{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HAIAA34HIFY7NR5FCOOFX2SBKL","short_pith_number":"pith:HAIAA34H","schema_version":"1.0","canonical_sha256":"3810006f874171f6c7a5139c5bea4152e1d4a713a9209325de25b13aa8c72888","source":{"kind":"arxiv","id":"1904.01705","version":1},"attestation_state":"computed","paper":{"title":"Improving Noise Tolerance of Mixed-Signal Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.ET","authors_text":"Dmitri B. Strukov, Michael Klachko, Mohammad Reza Mahmoodi","submitted_at":"2019-04-02T23:24:18Z","abstract_excerpt":"Mixed-signal hardware accelerators for deep learning achieve orders of magnitude better power efficiency than their digital counterparts. In the ultra-low power consumption regime, limited signal precision inherent to analog computation becomes a challenge. We perform a case study of a 6-layer convolutional neural network running on a mixed-signal accelerator and evaluate its sensitivity to hardware specific noise. We apply various methods to improve noise robustness of the network and demonstrate an effective way to optimize useful signal ranges through adaptive signal clipping. The resulting"},"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":"1904.01705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.ET","submitted_at":"2019-04-02T23:24:18Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"33aacb75b792f93e4d23aee87b16b9f0dd55cffc0a7098d34680e2d03fd13374","abstract_canon_sha256":"5cefbf37d81bfed69ded1be8431dee686438649d2dcb5cb97d2997a6057a6036"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:30.095011Z","signature_b64":"IFODZgMiHFBGl1dj2/5UGrN8Y3CPGq/2cnZmDyt9MkSOeM+ohrCSxWtvIU86q/vViI6KuHv4f1FQIAkgKvKcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3810006f874171f6c7a5139c5bea4152e1d4a713a9209325de25b13aa8c72888","last_reissued_at":"2026-05-17T23:49:30.094406Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:30.094406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Noise Tolerance of Mixed-Signal Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.ET","authors_text":"Dmitri B. Strukov, Michael Klachko, Mohammad Reza Mahmoodi","submitted_at":"2019-04-02T23:24:18Z","abstract_excerpt":"Mixed-signal hardware accelerators for deep learning achieve orders of magnitude better power efficiency than their digital counterparts. In the ultra-low power consumption regime, limited signal precision inherent to analog computation becomes a challenge. We perform a case study of a 6-layer convolutional neural network running on a mixed-signal accelerator and evaluate its sensitivity to hardware specific noise. We apply various methods to improve noise robustness of the network and demonstrate an effective way to optimize useful signal ranges through adaptive signal clipping. The resulting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01705","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":"1904.01705","created_at":"2026-05-17T23:49:30.094522+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.01705v1","created_at":"2026-05-17T23:49:30.094522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01705","created_at":"2026-05-17T23:49:30.094522+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAIAA34HIFY7","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAIAA34HIFY7NR5F","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAIAA34H","created_at":"2026-05-18T12:33:18.533446+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/HAIAA34HIFY7NR5FCOOFX2SBKL","json":"https://pith.science/pith/HAIAA34HIFY7NR5FCOOFX2SBKL.json","graph_json":"https://pith.science/api/pith-number/HAIAA34HIFY7NR5FCOOFX2SBKL/graph.json","events_json":"https://pith.science/api/pith-number/HAIAA34HIFY7NR5FCOOFX2SBKL/events.json","paper":"https://pith.science/paper/HAIAA34H"},"agent_actions":{"view_html":"https://pith.science/pith/HAIAA34HIFY7NR5FCOOFX2SBKL","download_json":"https://pith.science/pith/HAIAA34HIFY7NR5FCOOFX2SBKL.json","view_paper":"https://pith.science/paper/HAIAA34H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.01705&json=true","fetch_graph":"https://pith.science/api/pith-number/HAIAA34HIFY7NR5FCOOFX2SBKL/graph.json","fetch_events":"https://pith.science/api/pith-number/HAIAA34HIFY7NR5FCOOFX2SBKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAIAA34HIFY7NR5FCOOFX2SBKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAIAA34HIFY7NR5FCOOFX2SBKL/action/storage_attestation","attest_author":"https://pith.science/pith/HAIAA34HIFY7NR5FCOOFX2SBKL/action/author_attestation","sign_citation":"https://pith.science/pith/HAIAA34HIFY7NR5FCOOFX2SBKL/action/citation_signature","submit_replication":"https://pith.science/pith/HAIAA34HIFY7NR5FCOOFX2SBKL/action/replication_record"}},"created_at":"2026-05-17T23:49:30.094522+00:00","updated_at":"2026-05-17T23:49:30.094522+00:00"}