{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WY5KYF5LXMTLLFM6UHUX437GAJ","short_pith_number":"pith:WY5KYF5L","schema_version":"1.0","canonical_sha256":"b63aac17abbb26b5959ea1e97e6fe6027ba7ae2f5f3d900697bb4a9449ec144a","source":{"kind":"arxiv","id":"1906.03138","version":2},"attestation_state":"computed","paper":{"title":"Accurate deep neural network inference using computational phase-change memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.ET","authors_text":"Abu Sebastian, Bipin Rajendran, Christophe Piveteau, Evangelos Eleftheriou, Irem Boybat, Manuel Le Gallo, Martino Dazzi, Simon Haefeli, S.R. Nandakumar, Vinay Joshi","submitted_at":"2019-06-07T14:50:52Z","abstract_excerpt":"In-memory computing is a promising non-von Neumann approach for making energy-efficient deep learning inference hardware. Crossbar arrays of resistive memory devices can be used to encode the network weights and perform efficient analog matrix-vector multiplications without intermediate movements of data. However, due to device variability and noise, the network needs to be trained in a specific way so that transferring the digitally trained weights to the analog resistive memory devices will not result in significant loss of accuracy. Here, we introduce a methodology to train ResNet-type conv"},"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":"1906.03138","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.ET","submitted_at":"2019-06-07T14:50:52Z","cross_cats_sorted":[],"title_canon_sha256":"3cb96ef8b1a64fd01a862a685f8ceebcdf02235ee97143818a3e077283fc6ca2","abstract_canon_sha256":"9ee15b617d86dee9c1bbc36835025aabba5d632f33ed63f9fa4e4890555e0e7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:19.402420Z","signature_b64":"kLRhPbzYn09DMQHmOXCvLV+zb0EH8aoXas8Kpfgh5yucQ/03MOn4nwGT54lHn3Ya57MKas4AwgjOIiPRe3RYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b63aac17abbb26b5959ea1e97e6fe6027ba7ae2f5f3d900697bb4a9449ec144a","last_reissued_at":"2026-07-05T01:03:19.401907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:19.401907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accurate deep neural network inference using computational phase-change memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.ET","authors_text":"Abu Sebastian, Bipin Rajendran, Christophe Piveteau, Evangelos Eleftheriou, Irem Boybat, Manuel Le Gallo, Martino Dazzi, Simon Haefeli, S.R. Nandakumar, Vinay Joshi","submitted_at":"2019-06-07T14:50:52Z","abstract_excerpt":"In-memory computing is a promising non-von Neumann approach for making energy-efficient deep learning inference hardware. Crossbar arrays of resistive memory devices can be used to encode the network weights and perform efficient analog matrix-vector multiplications without intermediate movements of data. However, due to device variability and noise, the network needs to be trained in a specific way so that transferring the digitally trained weights to the analog resistive memory devices will not result in significant loss of accuracy. Here, we introduce a methodology to train ResNet-type conv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03138","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/1906.03138/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":"1906.03138","created_at":"2026-07-05T01:03:19.401967+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.03138v2","created_at":"2026-07-05T01:03:19.401967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03138","created_at":"2026-07-05T01:03:19.401967+00:00"},{"alias_kind":"pith_short_12","alias_value":"WY5KYF5LXMTL","created_at":"2026-07-05T01:03:19.401967+00:00"},{"alias_kind":"pith_short_16","alias_value":"WY5KYF5LXMTLLFM6","created_at":"2026-07-05T01:03:19.401967+00:00"},{"alias_kind":"pith_short_8","alias_value":"WY5KYF5L","created_at":"2026-07-05T01:03:19.401967+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18495","citing_title":"AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory Computing","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WY5KYF5LXMTLLFM6UHUX437GAJ","json":"https://pith.science/pith/WY5KYF5LXMTLLFM6UHUX437GAJ.json","graph_json":"https://pith.science/api/pith-number/WY5KYF5LXMTLLFM6UHUX437GAJ/graph.json","events_json":"https://pith.science/api/pith-number/WY5KYF5LXMTLLFM6UHUX437GAJ/events.json","paper":"https://pith.science/paper/WY5KYF5L"},"agent_actions":{"view_html":"https://pith.science/pith/WY5KYF5LXMTLLFM6UHUX437GAJ","download_json":"https://pith.science/pith/WY5KYF5LXMTLLFM6UHUX437GAJ.json","view_paper":"https://pith.science/paper/WY5KYF5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.03138&json=true","fetch_graph":"https://pith.science/api/pith-number/WY5KYF5LXMTLLFM6UHUX437GAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WY5KYF5LXMTLLFM6UHUX437GAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WY5KYF5LXMTLLFM6UHUX437GAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WY5KYF5LXMTLLFM6UHUX437GAJ/action/storage_attestation","attest_author":"https://pith.science/pith/WY5KYF5LXMTLLFM6UHUX437GAJ/action/author_attestation","sign_citation":"https://pith.science/pith/WY5KYF5LXMTLLFM6UHUX437GAJ/action/citation_signature","submit_replication":"https://pith.science/pith/WY5KYF5LXMTLLFM6UHUX437GAJ/action/replication_record"}},"created_at":"2026-07-05T01:03:19.401967+00:00","updated_at":"2026-07-05T01:03:19.401967+00:00"}