{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SLVDF3QS5QFSNNWP52LOLIXZVZ","short_pith_number":"pith:SLVDF3QS","schema_version":"1.0","canonical_sha256":"92ea32ee12ec0b26b6cfee96e5a2f9ae655ce89a49e2474a26b7f02fa45c5388","source":{"kind":"arxiv","id":"1802.02643","version":3},"attestation_state":"computed","paper":{"title":"Gradient conjugate priors and multi-layer neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Hannes Stuke, Pavel Gurevich","submitted_at":"2018-02-07T21:29:52Z","abstract_excerpt":"The paper deals with learning probability distributions of observed data by artificial neural networks. We suggest a so-called gradient conjugate prior (GCP) update appropriate for neural networks, which is a modification of the classical Bayesian update for conjugate priors. We establish a connection between the gradient conjugate prior update and the maximization of the log-likelihood of the predictive distribution. Unlike for the Bayesian neural networks, we use deterministic weights of neural networks, but rather assume that the ground truth distribution is normal with unknown mean and var"},"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":"1802.02643","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-02-07T21:29:52Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"e42e3220278c0adb79efd7f1ced2a9aa2b1b35d92f0fddb31abf704c7df8c680","abstract_canon_sha256":"edcf9e64bec0ec4502e252c1ce1f4977b8c2b1e4703b2db6107b232252a32170"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:28.510987Z","signature_b64":"+pPgr7OYab9CH5Y2TcXE+7+KlN35tsvghuMVZGVaVQK/O0NUPOv46wh3OfrnzZrCxFpODGWpmJZyGjY7OAnoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92ea32ee12ec0b26b6cfee96e5a2f9ae655ce89a49e2474a26b7f02fa45c5388","last_reissued_at":"2026-05-17T23:50:28.510309Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:28.510309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient conjugate priors and multi-layer neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Hannes Stuke, Pavel Gurevich","submitted_at":"2018-02-07T21:29:52Z","abstract_excerpt":"The paper deals with learning probability distributions of observed data by artificial neural networks. We suggest a so-called gradient conjugate prior (GCP) update appropriate for neural networks, which is a modification of the classical Bayesian update for conjugate priors. We establish a connection between the gradient conjugate prior update and the maximization of the log-likelihood of the predictive distribution. Unlike for the Bayesian neural networks, we use deterministic weights of neural networks, but rather assume that the ground truth distribution is normal with unknown mean and var"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.02643","kind":"arxiv","version":3},"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":"1802.02643","created_at":"2026-05-17T23:50:28.510418+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.02643v3","created_at":"2026-05-17T23:50:28.510418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.02643","created_at":"2026-05-17T23:50:28.510418+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLVDF3QS5QFS","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLVDF3QS5QFSNNWP","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLVDF3QS","created_at":"2026-05-18T12:32:53.628368+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/SLVDF3QS5QFSNNWP52LOLIXZVZ","json":"https://pith.science/pith/SLVDF3QS5QFSNNWP52LOLIXZVZ.json","graph_json":"https://pith.science/api/pith-number/SLVDF3QS5QFSNNWP52LOLIXZVZ/graph.json","events_json":"https://pith.science/api/pith-number/SLVDF3QS5QFSNNWP52LOLIXZVZ/events.json","paper":"https://pith.science/paper/SLVDF3QS"},"agent_actions":{"view_html":"https://pith.science/pith/SLVDF3QS5QFSNNWP52LOLIXZVZ","download_json":"https://pith.science/pith/SLVDF3QS5QFSNNWP52LOLIXZVZ.json","view_paper":"https://pith.science/paper/SLVDF3QS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.02643&json=true","fetch_graph":"https://pith.science/api/pith-number/SLVDF3QS5QFSNNWP52LOLIXZVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/SLVDF3QS5QFSNNWP52LOLIXZVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLVDF3QS5QFSNNWP52LOLIXZVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLVDF3QS5QFSNNWP52LOLIXZVZ/action/storage_attestation","attest_author":"https://pith.science/pith/SLVDF3QS5QFSNNWP52LOLIXZVZ/action/author_attestation","sign_citation":"https://pith.science/pith/SLVDF3QS5QFSNNWP52LOLIXZVZ/action/citation_signature","submit_replication":"https://pith.science/pith/SLVDF3QS5QFSNNWP52LOLIXZVZ/action/replication_record"}},"created_at":"2026-05-17T23:50:28.510418+00:00","updated_at":"2026-05-17T23:50:28.510418+00:00"}