{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6M4TEEU7AM5FIA6EEE3MV5TLUK","short_pith_number":"pith:6M4TEEU7","schema_version":"1.0","canonical_sha256":"f33932129f033a5403c42136caf66ba2a9c9ddcfe29711ce9193ba0639a9247a","source":{"kind":"arxiv","id":"1901.10570","version":2},"attestation_state":"computed","paper":{"title":"Using Floating Gate Memory to Train Ideal Accuracy Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn"],"primary_cat":"cs.ET","authors_text":"Alex Hsia, Bruce Draper, Diana Garland, Elliot Fuller, Jacobs-Gedrim, John Niroula, Matthew J. Marinella, Michael S. Van Heukelom, Robin B, Sapan Agarwal","submitted_at":"2019-01-29T21:41:09Z","abstract_excerpt":"Floating gate SONOS (Silicon-Oxygen-Nitrogen-Oxygen-Silicon) transistors can be used to train neural networks to ideal accuracies that match those of floating point digital weights on the MNIST dataset when using multiple devices to represent a weight or within 1% of ideal accuracy when using a single device. This is enabled by operating devices in the subthreshold regime, where they exhibit symmetric write nonlinearities. A neural training accelerator core based on SONOS with a single device per weight would increase energy efficiency by 120X, operate 2.1X faster and require 5X lower area tha"},"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":"1901.10570","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.ET","submitted_at":"2019-01-29T21:41:09Z","cross_cats_sorted":["cond-mat.dis-nn"],"title_canon_sha256":"081a017622df514ab7fd30536215b4797f6b15fe0168b0bd74bde6ec23f55565","abstract_canon_sha256":"3c5cb511e1d4974dc3a3d2af36489616f719f9436f7388dbb12d25437c35e4d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:31.848395Z","signature_b64":"gVj917FwDsb3ivZ9kOrpYDhFX+IGwRc7Mz32Au1612rj2BffkSBVwhIJBkltJByQ3rlwSofOI1rRAfUpdn52Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f33932129f033a5403c42136caf66ba2a9c9ddcfe29711ce9193ba0639a9247a","last_reissued_at":"2026-05-17T23:52:31.847942Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:31.847942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Floating Gate Memory to Train Ideal Accuracy Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn"],"primary_cat":"cs.ET","authors_text":"Alex Hsia, Bruce Draper, Diana Garland, Elliot Fuller, Jacobs-Gedrim, John Niroula, Matthew J. Marinella, Michael S. Van Heukelom, Robin B, Sapan Agarwal","submitted_at":"2019-01-29T21:41:09Z","abstract_excerpt":"Floating gate SONOS (Silicon-Oxygen-Nitrogen-Oxygen-Silicon) transistors can be used to train neural networks to ideal accuracies that match those of floating point digital weights on the MNIST dataset when using multiple devices to represent a weight or within 1% of ideal accuracy when using a single device. This is enabled by operating devices in the subthreshold regime, where they exhibit symmetric write nonlinearities. A neural training accelerator core based on SONOS with a single device per weight would increase energy efficiency by 120X, operate 2.1X faster and require 5X lower area tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10570","kind":"arxiv","version":2},"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":"1901.10570","created_at":"2026-05-17T23:52:31.848015+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.10570v2","created_at":"2026-05-17T23:52:31.848015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10570","created_at":"2026-05-17T23:52:31.848015+00:00"},{"alias_kind":"pith_short_12","alias_value":"6M4TEEU7AM5F","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6M4TEEU7AM5FIA6E","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6M4TEEU7","created_at":"2026-05-18T12:33:10.108867+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/6M4TEEU7AM5FIA6EEE3MV5TLUK","json":"https://pith.science/pith/6M4TEEU7AM5FIA6EEE3MV5TLUK.json","graph_json":"https://pith.science/api/pith-number/6M4TEEU7AM5FIA6EEE3MV5TLUK/graph.json","events_json":"https://pith.science/api/pith-number/6M4TEEU7AM5FIA6EEE3MV5TLUK/events.json","paper":"https://pith.science/paper/6M4TEEU7"},"agent_actions":{"view_html":"https://pith.science/pith/6M4TEEU7AM5FIA6EEE3MV5TLUK","download_json":"https://pith.science/pith/6M4TEEU7AM5FIA6EEE3MV5TLUK.json","view_paper":"https://pith.science/paper/6M4TEEU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.10570&json=true","fetch_graph":"https://pith.science/api/pith-number/6M4TEEU7AM5FIA6EEE3MV5TLUK/graph.json","fetch_events":"https://pith.science/api/pith-number/6M4TEEU7AM5FIA6EEE3MV5TLUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6M4TEEU7AM5FIA6EEE3MV5TLUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6M4TEEU7AM5FIA6EEE3MV5TLUK/action/storage_attestation","attest_author":"https://pith.science/pith/6M4TEEU7AM5FIA6EEE3MV5TLUK/action/author_attestation","sign_citation":"https://pith.science/pith/6M4TEEU7AM5FIA6EEE3MV5TLUK/action/citation_signature","submit_replication":"https://pith.science/pith/6M4TEEU7AM5FIA6EEE3MV5TLUK/action/replication_record"}},"created_at":"2026-05-17T23:52:31.848015+00:00","updated_at":"2026-05-17T23:52:31.848015+00:00"}