{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BAFQ7LL7RVEU54BKWA3JTPCU76","short_pith_number":"pith:BAFQ7LL7","schema_version":"1.0","canonical_sha256":"080b0fad7f8d494ef02ab03699bc54ffa554141006597e186b805dea9796f81a","source":{"kind":"arxiv","id":"1812.03608","version":1},"attestation_state":"computed","paper":{"title":"Reliable Identification of Redundant Kernels for Convolutional Neural Network Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Liqiang Zhu, Wei Wang","submitted_at":"2018-12-10T03:28:15Z","abstract_excerpt":"To compress deep convolutional neural networks (CNNs) with large memory footprint and long inference time, this paper proposes a novel pruning criterion using layer-wised Ln-norm of feature maps. Different from existing pruning criteria, which are mainly based on L1-norm of convolution kernels, the proposed method utilizes Ln-norm of output feature maps after non-linear activations, where n is a variable, increasing from 1 at the first convolution layer to inf at the last convolution layer. With the ability of accurately identifying unimportant convolution kernels, the proposed method achieves"},"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":"1812.03608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-12-10T03:28:15Z","cross_cats_sorted":[],"title_canon_sha256":"9f54aac5d12d73729fa25eb4c32dc3be5b5ee18aab6795f47281ed41b5e91127","abstract_canon_sha256":"ccb3fd7bb7562985711f2e809da8aebcace144be8c4161edb6a2fd31ce401a11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:44.333133Z","signature_b64":"zRoZUpfXwW+WvtGAb4SpHQna46NzrBUK5sB2LbtwKoiG63xgBF5noVrrAXOjzhT5yZgjSMzkAPp52arnWRLLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"080b0fad7f8d494ef02ab03699bc54ffa554141006597e186b805dea9796f81a","last_reissued_at":"2026-05-17T23:58:44.332521Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:44.332521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliable Identification of Redundant Kernels for Convolutional Neural Network Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Liqiang Zhu, Wei Wang","submitted_at":"2018-12-10T03:28:15Z","abstract_excerpt":"To compress deep convolutional neural networks (CNNs) with large memory footprint and long inference time, this paper proposes a novel pruning criterion using layer-wised Ln-norm of feature maps. Different from existing pruning criteria, which are mainly based on L1-norm of convolution kernels, the proposed method utilizes Ln-norm of output feature maps after non-linear activations, where n is a variable, increasing from 1 at the first convolution layer to inf at the last convolution layer. With the ability of accurately identifying unimportant convolution kernels, the proposed method achieves"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03608","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":"1812.03608","created_at":"2026-05-17T23:58:44.332603+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.03608v1","created_at":"2026-05-17T23:58:44.332603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03608","created_at":"2026-05-17T23:58:44.332603+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAFQ7LL7RVEU","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAFQ7LL7RVEU54BK","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAFQ7LL7","created_at":"2026-05-18T12:32:13.499390+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/BAFQ7LL7RVEU54BKWA3JTPCU76","json":"https://pith.science/pith/BAFQ7LL7RVEU54BKWA3JTPCU76.json","graph_json":"https://pith.science/api/pith-number/BAFQ7LL7RVEU54BKWA3JTPCU76/graph.json","events_json":"https://pith.science/api/pith-number/BAFQ7LL7RVEU54BKWA3JTPCU76/events.json","paper":"https://pith.science/paper/BAFQ7LL7"},"agent_actions":{"view_html":"https://pith.science/pith/BAFQ7LL7RVEU54BKWA3JTPCU76","download_json":"https://pith.science/pith/BAFQ7LL7RVEU54BKWA3JTPCU76.json","view_paper":"https://pith.science/paper/BAFQ7LL7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.03608&json=true","fetch_graph":"https://pith.science/api/pith-number/BAFQ7LL7RVEU54BKWA3JTPCU76/graph.json","fetch_events":"https://pith.science/api/pith-number/BAFQ7LL7RVEU54BKWA3JTPCU76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAFQ7LL7RVEU54BKWA3JTPCU76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAFQ7LL7RVEU54BKWA3JTPCU76/action/storage_attestation","attest_author":"https://pith.science/pith/BAFQ7LL7RVEU54BKWA3JTPCU76/action/author_attestation","sign_citation":"https://pith.science/pith/BAFQ7LL7RVEU54BKWA3JTPCU76/action/citation_signature","submit_replication":"https://pith.science/pith/BAFQ7LL7RVEU54BKWA3JTPCU76/action/replication_record"}},"created_at":"2026-05-17T23:58:44.332603+00:00","updated_at":"2026-05-17T23:58:44.332603+00:00"}