{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KSJZKHC53JPUWFN45GMAOPXWFX","short_pith_number":"pith:KSJZKHC5","schema_version":"1.0","canonical_sha256":"5493951c5dda5f4b15bce998073ef62dff553e8c722642dd84c88f723b8dbaf2","source":{"kind":"arxiv","id":"1804.09461","version":2},"attestation_state":"computed","paper":{"title":"Structured Pruning for Efficient ConvNets via Incremental Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haoji Hu, Huan Wang, Qiming Zhang, Yuehai Wang, Yu Lu","submitted_at":"2018-04-25T09:59:45Z","abstract_excerpt":"Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance degrade. Despite its effectiveness, existing regularization-based parameter pruning methods usually drive weights towards zero with large and constant regularization factors, which neglects the fragility of the expressiveness of CNNs, and thus calls for a more gentle regularization scheme so that the networks can adapt during pruning. To achieve this, we propose a new and novel regularization-based pruning method, named IncReg, to incrementally ass"},"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":"1804.09461","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-25T09:59:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9a4d60059cf727d3136b688c3bde12fbe67730636b5ac326c9663d8899d24871","abstract_canon_sha256":"0567c30d92008e773015dc3f471364f0d5a422d1e86e5455c8f8ec5e16c4aeb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:34.211701Z","signature_b64":"10Ag3Mzd1h/7Z+QS0+Ehnm+5ZyMqNVakhqW+SL+BUcn6brwuDhG1xIBHUGy43kn1bEIR1pHkz7hyRkzknBKoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5493951c5dda5f4b15bce998073ef62dff553e8c722642dd84c88f723b8dbaf2","last_reissued_at":"2026-05-17T23:48:34.211210Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:34.211210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Pruning for Efficient ConvNets via Incremental Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haoji Hu, Huan Wang, Qiming Zhang, Yuehai Wang, Yu Lu","submitted_at":"2018-04-25T09:59:45Z","abstract_excerpt":"Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance degrade. Despite its effectiveness, existing regularization-based parameter pruning methods usually drive weights towards zero with large and constant regularization factors, which neglects the fragility of the expressiveness of CNNs, and thus calls for a more gentle regularization scheme so that the networks can adapt during pruning. To achieve this, we propose a new and novel regularization-based pruning method, named IncReg, to incrementally ass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09461","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":""},"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":"1804.09461","created_at":"2026-05-17T23:48:34.211289+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.09461v2","created_at":"2026-05-17T23:48:34.211289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09461","created_at":"2026-05-17T23:48:34.211289+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSJZKHC53JPU","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSJZKHC53JPUWFN4","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSJZKHC5","created_at":"2026-05-18T12:32:33.847187+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/KSJZKHC53JPUWFN45GMAOPXWFX","json":"https://pith.science/pith/KSJZKHC53JPUWFN45GMAOPXWFX.json","graph_json":"https://pith.science/api/pith-number/KSJZKHC53JPUWFN45GMAOPXWFX/graph.json","events_json":"https://pith.science/api/pith-number/KSJZKHC53JPUWFN45GMAOPXWFX/events.json","paper":"https://pith.science/paper/KSJZKHC5"},"agent_actions":{"view_html":"https://pith.science/pith/KSJZKHC53JPUWFN45GMAOPXWFX","download_json":"https://pith.science/pith/KSJZKHC53JPUWFN45GMAOPXWFX.json","view_paper":"https://pith.science/paper/KSJZKHC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.09461&json=true","fetch_graph":"https://pith.science/api/pith-number/KSJZKHC53JPUWFN45GMAOPXWFX/graph.json","fetch_events":"https://pith.science/api/pith-number/KSJZKHC53JPUWFN45GMAOPXWFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSJZKHC53JPUWFN45GMAOPXWFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSJZKHC53JPUWFN45GMAOPXWFX/action/storage_attestation","attest_author":"https://pith.science/pith/KSJZKHC53JPUWFN45GMAOPXWFX/action/author_attestation","sign_citation":"https://pith.science/pith/KSJZKHC53JPUWFN45GMAOPXWFX/action/citation_signature","submit_replication":"https://pith.science/pith/KSJZKHC53JPUWFN45GMAOPXWFX/action/replication_record"}},"created_at":"2026-05-17T23:48:34.211289+00:00","updated_at":"2026-05-17T23:48:34.211289+00:00"}