{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TRYX5FT2GLAFFRMLRXTA5X2QLR","short_pith_number":"pith:TRYX5FT2","schema_version":"1.0","canonical_sha256":"9c717e967a32c052c58b8de60edf505c6ae8c809db224c9d0deb930e2f24dd21","source":{"kind":"arxiv","id":"1908.07748","version":2},"attestation_state":"computed","paper":{"title":"RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Bohan Zhuang, Chunlei Liu, Guodong Guo, Jianzhuang Liu, Wenrui Ding, Xin Xia, Yuan Hu","submitted_at":"2019-08-21T08:28:44Z","abstract_excerpt":"Binarized convolutional neural networks (BCNNs) are widely used to improve memory and computation efficiency of deep convolutional neural networks (DCNNs) for mobile and AI chips based applications. However, current BCNNs are not able to fully explore their corresponding full-precision models, causing a significant performance gap between them. In this paper, we propose rectified binary convolutional networks (RBCNs), towards optimized BCNNs, by combining full-precision kernels and feature maps to rectify the binarization process in a unified framework. In particular, we use a GAN to train the"},"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":"1908.07748","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-21T08:28:44Z","cross_cats_sorted":[],"title_canon_sha256":"6c16b48bc8fa53a4b2f4156d45ed89a5395a853241dc7e96f371a73cfc6feb56","abstract_canon_sha256":"a19ab6e30a00ef50a7c5adeee2d250ae50d9803c5f1e82c7d8e94e37c1e7287d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:39.956435Z","signature_b64":"RiUQZtHksKorl+CH9egokIyJUmCw7fQvGIqFn7ghcDg/YOipoXorgFotAPP1zBid8P4DzVe6ulOKjJGtGXbDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c717e967a32c052c58b8de60edf505c6ae8c809db224c9d0deb930e2f24dd21","last_reissued_at":"2026-07-05T00:02:39.956034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:39.956034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Bohan Zhuang, Chunlei Liu, Guodong Guo, Jianzhuang Liu, Wenrui Ding, Xin Xia, Yuan Hu","submitted_at":"2019-08-21T08:28:44Z","abstract_excerpt":"Binarized convolutional neural networks (BCNNs) are widely used to improve memory and computation efficiency of deep convolutional neural networks (DCNNs) for mobile and AI chips based applications. However, current BCNNs are not able to fully explore their corresponding full-precision models, causing a significant performance gap between them. In this paper, we propose rectified binary convolutional networks (RBCNs), towards optimized BCNNs, by combining full-precision kernels and feature maps to rectify the binarization process in a unified framework. In particular, we use a GAN to train the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07748","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/1908.07748/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":"1908.07748","created_at":"2026-07-05T00:02:39.956100+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.07748v2","created_at":"2026-07-05T00:02:39.956100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07748","created_at":"2026-07-05T00:02:39.956100+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRYX5FT2GLAF","created_at":"2026-07-05T00:02:39.956100+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRYX5FT2GLAFFRML","created_at":"2026-07-05T00:02:39.956100+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRYX5FT2","created_at":"2026-07-05T00:02:39.956100+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/TRYX5FT2GLAFFRMLRXTA5X2QLR","json":"https://pith.science/pith/TRYX5FT2GLAFFRMLRXTA5X2QLR.json","graph_json":"https://pith.science/api/pith-number/TRYX5FT2GLAFFRMLRXTA5X2QLR/graph.json","events_json":"https://pith.science/api/pith-number/TRYX5FT2GLAFFRMLRXTA5X2QLR/events.json","paper":"https://pith.science/paper/TRYX5FT2"},"agent_actions":{"view_html":"https://pith.science/pith/TRYX5FT2GLAFFRMLRXTA5X2QLR","download_json":"https://pith.science/pith/TRYX5FT2GLAFFRMLRXTA5X2QLR.json","view_paper":"https://pith.science/paper/TRYX5FT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.07748&json=true","fetch_graph":"https://pith.science/api/pith-number/TRYX5FT2GLAFFRMLRXTA5X2QLR/graph.json","fetch_events":"https://pith.science/api/pith-number/TRYX5FT2GLAFFRMLRXTA5X2QLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRYX5FT2GLAFFRMLRXTA5X2QLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRYX5FT2GLAFFRMLRXTA5X2QLR/action/storage_attestation","attest_author":"https://pith.science/pith/TRYX5FT2GLAFFRMLRXTA5X2QLR/action/author_attestation","sign_citation":"https://pith.science/pith/TRYX5FT2GLAFFRMLRXTA5X2QLR/action/citation_signature","submit_replication":"https://pith.science/pith/TRYX5FT2GLAFFRMLRXTA5X2QLR/action/replication_record"}},"created_at":"2026-07-05T00:02:39.956100+00:00","updated_at":"2026-07-05T00:02:39.956100+00:00"}