{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7FC4J5LR3F2VP532B66UWC57EY","short_pith_number":"pith:7FC4J5LR","schema_version":"1.0","canonical_sha256":"f945c4f571d97557f77a0fbd4b0bbf262fb9e903d3ba73afe5842ba85f2be55d","source":{"kind":"arxiv","id":"1706.02393","version":1},"attestation_state":"computed","paper":{"title":"ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Denis A. Gudovskiy, Luca Rigazio","submitted_at":"2017-06-07T22:00:25Z","abstract_excerpt":"In this paper we introduce ShiftCNN, a generalized low-precision architecture for inference of multiplierless convolutional neural networks (CNNs). ShiftCNN is based on a power-of-two weight representation and, as a result, performs only shift and addition operations. Furthermore, ShiftCNN substantially reduces computational cost of convolutional layers by precomputing convolution terms. Such an optimization can be applied to any CNN architecture with a relatively small codebook of weights and allows to decrease the number of product operations by at least two orders of magnitude. The proposed"},"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":"1706.02393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-07T22:00:25Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"df36460da3f2eb11a3575ea780355b1ee7c4a851311305bf1710ba0211f9f59d","abstract_canon_sha256":"12c6420174c26b9b94a759b9c0c6e84e75170a398e43a2f1062d3fa71392ee07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:45.604960Z","signature_b64":"fk1duih8hgb8h19Q/96KWV5sKkyAwtMB8QAaR3b5e3J55MBYlfsrNcSQFM7hlF3qgQLgDSMBV+HdPGIIAhe6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f945c4f571d97557f77a0fbd4b0bbf262fb9e903d3ba73afe5842ba85f2be55d","last_reissued_at":"2026-05-18T00:42:45.604545Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:45.604545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Denis A. Gudovskiy, Luca Rigazio","submitted_at":"2017-06-07T22:00:25Z","abstract_excerpt":"In this paper we introduce ShiftCNN, a generalized low-precision architecture for inference of multiplierless convolutional neural networks (CNNs). ShiftCNN is based on a power-of-two weight representation and, as a result, performs only shift and addition operations. Furthermore, ShiftCNN substantially reduces computational cost of convolutional layers by precomputing convolution terms. Such an optimization can be applied to any CNN architecture with a relatively small codebook of weights and allows to decrease the number of product operations by at least two orders of magnitude. The proposed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02393","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":"1706.02393","created_at":"2026-05-18T00:42:45.604601+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.02393v1","created_at":"2026-05-18T00:42:45.604601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02393","created_at":"2026-05-18T00:42:45.604601+00:00"},{"alias_kind":"pith_short_12","alias_value":"7FC4J5LR3F2V","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7FC4J5LR3F2VP532","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7FC4J5LR","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06082","citing_title":"PoTAcc: A Pipeline for End-to-End Acceleration of Power-of-Two Quantized DNNs","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7FC4J5LR3F2VP532B66UWC57EY","json":"https://pith.science/pith/7FC4J5LR3F2VP532B66UWC57EY.json","graph_json":"https://pith.science/api/pith-number/7FC4J5LR3F2VP532B66UWC57EY/graph.json","events_json":"https://pith.science/api/pith-number/7FC4J5LR3F2VP532B66UWC57EY/events.json","paper":"https://pith.science/paper/7FC4J5LR"},"agent_actions":{"view_html":"https://pith.science/pith/7FC4J5LR3F2VP532B66UWC57EY","download_json":"https://pith.science/pith/7FC4J5LR3F2VP532B66UWC57EY.json","view_paper":"https://pith.science/paper/7FC4J5LR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.02393&json=true","fetch_graph":"https://pith.science/api/pith-number/7FC4J5LR3F2VP532B66UWC57EY/graph.json","fetch_events":"https://pith.science/api/pith-number/7FC4J5LR3F2VP532B66UWC57EY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7FC4J5LR3F2VP532B66UWC57EY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7FC4J5LR3F2VP532B66UWC57EY/action/storage_attestation","attest_author":"https://pith.science/pith/7FC4J5LR3F2VP532B66UWC57EY/action/author_attestation","sign_citation":"https://pith.science/pith/7FC4J5LR3F2VP532B66UWC57EY/action/citation_signature","submit_replication":"https://pith.science/pith/7FC4J5LR3F2VP532B66UWC57EY/action/replication_record"}},"created_at":"2026-05-18T00:42:45.604601+00:00","updated_at":"2026-05-18T00:42:45.604601+00:00"}