{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:YRDA3RB7O6WLKTQ37QCMJUJJAO","short_pith_number":"pith:YRDA3RB7","canonical_record":{"source":{"id":"1705.10388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-29T20:35:42Z","cross_cats_sorted":[],"title_canon_sha256":"ba9e9e7f241e710a20ca0c527adcacb15fe03e0a92dd281544d3033f2bf7b496","abstract_canon_sha256":"82e24c152448d4bea6ff42c15c0a2d87cf9d913feb2c7d49c6bf179364a3968a"},"schema_version":"1.0"},"canonical_sha256":"c4460dc43f77acb54e1bfc04c4d1290397d48a57a6dd9a3bb02c29a369202b18","source":{"kind":"arxiv","id":"1705.10388","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.10388","created_at":"2026-05-18T00:43:31Z"},{"alias_kind":"arxiv_version","alias_value":"1705.10388v1","created_at":"2026-05-18T00:43:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10388","created_at":"2026-05-18T00:43:31Z"},{"alias_kind":"pith_short_12","alias_value":"YRDA3RB7O6WL","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"YRDA3RB7O6WLKTQ3","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"YRDA3RB7","created_at":"2026-05-18T12:31:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:YRDA3RB7O6WLKTQ37QCMJUJJAO","target":"record","payload":{"canonical_record":{"source":{"id":"1705.10388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-29T20:35:42Z","cross_cats_sorted":[],"title_canon_sha256":"ba9e9e7f241e710a20ca0c527adcacb15fe03e0a92dd281544d3033f2bf7b496","abstract_canon_sha256":"82e24c152448d4bea6ff42c15c0a2d87cf9d913feb2c7d49c6bf179364a3968a"},"schema_version":"1.0"},"canonical_sha256":"c4460dc43f77acb54e1bfc04c4d1290397d48a57a6dd9a3bb02c29a369202b18","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:31.187023Z","signature_b64":"o02VnzSua/tVOC2VcsxUpdBc9kIaWxJX/Mti9BrCC6p4VzvGjgoTaUMIdaiGqEL6u3Nk+Buldosxr9okEkQXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4460dc43f77acb54e1bfc04c4d1290397d48a57a6dd9a3bb02c29a369202b18","last_reissued_at":"2026-05-18T00:43:31.186481Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:31.186481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.10388","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:43:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Ck6sFMAasQ2UZeA/ZI/+MWtGvITaoUfWzuDZ8O/8sOsUdyRw2OrmD6tEjJIjlTKzomfa/1vHr41TGxViKyXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:46:53.359339Z"},"content_sha256":"212d452690237d87832540faeb1d21784d9494d15712ccbc1aaf1aa221defbce","schema_version":"1.0","event_id":"sha256:212d452690237d87832540faeb1d21784d9494d15712ccbc1aaf1aa221defbce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:YRDA3RB7O6WLKTQ37QCMJUJJAO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model Selection in Bayesian Neural Networks via Horseshoe Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Finale Doshi-Velez, Soumya Ghosh","submitted_at":"2017-05-29T20:35:42Z","abstract_excerpt":"Bayesian Neural Networks (BNNs) have recently received increasing attention for their ability to provide well-calibrated posterior uncertainties. However, model selection---even choosing the number of nodes---remains an open question. In this work, we apply a horseshoe prior over node pre-activations of a Bayesian neural network, which effectively turns off nodes that do not help explain the data. We demonstrate that our prior prevents the BNN from under-fitting even when the number of nodes required is grossly over-estimated. Moreover, this model selection over the number of nodes doesn't com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10388","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:43:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aCsXfSeBlwON1cJ2yV3k55b7R7jdxj6HMMyX5O2CfYiCoMOwkR+N+8iifE8Qh5+AaRI4sRDqm3yZLpXbIdQLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:46:53.359884Z"},"content_sha256":"ee17834670b6dfffc1e4da2ae169efd0777b120cc7ac75e341c1e7ab12420190","schema_version":"1.0","event_id":"sha256:ee17834670b6dfffc1e4da2ae169efd0777b120cc7ac75e341c1e7ab12420190"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YRDA3RB7O6WLKTQ37QCMJUJJAO/bundle.json","state_url":"https://pith.science/pith/YRDA3RB7O6WLKTQ37QCMJUJJAO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YRDA3RB7O6WLKTQ37QCMJUJJAO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T19:46:53Z","links":{"resolver":"https://pith.science/pith/YRDA3RB7O6WLKTQ37QCMJUJJAO","bundle":"https://pith.science/pith/YRDA3RB7O6WLKTQ37QCMJUJJAO/bundle.json","state":"https://pith.science/pith/YRDA3RB7O6WLKTQ37QCMJUJJAO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YRDA3RB7O6WLKTQ37QCMJUJJAO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:YRDA3RB7O6WLKTQ37QCMJUJJAO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"82e24c152448d4bea6ff42c15c0a2d87cf9d913feb2c7d49c6bf179364a3968a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-29T20:35:42Z","title_canon_sha256":"ba9e9e7f241e710a20ca0c527adcacb15fe03e0a92dd281544d3033f2bf7b496"},"schema_version":"1.0","source":{"id":"1705.10388","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.10388","created_at":"2026-05-18T00:43:31Z"},{"alias_kind":"arxiv_version","alias_value":"1705.10388v1","created_at":"2026-05-18T00:43:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10388","created_at":"2026-05-18T00:43:31Z"},{"alias_kind":"pith_short_12","alias_value":"YRDA3RB7O6WL","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"YRDA3RB7O6WLKTQ3","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"YRDA3RB7","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:ee17834670b6dfffc1e4da2ae169efd0777b120cc7ac75e341c1e7ab12420190","target":"graph","created_at":"2026-05-18T00:43:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Bayesian Neural Networks (BNNs) have recently received increasing attention for their ability to provide well-calibrated posterior uncertainties. However, model selection---even choosing the number of nodes---remains an open question. In this work, we apply a horseshoe prior over node pre-activations of a Bayesian neural network, which effectively turns off nodes that do not help explain the data. We demonstrate that our prior prevents the BNN from under-fitting even when the number of nodes required is grossly over-estimated. Moreover, this model selection over the number of nodes doesn't com","authors_text":"Finale Doshi-Velez, Soumya Ghosh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-29T20:35:42Z","title":"Model Selection in Bayesian Neural Networks via Horseshoe Priors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10388","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:212d452690237d87832540faeb1d21784d9494d15712ccbc1aaf1aa221defbce","target":"record","created_at":"2026-05-18T00:43:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"82e24c152448d4bea6ff42c15c0a2d87cf9d913feb2c7d49c6bf179364a3968a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-29T20:35:42Z","title_canon_sha256":"ba9e9e7f241e710a20ca0c527adcacb15fe03e0a92dd281544d3033f2bf7b496"},"schema_version":"1.0","source":{"id":"1705.10388","kind":"arxiv","version":1}},"canonical_sha256":"c4460dc43f77acb54e1bfc04c4d1290397d48a57a6dd9a3bb02c29a369202b18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4460dc43f77acb54e1bfc04c4d1290397d48a57a6dd9a3bb02c29a369202b18","first_computed_at":"2026-05-18T00:43:31.186481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:31.186481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o02VnzSua/tVOC2VcsxUpdBc9kIaWxJX/Mti9BrCC6p4VzvGjgoTaUMIdaiGqEL6u3Nk+Buldosxr9okEkQXBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:31.187023Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.10388","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:212d452690237d87832540faeb1d21784d9494d15712ccbc1aaf1aa221defbce","sha256:ee17834670b6dfffc1e4da2ae169efd0777b120cc7ac75e341c1e7ab12420190"],"state_sha256":"a777dc688d0d74143d80ffa235c02bf57464e5091fa27e0143e48198d765a6df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"riGqSW14YFQePO9Jdeh85gMakAXqA+MM886qcofCQ1+5QPIz12zJK6U52jZpZ5JCRO63sRAQoNUn/eXPxoUiAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T19:46:53.362786Z","bundle_sha256":"a0aa89bbd480b0414176a581206038757e647de9cd5046934f6259404a26655c"}}