{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:EOSAVP4T57AQNPETLSQZB2HXEA","short_pith_number":"pith:EOSAVP4T","schema_version":"1.0","canonical_sha256":"23a40abf93efc106bc935ca190e8f72033e2d9798328fe7bb9630161803fd40e","source":{"kind":"arxiv","id":"1606.07786","version":2},"attestation_state":"computed","paper":{"title":"Precise neural network computation with imprecise analog devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Daniel Neil, Giacomo Indiveri, Jonathan Binas, Michael Pfeiffer, Shih-Chii Liu","submitted_at":"2016-06-23T18:32:43Z","abstract_excerpt":"The operations used for neural network computation map favorably onto simple analog circuits, which outshine their digital counterparts in terms of compactness and efficiency. Nevertheless, such implementations have been largely supplanted by digital designs, partly because of device mismatch effects due to material and fabrication imperfections. We propose a framework that exploits the power of deep learning to compensate for this mismatch by incorporating the measured device variations as constraints in the neural network training process. This eliminates the need for mismatch minimization s"},"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":"1606.07786","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-06-23T18:32:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9aedb76e3da6341733bf3d68f63ecef56a49c47aae01652c4a25e80ea043fcb2","abstract_canon_sha256":"35cd0db2ca132e34c1d9ff1920b18ad8080ae2b33fcf42fd4df7bb5e7aa43847"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:51.188435Z","signature_b64":"aDb0iMSfRH75e+DNIQdUB0HAjkV2KXIq96e7/7RkuYDvI5iOCTq9gBwOILrAetpY1cA3zwK+41goKaRwF94TAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23a40abf93efc106bc935ca190e8f72033e2d9798328fe7bb9630161803fd40e","last_reissued_at":"2026-07-05T00:42:51.187980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:51.187980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Precise neural network computation with imprecise analog devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Daniel Neil, Giacomo Indiveri, Jonathan Binas, Michael Pfeiffer, Shih-Chii Liu","submitted_at":"2016-06-23T18:32:43Z","abstract_excerpt":"The operations used for neural network computation map favorably onto simple analog circuits, which outshine their digital counterparts in terms of compactness and efficiency. Nevertheless, such implementations have been largely supplanted by digital designs, partly because of device mismatch effects due to material and fabrication imperfections. We propose a framework that exploits the power of deep learning to compensate for this mismatch by incorporating the measured device variations as constraints in the neural network training process. This eliminates the need for mismatch minimization s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.07786","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1606.07786/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":"1606.07786","created_at":"2026-07-05T00:42:51.188048+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.07786v2","created_at":"2026-07-05T00:42:51.188048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.07786","created_at":"2026-07-05T00:42:51.188048+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOSAVP4T57AQ","created_at":"2026-07-05T00:42:51.188048+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOSAVP4T57AQNPET","created_at":"2026-07-05T00:42:51.188048+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOSAVP4T","created_at":"2026-07-05T00:42:51.188048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14531","citing_title":"On Hardening DNNs against Noisy Computations","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EOSAVP4T57AQNPETLSQZB2HXEA","json":"https://pith.science/pith/EOSAVP4T57AQNPETLSQZB2HXEA.json","graph_json":"https://pith.science/api/pith-number/EOSAVP4T57AQNPETLSQZB2HXEA/graph.json","events_json":"https://pith.science/api/pith-number/EOSAVP4T57AQNPETLSQZB2HXEA/events.json","paper":"https://pith.science/paper/EOSAVP4T"},"agent_actions":{"view_html":"https://pith.science/pith/EOSAVP4T57AQNPETLSQZB2HXEA","download_json":"https://pith.science/pith/EOSAVP4T57AQNPETLSQZB2HXEA.json","view_paper":"https://pith.science/paper/EOSAVP4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.07786&json=true","fetch_graph":"https://pith.science/api/pith-number/EOSAVP4T57AQNPETLSQZB2HXEA/graph.json","fetch_events":"https://pith.science/api/pith-number/EOSAVP4T57AQNPETLSQZB2HXEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOSAVP4T57AQNPETLSQZB2HXEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOSAVP4T57AQNPETLSQZB2HXEA/action/storage_attestation","attest_author":"https://pith.science/pith/EOSAVP4T57AQNPETLSQZB2HXEA/action/author_attestation","sign_citation":"https://pith.science/pith/EOSAVP4T57AQNPETLSQZB2HXEA/action/citation_signature","submit_replication":"https://pith.science/pith/EOSAVP4T57AQNPETLSQZB2HXEA/action/replication_record"}},"created_at":"2026-07-05T00:42:51.188048+00:00","updated_at":"2026-07-05T00:42:51.188048+00:00"}