{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UKXSQACJXE3KGTMJBINRWZHMDL","short_pith_number":"pith:UKXSQACJ","schema_version":"1.0","canonical_sha256":"a2af280049b936a34d890a1b1b64ec1adc1d78ad280255db997260ef3743f519","source":{"kind":"arxiv","id":"2002.04809","version":1},"attestation_state":"computed","paper":{"title":"Lookahead: A Far-Sighted Alternative of Magnitude-based Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jaeho Lee, Jinwoo Shin, Sangwoo Mo, Sejun Park","submitted_at":"2020-02-12T05:38:42Z","abstract_excerpt":"Magnitude-based pruning is one of the simplest methods for pruning neural networks. Despite its simplicity, magnitude-based pruning and its variants demonstrated remarkable performances for pruning modern architectures. Based on the observation that magnitude-based pruning indeed minimizes the Frobenius distortion of a linear operator corresponding to a single layer, we develop a simple pruning method, coined lookahead pruning, by extending the single layer optimization to a multi-layer optimization. Our experimental results demonstrate that the proposed method consistently outperforms magnitu"},"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":"2002.04809","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T05:38:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5b82f3376989ef239fdaa4524a14e932b6bec95676c4a15d9f30d5c285ab8dcf","abstract_canon_sha256":"a97b31c6e4c35b38aca604f2a46e772f00d2d6ddecef7988e7811c771f9c0263"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:46.814134Z","signature_b64":"6DTUGfIZ/ZWLgyGJboF6TnEtrwM94595zSH3g4QYTa2iRaerQ20Jf9Hdssh2PIok5/G0goV6Y3wtOwFojPf8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2af280049b936a34d890a1b1b64ec1adc1d78ad280255db997260ef3743f519","last_reissued_at":"2026-07-05T00:40:46.813648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:46.813648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lookahead: A Far-Sighted Alternative of Magnitude-based Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jaeho Lee, Jinwoo Shin, Sangwoo Mo, Sejun Park","submitted_at":"2020-02-12T05:38:42Z","abstract_excerpt":"Magnitude-based pruning is one of the simplest methods for pruning neural networks. Despite its simplicity, magnitude-based pruning and its variants demonstrated remarkable performances for pruning modern architectures. Based on the observation that magnitude-based pruning indeed minimizes the Frobenius distortion of a linear operator corresponding to a single layer, we develop a simple pruning method, coined lookahead pruning, by extending the single layer optimization to a multi-layer optimization. Our experimental results demonstrate that the proposed method consistently outperforms magnitu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.04809","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.04809/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":"2002.04809","created_at":"2026-07-05T00:40:46.813711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.04809v1","created_at":"2026-07-05T00:40:46.813711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.04809","created_at":"2026-07-05T00:40:46.813711+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKXSQACJXE3K","created_at":"2026-07-05T00:40:46.813711+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKXSQACJXE3KGTMJ","created_at":"2026-07-05T00:40:46.813711+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKXSQACJ","created_at":"2026-07-05T00:40:46.813711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":291,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00927","citing_title":"Post-Training Pruning for Diffusion Transformers","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24380","citing_title":"Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":291,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UKXSQACJXE3KGTMJBINRWZHMDL","json":"https://pith.science/pith/UKXSQACJXE3KGTMJBINRWZHMDL.json","graph_json":"https://pith.science/api/pith-number/UKXSQACJXE3KGTMJBINRWZHMDL/graph.json","events_json":"https://pith.science/api/pith-number/UKXSQACJXE3KGTMJBINRWZHMDL/events.json","paper":"https://pith.science/paper/UKXSQACJ"},"agent_actions":{"view_html":"https://pith.science/pith/UKXSQACJXE3KGTMJBINRWZHMDL","download_json":"https://pith.science/pith/UKXSQACJXE3KGTMJBINRWZHMDL.json","view_paper":"https://pith.science/paper/UKXSQACJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.04809&json=true","fetch_graph":"https://pith.science/api/pith-number/UKXSQACJXE3KGTMJBINRWZHMDL/graph.json","fetch_events":"https://pith.science/api/pith-number/UKXSQACJXE3KGTMJBINRWZHMDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKXSQACJXE3KGTMJBINRWZHMDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKXSQACJXE3KGTMJBINRWZHMDL/action/storage_attestation","attest_author":"https://pith.science/pith/UKXSQACJXE3KGTMJBINRWZHMDL/action/author_attestation","sign_citation":"https://pith.science/pith/UKXSQACJXE3KGTMJBINRWZHMDL/action/citation_signature","submit_replication":"https://pith.science/pith/UKXSQACJXE3KGTMJBINRWZHMDL/action/replication_record"}},"created_at":"2026-07-05T00:40:46.813711+00:00","updated_at":"2026-07-05T00:40:46.813711+00:00"}