{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z5TV3QU6BN6C7WXNXVTK5RSSBN","short_pith_number":"pith:Z5TV3QU6","schema_version":"1.0","canonical_sha256":"cf675dc29e0b7c2fdaedbd66aec6520b7af8396f04d83ad85fa8eb8ac9b07064","source":{"kind":"arxiv","id":"2409.18553","version":1},"attestation_state":"computed","paper":{"title":"Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Massoud Pedram, Mehdi Kamal, Mohammad Erfan Sadeghi, Seyedarmin Azizi","submitted_at":"2024-09-27T08:45:55Z","abstract_excerpt":"In this paper, we propose a framework to enhance the robustness of the neural models by mitigating the effects of process-induced and aging-related variations of analog computing components on the accuracy of the analog neural networks. We model these variations as the noise affecting the precision of the activations and introduce a denoising block inserted between selected layers of a pre-trained model. We demonstrate that training the denoising block significantly increases the model's robustness against various noise levels. To minimize the overhead associated with adding these blocks, we p"},"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":"2409.18553","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-27T08:45:55Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"55d2be440a7384f6a743b0424f8eb919ce66c4cd1953213772ac59f2bd0d3328","abstract_canon_sha256":"3dcae078d847c1f406b901b70b66e5694103e095f2dd0966c7f49d0c235ef790"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:37.415257Z","signature_b64":"n08pXjIWA51kpuR3kAtn3GbsiG9mCBuCC6sXvJFE0/LB/x+Y7i3ty5biackFDpaUE9uBE4NY7A9YE8VXUbEnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf675dc29e0b7c2fdaedbd66aec6520b7af8396f04d83ad85fa8eb8ac9b07064","last_reissued_at":"2026-07-05T09:12:37.414808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:37.414808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Massoud Pedram, Mehdi Kamal, Mohammad Erfan Sadeghi, Seyedarmin Azizi","submitted_at":"2024-09-27T08:45:55Z","abstract_excerpt":"In this paper, we propose a framework to enhance the robustness of the neural models by mitigating the effects of process-induced and aging-related variations of analog computing components on the accuracy of the analog neural networks. We model these variations as the noise affecting the precision of the activations and introduce a denoising block inserted between selected layers of a pre-trained model. We demonstrate that training the denoising block significantly increases the model's robustness against various noise levels. To minimize the overhead associated with adding these blocks, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18553","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.18553/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2409.18553","created_at":"2026-07-05T09:12:37.414863+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18553v1","created_at":"2026-07-05T09:12:37.414863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18553","created_at":"2026-07-05T09:12:37.414863+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5TV3QU6BN6C","created_at":"2026-07-05T09:12:37.414863+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5TV3QU6BN6C7WXN","created_at":"2026-07-05T09:12:37.414863+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5TV3QU6","created_at":"2026-07-05T09:12:37.414863+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.00951","citing_title":"Preserving Privacy and Utility in LLM-Based Product Recommendations","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z5TV3QU6BN6C7WXNXVTK5RSSBN","json":"https://pith.science/pith/Z5TV3QU6BN6C7WXNXVTK5RSSBN.json","graph_json":"https://pith.science/api/pith-number/Z5TV3QU6BN6C7WXNXVTK5RSSBN/graph.json","events_json":"https://pith.science/api/pith-number/Z5TV3QU6BN6C7WXNXVTK5RSSBN/events.json","paper":"https://pith.science/paper/Z5TV3QU6"},"agent_actions":{"view_html":"https://pith.science/pith/Z5TV3QU6BN6C7WXNXVTK5RSSBN","download_json":"https://pith.science/pith/Z5TV3QU6BN6C7WXNXVTK5RSSBN.json","view_paper":"https://pith.science/paper/Z5TV3QU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18553&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5TV3QU6BN6C7WXNXVTK5RSSBN/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5TV3QU6BN6C7WXNXVTK5RSSBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5TV3QU6BN6C7WXNXVTK5RSSBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5TV3QU6BN6C7WXNXVTK5RSSBN/action/storage_attestation","attest_author":"https://pith.science/pith/Z5TV3QU6BN6C7WXNXVTK5RSSBN/action/author_attestation","sign_citation":"https://pith.science/pith/Z5TV3QU6BN6C7WXNXVTK5RSSBN/action/citation_signature","submit_replication":"https://pith.science/pith/Z5TV3QU6BN6C7WXNXVTK5RSSBN/action/replication_record"}},"created_at":"2026-07-05T09:12:37.414863+00:00","updated_at":"2026-07-05T09:12:37.414863+00:00"}