{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:N4V4Z45K3QC34FHXDSAW3RYNSP","short_pith_number":"pith:N4V4Z45K","schema_version":"1.0","canonical_sha256":"6f2bccf3aadc05be14f71c816dc70d93ea1d68b2b26d8547f3e2a3680e53185b","source":{"kind":"arxiv","id":"1802.08530","version":1},"attestation_state":"computed","paper":{"title":"Training wide residual networks for deployment using a single bit for each weight","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mark D. McDonnell","submitted_at":"2018-02-23T13:54:23Z","abstract_excerpt":"For fast and energy-efficient deployment of trained deep neural networks on resource-constrained embedded hardware, each learned weight parameter should ideally be represented and stored using a single bit. Error-rates usually increase when this requirement is imposed. Here, we report large improvements in error rates on multiple datasets, for deep convolutional neural networks deployed with 1-bit-per-weight. Using wide residual networks as our main baseline, our approach simplifies existing methods that binarize weights by applying the sign function in training; we apply scaling factors for 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":"1802.08530","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-23T13:54:23Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"372717172f3da79bd0e4c75204cb76bf0d4817182b06f82ac0fe6353e9f5c7ff","abstract_canon_sha256":"75ef439722809b182a249be24cb511677074e187a2e2d3f20f665fdb9c849e38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:36.753713Z","signature_b64":"7pWzMFC7M2D4yfpnTFiH1Im2eRlyk2K9oHWzWcEPRHcz+9bctmnikT+bUAlHzAf8ToEbNU2f2h3TVtZFdOmvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f2bccf3aadc05be14f71c816dc70d93ea1d68b2b26d8547f3e2a3680e53185b","last_reissued_at":"2026-05-18T00:22:36.753129Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:36.753129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training wide residual networks for deployment using a single bit for each weight","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mark D. McDonnell","submitted_at":"2018-02-23T13:54:23Z","abstract_excerpt":"For fast and energy-efficient deployment of trained deep neural networks on resource-constrained embedded hardware, each learned weight parameter should ideally be represented and stored using a single bit. Error-rates usually increase when this requirement is imposed. Here, we report large improvements in error rates on multiple datasets, for deep convolutional neural networks deployed with 1-bit-per-weight. Using wide residual networks as our main baseline, our approach simplifies existing methods that binarize weights by applying the sign function in training; we apply scaling factors for e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08530","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":""},"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":"1802.08530","created_at":"2026-05-18T00:22:36.753206+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.08530v1","created_at":"2026-05-18T00:22:36.753206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08530","created_at":"2026-05-18T00:22:36.753206+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4V4Z45K3QC3","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4V4Z45K3QC34FHX","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4V4Z45K","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.06916","citing_title":"Single-bit-per-weight deep convolutional neural networks without batch-normalization layers for embedded systems","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N4V4Z45K3QC34FHXDSAW3RYNSP","json":"https://pith.science/pith/N4V4Z45K3QC34FHXDSAW3RYNSP.json","graph_json":"https://pith.science/api/pith-number/N4V4Z45K3QC34FHXDSAW3RYNSP/graph.json","events_json":"https://pith.science/api/pith-number/N4V4Z45K3QC34FHXDSAW3RYNSP/events.json","paper":"https://pith.science/paper/N4V4Z45K"},"agent_actions":{"view_html":"https://pith.science/pith/N4V4Z45K3QC34FHXDSAW3RYNSP","download_json":"https://pith.science/pith/N4V4Z45K3QC34FHXDSAW3RYNSP.json","view_paper":"https://pith.science/paper/N4V4Z45K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.08530&json=true","fetch_graph":"https://pith.science/api/pith-number/N4V4Z45K3QC34FHXDSAW3RYNSP/graph.json","fetch_events":"https://pith.science/api/pith-number/N4V4Z45K3QC34FHXDSAW3RYNSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4V4Z45K3QC34FHXDSAW3RYNSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4V4Z45K3QC34FHXDSAW3RYNSP/action/storage_attestation","attest_author":"https://pith.science/pith/N4V4Z45K3QC34FHXDSAW3RYNSP/action/author_attestation","sign_citation":"https://pith.science/pith/N4V4Z45K3QC34FHXDSAW3RYNSP/action/citation_signature","submit_replication":"https://pith.science/pith/N4V4Z45K3QC34FHXDSAW3RYNSP/action/replication_record"}},"created_at":"2026-05-18T00:22:36.753206+00:00","updated_at":"2026-05-18T00:22:36.753206+00:00"}