{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FAED2YDP3NKUIBOWDLTQDYSN44","short_pith_number":"pith:FAED2YDP","schema_version":"1.0","canonical_sha256":"28083d606fdb554405d61ae701e24de72fce372bdb1e51a591a3627b5fe6a5fb","source":{"kind":"arxiv","id":"1706.04332","version":3},"attestation_state":"computed","paper":{"title":"MATIC: Learning Around Errors for Efficient Low-Voltage Neural Network Accelerators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Armin Alaghi, Luis Ceze, Patrick Howe, Sung Kim, Thierry Moreau, Visvesh Sathe","submitted_at":"2017-06-14T06:36:02Z","abstract_excerpt":"As a result of the increasing demand for deep neural network (DNN)-based services, efforts to develop dedicated hardware accelerators for DNNs are growing rapidly. However,while accelerators with high performance and efficiency on convolutional deep neural networks (Conv-DNNs) have been developed, less progress has been made with regards to fully-connected DNNs (FC-DNNs). In this paper, we propose MATIC (Memory Adaptive Training with In-situ Canaries), a methodology that enables aggressive voltage scaling of accelerator weight memories to improve the energy-efficiency of DNN accelerators. To e"},"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":"1706.04332","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-06-14T06:36:02Z","cross_cats_sorted":[],"title_canon_sha256":"42f4e2968ecb0c1d73efb6ad6e2a8995046270198413edb4a1ecd0fb375d83f8","abstract_canon_sha256":"e955b51dd5ecd7e30785434336f66cbff55fe44c8eb30d63a35bd911d6bd3433"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:22.170370Z","signature_b64":"qK+jK/UbmvDm7YyMC3xrFLI4lktcBsM8itU21ETaTpkRnu33ogE1bkhtRn+NBILNXhjz4tITsd6bB/n1MdmfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28083d606fdb554405d61ae701e24de72fce372bdb1e51a591a3627b5fe6a5fb","last_reissued_at":"2026-05-18T00:20:22.169822Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:22.169822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MATIC: Learning Around Errors for Efficient Low-Voltage Neural Network Accelerators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Armin Alaghi, Luis Ceze, Patrick Howe, Sung Kim, Thierry Moreau, Visvesh Sathe","submitted_at":"2017-06-14T06:36:02Z","abstract_excerpt":"As a result of the increasing demand for deep neural network (DNN)-based services, efforts to develop dedicated hardware accelerators for DNNs are growing rapidly. However,while accelerators with high performance and efficiency on convolutional deep neural networks (Conv-DNNs) have been developed, less progress has been made with regards to fully-connected DNNs (FC-DNNs). In this paper, we propose MATIC (Memory Adaptive Training with In-situ Canaries), a methodology that enables aggressive voltage scaling of accelerator weight memories to improve the energy-efficiency of DNN accelerators. To e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04332","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":"1706.04332","created_at":"2026-05-18T00:20:22.169892+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.04332v3","created_at":"2026-05-18T00:20:22.169892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04332","created_at":"2026-05-18T00:20:22.169892+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAED2YDP3NKU","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAED2YDP3NKUIBOW","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAED2YDP","created_at":"2026-05-18T12:31:15.632608+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/FAED2YDP3NKUIBOWDLTQDYSN44","json":"https://pith.science/pith/FAED2YDP3NKUIBOWDLTQDYSN44.json","graph_json":"https://pith.science/api/pith-number/FAED2YDP3NKUIBOWDLTQDYSN44/graph.json","events_json":"https://pith.science/api/pith-number/FAED2YDP3NKUIBOWDLTQDYSN44/events.json","paper":"https://pith.science/paper/FAED2YDP"},"agent_actions":{"view_html":"https://pith.science/pith/FAED2YDP3NKUIBOWDLTQDYSN44","download_json":"https://pith.science/pith/FAED2YDP3NKUIBOWDLTQDYSN44.json","view_paper":"https://pith.science/paper/FAED2YDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.04332&json=true","fetch_graph":"https://pith.science/api/pith-number/FAED2YDP3NKUIBOWDLTQDYSN44/graph.json","fetch_events":"https://pith.science/api/pith-number/FAED2YDP3NKUIBOWDLTQDYSN44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAED2YDP3NKUIBOWDLTQDYSN44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAED2YDP3NKUIBOWDLTQDYSN44/action/storage_attestation","attest_author":"https://pith.science/pith/FAED2YDP3NKUIBOWDLTQDYSN44/action/author_attestation","sign_citation":"https://pith.science/pith/FAED2YDP3NKUIBOWDLTQDYSN44/action/citation_signature","submit_replication":"https://pith.science/pith/FAED2YDP3NKUIBOWDLTQDYSN44/action/replication_record"}},"created_at":"2026-05-18T00:20:22.169892+00:00","updated_at":"2026-05-18T00:20:22.169892+00:00"}