{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PACZZ6JXWPLKSFJYW2P6VQGQQB","short_pith_number":"pith:PACZZ6JX","schema_version":"1.0","canonical_sha256":"78059cf937b3d6a91538b69feac0d08049aef7d52cd02eeefdfa20d5b48c08bd","source":{"kind":"arxiv","id":"1711.00449","version":2},"attestation_state":"computed","paper":{"title":"Attacking Binarized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Angus Galloway, Graham W. Taylor, Medhat Moussa","submitted_at":"2017-11-01T17:28:26Z","abstract_excerpt":"Neural networks with low-precision weights and activations offer compelling efficiency advantages over their full-precision equivalents. The two most frequently discussed benefits of quantization are reduced memory consumption, and a faster forward pass when implemented with efficient bitwise operations. We propose a third benefit of very low-precision neural networks: improved robustness against some adversarial attacks, and in the worst case, performance that is on par with full-precision models. We focus on the very low-precision case where weights and activations are both quantized to $\\pm"},"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":"1711.00449","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-01T17:28:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d6545853cea93063e433f78189fb76519553c2609f6d9a8eb35b99b995dcb3e1","abstract_canon_sha256":"dc94cfb543903b61b8af6cb557b33319e4d07402af39ab3a5123a3b7cec666e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:42.174529Z","signature_b64":"eizcorVVQZ0r6o+1HV8HfVsXiQOTx7ewp7cxvEJ1ORRzXeC1y/neUAJIvqo55k5htp+aPi4y6U2EkzjHSW7DCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78059cf937b3d6a91538b69feac0d08049aef7d52cd02eeefdfa20d5b48c08bd","last_reissued_at":"2026-05-18T00:24:42.173783Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:42.173783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attacking Binarized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Angus Galloway, Graham W. Taylor, Medhat Moussa","submitted_at":"2017-11-01T17:28:26Z","abstract_excerpt":"Neural networks with low-precision weights and activations offer compelling efficiency advantages over their full-precision equivalents. The two most frequently discussed benefits of quantization are reduced memory consumption, and a faster forward pass when implemented with efficient bitwise operations. We propose a third benefit of very low-precision neural networks: improved robustness against some adversarial attacks, and in the worst case, performance that is on par with full-precision models. We focus on the very low-precision case where weights and activations are both quantized to $\\pm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00449","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":"1711.00449","created_at":"2026-05-18T00:24:42.173897+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.00449v2","created_at":"2026-05-18T00:24:42.173897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00449","created_at":"2026-05-18T00:24:42.173897+00:00"},{"alias_kind":"pith_short_12","alias_value":"PACZZ6JXWPLK","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PACZZ6JXWPLKSFJY","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PACZZ6JX","created_at":"2026-05-18T12:31:37.085036+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/PACZZ6JXWPLKSFJYW2P6VQGQQB","json":"https://pith.science/pith/PACZZ6JXWPLKSFJYW2P6VQGQQB.json","graph_json":"https://pith.science/api/pith-number/PACZZ6JXWPLKSFJYW2P6VQGQQB/graph.json","events_json":"https://pith.science/api/pith-number/PACZZ6JXWPLKSFJYW2P6VQGQQB/events.json","paper":"https://pith.science/paper/PACZZ6JX"},"agent_actions":{"view_html":"https://pith.science/pith/PACZZ6JXWPLKSFJYW2P6VQGQQB","download_json":"https://pith.science/pith/PACZZ6JXWPLKSFJYW2P6VQGQQB.json","view_paper":"https://pith.science/paper/PACZZ6JX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.00449&json=true","fetch_graph":"https://pith.science/api/pith-number/PACZZ6JXWPLKSFJYW2P6VQGQQB/graph.json","fetch_events":"https://pith.science/api/pith-number/PACZZ6JXWPLKSFJYW2P6VQGQQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PACZZ6JXWPLKSFJYW2P6VQGQQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PACZZ6JXWPLKSFJYW2P6VQGQQB/action/storage_attestation","attest_author":"https://pith.science/pith/PACZZ6JXWPLKSFJYW2P6VQGQQB/action/author_attestation","sign_citation":"https://pith.science/pith/PACZZ6JXWPLKSFJYW2P6VQGQQB/action/citation_signature","submit_replication":"https://pith.science/pith/PACZZ6JXWPLKSFJYW2P6VQGQQB/action/replication_record"}},"created_at":"2026-05-18T00:24:42.173897+00:00","updated_at":"2026-05-18T00:24:42.173897+00:00"}