WHUQ7NDUURWB/action/author_attestation","sign_citation":"https://pith.science/pith/QVHAWP3LVRB7C3WHUQ7NDUURWB/action/citation_signature","submit_replication":"https://pith.science/pith/QVHAWP3LVRB7C3WHUQ7NDUURWB/action/replication_record"}},"created_at":"2026-05-18T00:25:33.080798+00:00","updated_at":"2026-05-18T00:25:33.080798+00:00"}