{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:DYMOOSMVSRXTC2ZYQGW74IZJSK","short_pith_number":"pith:DYMOOSMV","schema_version":"1.0","canonical_sha256":"1e18e74995946f316b3881adfe2329929e6f1cef0b51fb54b34ba23afa3e4c11","source":{"kind":"arxiv","id":"1303.6938","version":1},"attestation_state":"computed","paper":{"title":"Expectation Propagation for Neural Networks with Sparsity-promoting Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Aapo Nummenmaa, Aki Vehtari, Pasi Jyl\\\"anki","submitted_at":"2013-03-27T19:40:26Z","abstract_excerpt":"We propose a novel approach for nonlinear regression using a two-layer neural network (NN) model structure with sparsity-favoring hierarchical priors on the network weights. We present an expectation propagation (EP) approach for approximate integration over the posterior distribution of the weights, the hierarchical scale parameters of the priors, and the residual scale. Using a factorized posterior approximation we derive a computationally efficient algorithm, whose complexity scales similarly to an ensemble of independent sparse linear models. The approach enables flexible definition of wei"},"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":"1303.6938","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-03-27T19:40:26Z","cross_cats_sorted":[],"title_canon_sha256":"e00e6bb2e07228864819993a604d86aa594763afc0c565e5919663d86a2465ad","abstract_canon_sha256":"038f1ef8e826bb1b53deef0244a7d49785d7ba9af460bb9a57296b21a06c6bca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:28:55.373506Z","signature_b64":"4yBE8DVR+p54PVF2irV6wMGawScTnsLpd1mICoAS5IybpZL0uziP3pG1NZYGIr8vU+Tg9szGy3miGZWG4+WYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e18e74995946f316b3881adfe2329929e6f1cef0b51fb54b34ba23afa3e4c11","last_reissued_at":"2026-05-18T02:28:55.372950Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:28:55.372950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expectation Propagation for Neural Networks with Sparsity-promoting Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Aapo Nummenmaa, Aki Vehtari, Pasi Jyl\\\"anki","submitted_at":"2013-03-27T19:40:26Z","abstract_excerpt":"We propose a novel approach for nonlinear regression using a two-layer neural network (NN) model structure with sparsity-favoring hierarchical priors on the network weights. We present an expectation propagation (EP) approach for approximate integration over the posterior distribution of the weights, the hierarchical scale parameters of the priors, and the residual scale. Using a factorized posterior approximation we derive a computationally efficient algorithm, whose complexity scales similarly to an ensemble of independent sparse linear models. The approach enables flexible definition of wei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1303.6938","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":"1303.6938","created_at":"2026-05-18T02:28:55.373021+00:00"},{"alias_kind":"arxiv_version","alias_value":"1303.6938v1","created_at":"2026-05-18T02:28:55.373021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1303.6938","created_at":"2026-05-18T02:28:55.373021+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYMOOSMVSRXT","created_at":"2026-05-18T12:27:43.054852+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYMOOSMVSRXTC2ZY","created_at":"2026-05-18T12:27:43.054852+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYMOOSMV","created_at":"2026-05-18T12:27:43.054852+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/DYMOOSMVSRXTC2ZYQGW74IZJSK","json":"https://pith.science/pith/DYMOOSMVSRXTC2ZYQGW74IZJSK.json","graph_json":"https://pith.science/api/pith-number/DYMOOSMVSRXTC2ZYQGW74IZJSK/graph.json","events_json":"https://pith.science/api/pith-number/DYMOOSMVSRXTC2ZYQGW74IZJSK/events.json","paper":"https://pith.science/paper/DYMOOSMV"},"agent_actions":{"view_html":"https://pith.science/pith/DYMOOSMVSRXTC2ZYQGW74IZJSK","download_json":"https://pith.science/pith/DYMOOSMVSRXTC2ZYQGW74IZJSK.json","view_paper":"https://pith.science/paper/DYMOOSMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1303.6938&json=true","fetch_graph":"https://pith.science/api/pith-number/DYMOOSMVSRXTC2ZYQGW74IZJSK/graph.json","fetch_events":"https://pith.science/api/pith-number/DYMOOSMVSRXTC2ZYQGW74IZJSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYMOOSMVSRXTC2ZYQGW74IZJSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYMOOSMVSRXTC2ZYQGW74IZJSK/action/storage_attestation","attest_author":"https://pith.science/pith/DYMOOSMVSRXTC2ZYQGW74IZJSK/action/author_attestation","sign_citation":"https://pith.science/pith/DYMOOSMVSRXTC2ZYQGW74IZJSK/action/citation_signature","submit_replication":"https://pith.science/pith/DYMOOSMVSRXTC2ZYQGW74IZJSK/action/replication_record"}},"created_at":"2026-05-18T02:28:55.373021+00:00","updated_at":"2026-05-18T02:28:55.373021+00:00"}