{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:NWGBSLYECNMFGGNHFM3AHY4VWJ","short_pith_number":"pith:NWGBSLYE","schema_version":"1.0","canonical_sha256":"6d8c192f0413585319a72b3603e395b27234b8d22d228d0d470642bde42c6287","source":{"kind":"arxiv","id":"1511.00363","version":3},"attestation_state":"computed","paper":{"title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jean-Pierre David, Matthieu Courbariaux, Yoshua Bengio","submitted_at":"2015-11-02T02:50:05Z","abstract_excerpt":"Deep Neural Networks (DNN) have achieved state-of-the-art results in a wide range of tasks, with the best results obtained with large training sets and large models. In the past, GPUs enabled these breakthroughs because of their greater computational speed. In the future, faster computation at both training and test time is likely to be crucial for further progress and for consumer applications on low-power devices. As a result, there is much interest in research and development of dedicated hardware for Deep Learning (DL). Binary weights, i.e., weights which are constrained to only two possib"},"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":"1511.00363","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-02T02:50:05Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"a15ceec5d5ca225a3b24f5ee030a5f7f37fa4737ee499724721312d6625a40cb","abstract_canon_sha256":"12a04156a327cdc982afd5eee4990891c197a259d020d4210993f5ba4646a3ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:00.090120Z","signature_b64":"wTf4hLO7iTT/EDqDyRrJZ3OYTbdY3QEFnDqW9p4pV6xamRbRvKqd/wtC1993JD1xNTJjUZMjvb/rmnN26mIjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d8c192f0413585319a72b3603e395b27234b8d22d228d0d470642bde42c6287","last_reissued_at":"2026-05-18T01:17:00.089466Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:00.089466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jean-Pierre David, Matthieu Courbariaux, Yoshua Bengio","submitted_at":"2015-11-02T02:50:05Z","abstract_excerpt":"Deep Neural Networks (DNN) have achieved state-of-the-art results in a wide range of tasks, with the best results obtained with large training sets and large models. In the past, GPUs enabled these breakthroughs because of their greater computational speed. In the future, faster computation at both training and test time is likely to be crucial for further progress and for consumer applications on low-power devices. As a result, there is much interest in research and development of dedicated hardware for Deep Learning (DL). Binary weights, i.e., weights which are constrained to only two possib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.00363","kind":"arxiv","version":3},"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":"1511.00363","created_at":"2026-05-18T01:17:00.089569+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.00363v3","created_at":"2026-05-18T01:17:00.089569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.00363","created_at":"2026-05-18T01:17:00.089569+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWGBSLYECNMF","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWGBSLYECNMFGGNH","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWGBSLYE","created_at":"2026-05-18T12:29:34.919912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1906.12172","citing_title":"New pointwise convolution in Deep Neural Networks through Extremely Fast and Non Parametric Transforms","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06916","citing_title":"Single-bit-per-weight deep convolutional neural networks without batch-normalization layers for embedded systems","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11840","citing_title":"Learning Instance-wise Sparsity for Accelerating Deep Models","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2501.19221","citing_title":"VeloxQ: A Fast and Efficient QUBO Solver","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18933","citing_title":"A Geometric Analysis of Sign-Magnitude Asymmetry in a ReLU + RMSNorm Block under Ternary Quantization","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NWGBSLYECNMFGGNHFM3AHY4VWJ","json":"https://pith.science/pith/NWGBSLYECNMFGGNHFM3AHY4VWJ.json","graph_json":"https://pith.science/api/pith-number/NWGBSLYECNMFGGNHFM3AHY4VWJ/graph.json","events_json":"https://pith.science/api/pith-number/NWGBSLYECNMFGGNHFM3AHY4VWJ/events.json","paper":"https://pith.science/paper/NWGBSLYE"},"agent_actions":{"view_html":"https://pith.science/pith/NWGBSLYECNMFGGNHFM3AHY4VWJ","download_json":"https://pith.science/pith/NWGBSLYECNMFGGNHFM3AHY4VWJ.json","view_paper":"https://pith.science/paper/NWGBSLYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.00363&json=true","fetch_graph":"https://pith.science/api/pith-number/NWGBSLYECNMFGGNHFM3AHY4VWJ/graph.json","fetch_events":"https://pith.science/api/pith-number/NWGBSLYECNMFGGNHFM3AHY4VWJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWGBSLYECNMFGGNHFM3AHY4VWJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWGBSLYECNMFGGNHFM3AHY4VWJ/action/storage_attestation","attest_author":"https://pith.science/pith/NWGBSLYECNMFGGNHFM3AHY4VWJ/action/author_attestation","sign_citation":"https://pith.science/pith/NWGBSLYECNMFGGNHFM3AHY4VWJ/action/citation_signature","submit_replication":"https://pith.science/pith/NWGBSLYECNMFGGNHFM3AHY4VWJ/action/replication_record"}},"created_at":"2026-05-18T01:17:00.089569+00:00","updated_at":"2026-05-18T01:17:00.089569+00:00"}