{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GMI4OHIU6YVDF4Q3PAYQGPS7UO","short_pith_number":"pith:GMI4OHIU","schema_version":"1.0","canonical_sha256":"3311c71d14f62a32f21b7831033e5fa3904c900f3051b36e0049c656a262280d","source":{"kind":"arxiv","id":"1708.08917","version":1},"attestation_state":"computed","paper":{"title":"CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Bo Yuan, Caiwen Ding, Chao Wang, Geng Yuan, Jian Tang, Ning Liu, Qinru Qiu, Siyu Liao, Xiaolong Ma, Xuehai Qian, Xue Lin, Yanzhi Wang, Yipeng Zhang, Youwei Zhuo, Yu Bai, Zhe Li","submitted_at":"2017-08-29T04:18:57Z","abstract_excerpt":"Large-scale deep neural networks (DNNs) are both compute and memory intensive. As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy. For DNNs, the model size is an important factor affecting performance, scalability and energy efficiency. Weight pruning achieves good compression ratios but suffers from three drawbacks: 1) the irregular network structure after pruning; 2) the increased training complexity; and 3) the lack of rigorous guarantee of compression ratio and inference accuracy. To overcome these limitations, "},"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":"1708.08917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-29T04:18:57Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"64efadd3d223ce41c8c1bd37f26d69211d548bff06a62736d998637585a27af7","abstract_canon_sha256":"547935382fac89c331cd779e1bb0d019d08917cfb607826ca9b2239bdc0c1c35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:46.081928Z","signature_b64":"2fjyCfhWG2I3imJR85oM1I3BBlnMhCdKv7ykDMh0W18n+d2Y+Ur4rYi8jvRGYro3MYR2scU8+YOe/ke2+SBxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3311c71d14f62a32f21b7831033e5fa3904c900f3051b36e0049c656a262280d","last_reissued_at":"2026-05-18T00:35:46.081262Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:46.081262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Bo Yuan, Caiwen Ding, Chao Wang, Geng Yuan, Jian Tang, Ning Liu, Qinru Qiu, Siyu Liao, Xiaolong Ma, Xuehai Qian, Xue Lin, Yanzhi Wang, Yipeng Zhang, Youwei Zhuo, Yu Bai, Zhe Li","submitted_at":"2017-08-29T04:18:57Z","abstract_excerpt":"Large-scale deep neural networks (DNNs) are both compute and memory intensive. As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy. For DNNs, the model size is an important factor affecting performance, scalability and energy efficiency. Weight pruning achieves good compression ratios but suffers from three drawbacks: 1) the irregular network structure after pruning; 2) the increased training complexity; and 3) the lack of rigorous guarantee of compression ratio and inference accuracy. To overcome these limitations, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.08917","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":"1708.08917","created_at":"2026-05-18T00:35:46.081368+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.08917v1","created_at":"2026-05-18T00:35:46.081368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.08917","created_at":"2026-05-18T00:35:46.081368+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMI4OHIU6YVD","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMI4OHIU6YVDF4Q3","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMI4OHIU","created_at":"2026-05-18T12:31:18.294218+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/GMI4OHIU6YVDF4Q3PAYQGPS7UO","json":"https://pith.science/pith/GMI4OHIU6YVDF4Q3PAYQGPS7UO.json","graph_json":"https://pith.science/api/pith-number/GMI4OHIU6YVDF4Q3PAYQGPS7UO/graph.json","events_json":"https://pith.science/api/pith-number/GMI4OHIU6YVDF4Q3PAYQGPS7UO/events.json","paper":"https://pith.science/paper/GMI4OHIU"},"agent_actions":{"view_html":"https://pith.science/pith/GMI4OHIU6YVDF4Q3PAYQGPS7UO","download_json":"https://pith.science/pith/GMI4OHIU6YVDF4Q3PAYQGPS7UO.json","view_paper":"https://pith.science/paper/GMI4OHIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.08917&json=true","fetch_graph":"https://pith.science/api/pith-number/GMI4OHIU6YVDF4Q3PAYQGPS7UO/graph.json","fetch_events":"https://pith.science/api/pith-number/GMI4OHIU6YVDF4Q3PAYQGPS7UO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMI4OHIU6YVDF4Q3PAYQGPS7UO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMI4OHIU6YVDF4Q3PAYQGPS7UO/action/storage_attestation","attest_author":"https://pith.science/pith/GMI4OHIU6YVDF4Q3PAYQGPS7UO/action/author_attestation","sign_citation":"https://pith.science/pith/GMI4OHIU6YVDF4Q3PAYQGPS7UO/action/citation_signature","submit_replication":"https://pith.science/pith/GMI4OHIU6YVDF4Q3PAYQGPS7UO/action/replication_record"}},"created_at":"2026-05-18T00:35:46.081368+00:00","updated_at":"2026-05-18T00:35:46.081368+00:00"}