{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ESKNNKHYRX3LS6223CHSID7EVB","short_pith_number":"pith:ESKNNKHY","schema_version":"1.0","canonical_sha256":"2494d6a8f88df6b97b5ad88f240fe4a84278e7e82216758f7e70d9f30d1eea5a","source":{"kind":"arxiv","id":"1811.12465","version":1},"attestation_state":"computed","paper":{"title":"Uncertainty propagation in neural networks for sparse coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Danil Kuzin, Lyudmila Mihaylova, Olga Isupova","submitted_at":"2018-11-29T20:16:03Z","abstract_excerpt":"A novel method to propagate uncertainty through the soft-thresholding nonlinearity is proposed in this paper. At every layer the current distribution of the target vector is represented as a spike and slab distribution, which represents the probabilities of each variable being zero, or Gaussian-distributed. Using the proposed method of uncertainty propagation, the gradients of the logarithms of normalisation constants are derived, that can be used to update a weight distribution. A novel Bayesian neural network for sparse coding is designed utilising both the proposed method of uncertainty pro"},"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":"1811.12465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-11-29T20:16:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"250bf5569e26552c789e5fccd4faecdfe26aa0225fbac5075953482ddb5f9cec","abstract_canon_sha256":"710a91fd8d501a5668e68c7f76985023ffb7833da6cfcfb1d4ba4fa50c13ea8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:31.578721Z","signature_b64":"aLhoxT912PTBafJOGd2x1Z+rf+THIyrSbKq/uVjGSAKId/RNpE21cpOcR+qoAT5EEJEvy5WCH0/t46c//U9DDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2494d6a8f88df6b97b5ad88f240fe4a84278e7e82216758f7e70d9f30d1eea5a","last_reissued_at":"2026-05-17T23:59:31.578136Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:31.578136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty propagation in neural networks for sparse coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Danil Kuzin, Lyudmila Mihaylova, Olga Isupova","submitted_at":"2018-11-29T20:16:03Z","abstract_excerpt":"A novel method to propagate uncertainty through the soft-thresholding nonlinearity is proposed in this paper. At every layer the current distribution of the target vector is represented as a spike and slab distribution, which represents the probabilities of each variable being zero, or Gaussian-distributed. Using the proposed method of uncertainty propagation, the gradients of the logarithms of normalisation constants are derived, that can be used to update a weight distribution. A novel Bayesian neural network for sparse coding is designed utilising both the proposed method of uncertainty pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12465","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":"1811.12465","created_at":"2026-05-17T23:59:31.578215+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.12465v1","created_at":"2026-05-17T23:59:31.578215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12465","created_at":"2026-05-17T23:59:31.578215+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESKNNKHYRX3L","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESKNNKHYRX3LS622","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESKNNKHY","created_at":"2026-05-18T12:32:22.470017+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/ESKNNKHYRX3LS6223CHSID7EVB","json":"https://pith.science/pith/ESKNNKHYRX3LS6223CHSID7EVB.json","graph_json":"https://pith.science/api/pith-number/ESKNNKHYRX3LS6223CHSID7EVB/graph.json","events_json":"https://pith.science/api/pith-number/ESKNNKHYRX3LS6223CHSID7EVB/events.json","paper":"https://pith.science/paper/ESKNNKHY"},"agent_actions":{"view_html":"https://pith.science/pith/ESKNNKHYRX3LS6223CHSID7EVB","download_json":"https://pith.science/pith/ESKNNKHYRX3LS6223CHSID7EVB.json","view_paper":"https://pith.science/paper/ESKNNKHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.12465&json=true","fetch_graph":"https://pith.science/api/pith-number/ESKNNKHYRX3LS6223CHSID7EVB/graph.json","fetch_events":"https://pith.science/api/pith-number/ESKNNKHYRX3LS6223CHSID7EVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESKNNKHYRX3LS6223CHSID7EVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESKNNKHYRX3LS6223CHSID7EVB/action/storage_attestation","attest_author":"https://pith.science/pith/ESKNNKHYRX3LS6223CHSID7EVB/action/author_attestation","sign_citation":"https://pith.science/pith/ESKNNKHYRX3LS6223CHSID7EVB/action/citation_signature","submit_replication":"https://pith.science/pith/ESKNNKHYRX3LS6223CHSID7EVB/action/replication_record"}},"created_at":"2026-05-17T23:59:31.578215+00:00","updated_at":"2026-05-17T23:59:31.578215+00:00"}