{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZKJLDE2S7D72QXR5SD6O2TJA6W","short_pith_number":"pith:ZKJLDE2S","schema_version":"1.0","canonical_sha256":"ca92b19352f8ffa85e3d90fced4d20f5aa011fd42c64de5e6649de4d7fad2250","source":{"kind":"arxiv","id":"1803.03764","version":5},"attestation_state":"computed","paper":{"title":"Variance Networks: When Expectation Does Not Meet Your Expectations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Arsenii Ashukha, Dmitry Molchanov, Dmitry Vetrov, Kirill Neklyudov","submitted_at":"2018-03-10T06:01:40Z","abstract_excerpt":"Ordinary stochastic neural networks mostly rely on the expected values of their weights to make predictions, whereas the induced noise is mostly used to capture the uncertainty, prevent overfitting and slightly boost the performance through test-time averaging. In this paper, we introduce variance layers, a different kind of stochastic layers. Each weight of a variance layer follows a zero-mean distribution and is only parameterized by its variance. We show that such layers can learn surprisingly well, can serve as an efficient exploration tool in reinforcement learning tasks and provide a dec"},"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":"1803.03764","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2018-03-10T06:01:40Z","cross_cats_sorted":[],"title_canon_sha256":"faee2b3bd5e9c8adb253a53dee7793145e32dcda3d16e828dd2bf53edca60c29","abstract_canon_sha256":"43a0d5091d692df6aa8a2c9939ef773bf9c77b62a078f75ac5f00166886e199f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:51.595188Z","signature_b64":"KYFj1Kg6bqvYZ+FKPebukXBR3LojHU3lBLNu6vFQKMNzD9hSlxY/83DMOC9k5BzqinrO88E67PeVnvnjtrDKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca92b19352f8ffa85e3d90fced4d20f5aa011fd42c64de5e6649de4d7fad2250","last_reissued_at":"2026-05-17T23:53:51.594484Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:51.594484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variance Networks: When Expectation Does Not Meet Your Expectations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Arsenii Ashukha, Dmitry Molchanov, Dmitry Vetrov, Kirill Neklyudov","submitted_at":"2018-03-10T06:01:40Z","abstract_excerpt":"Ordinary stochastic neural networks mostly rely on the expected values of their weights to make predictions, whereas the induced noise is mostly used to capture the uncertainty, prevent overfitting and slightly boost the performance through test-time averaging. In this paper, we introduce variance layers, a different kind of stochastic layers. Each weight of a variance layer follows a zero-mean distribution and is only parameterized by its variance. We show that such layers can learn surprisingly well, can serve as an efficient exploration tool in reinforcement learning tasks and provide a dec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.03764","kind":"arxiv","version":5},"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":"1803.03764","created_at":"2026-05-17T23:53:51.594598+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.03764v5","created_at":"2026-05-17T23:53:51.594598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.03764","created_at":"2026-05-17T23:53:51.594598+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKJLDE2S7D72","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKJLDE2S7D72QXR5","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKJLDE2S","created_at":"2026-05-18T12:33:07.085635+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/ZKJLDE2S7D72QXR5SD6O2TJA6W","json":"https://pith.science/pith/ZKJLDE2S7D72QXR5SD6O2TJA6W.json","graph_json":"https://pith.science/api/pith-number/ZKJLDE2S7D72QXR5SD6O2TJA6W/graph.json","events_json":"https://pith.science/api/pith-number/ZKJLDE2S7D72QXR5SD6O2TJA6W/events.json","paper":"https://pith.science/paper/ZKJLDE2S"},"agent_actions":{"view_html":"https://pith.science/pith/ZKJLDE2S7D72QXR5SD6O2TJA6W","download_json":"https://pith.science/pith/ZKJLDE2S7D72QXR5SD6O2TJA6W.json","view_paper":"https://pith.science/paper/ZKJLDE2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.03764&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKJLDE2S7D72QXR5SD6O2TJA6W/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKJLDE2S7D72QXR5SD6O2TJA6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKJLDE2S7D72QXR5SD6O2TJA6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKJLDE2S7D72QXR5SD6O2TJA6W/action/storage_attestation","attest_author":"https://pith.science/pith/ZKJLDE2S7D72QXR5SD6O2TJA6W/action/author_attestation","sign_citation":"https://pith.science/pith/ZKJLDE2S7D72QXR5SD6O2TJA6W/action/citation_signature","submit_replication":"https://pith.science/pith/ZKJLDE2S7D72QXR5SD6O2TJA6W/action/replication_record"}},"created_at":"2026-05-17T23:53:51.594598+00:00","updated_at":"2026-05-17T23:53:51.594598+00:00"}