{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TNOOF7K3D26NTULXYFHPFI6T7Y","short_pith_number":"pith:TNOOF7K3","schema_version":"1.0","canonical_sha256":"9b5ce2fd5b1ebcd9d177c14ef2a3d3fe1a288bc7766621a762b9772d54f3fbe5","source":{"kind":"arxiv","id":"1906.02535","version":1},"attestation_state":"computed","paper":{"title":"(Pen-) Ultimate DNN Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonio Gonzalez, Jose-Maria Arnau, Marc Riera","submitted_at":"2019-06-06T11:51:48Z","abstract_excerpt":"DNN pruning reduces memory footprint and computational work of DNN-based solutions to improve performance and energy-efficiency. An effective pruning scheme should be able to systematically remove connections and/or neurons that are unnecessary or redundant, reducing the DNN size without any loss in accuracy. In this paper we show that prior pruning schemes require an extremely time-consuming iterative process that requires retraining the DNN many times to tune the pruning hyperparameters. We propose a DNN pruning scheme based on Principal Component Analysis and relative importance of each neu"},"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":"1906.02535","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T11:51:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2dc8e845bc406e0349c4569d6c4cf815d00479b9083bac4c1e5bcb67eddba298","abstract_canon_sha256":"eaa5cff173b92fbeda1537726ea0f02521c162357b37d1a281cc26d8b35fa6b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:00.857198Z","signature_b64":"HcCUl3KXpu3K+UJSOCi/2OYl+1zMp7U79RxvV/KPKCrZpjOxS9RPSqlaNOq1q/JGxerVLwIB9LGo/PLv/MF3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b5ce2fd5b1ebcd9d177c14ef2a3d3fe1a288bc7766621a762b9772d54f3fbe5","last_reissued_at":"2026-05-17T23:44:00.856554Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:00.856554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"(Pen-) Ultimate DNN Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonio Gonzalez, Jose-Maria Arnau, Marc Riera","submitted_at":"2019-06-06T11:51:48Z","abstract_excerpt":"DNN pruning reduces memory footprint and computational work of DNN-based solutions to improve performance and energy-efficiency. An effective pruning scheme should be able to systematically remove connections and/or neurons that are unnecessary or redundant, reducing the DNN size without any loss in accuracy. In this paper we show that prior pruning schemes require an extremely time-consuming iterative process that requires retraining the DNN many times to tune the pruning hyperparameters. We propose a DNN pruning scheme based on Principal Component Analysis and relative importance of each neu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02535","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":"1906.02535","created_at":"2026-05-17T23:44:00.856685+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02535v1","created_at":"2026-05-17T23:44:00.856685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02535","created_at":"2026-05-17T23:44:00.856685+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNOOF7K3D26N","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNOOF7K3D26NTULX","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNOOF7K3","created_at":"2026-05-18T12:33:30.264802+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/TNOOF7K3D26NTULXYFHPFI6T7Y","json":"https://pith.science/pith/TNOOF7K3D26NTULXYFHPFI6T7Y.json","graph_json":"https://pith.science/api/pith-number/TNOOF7K3D26NTULXYFHPFI6T7Y/graph.json","events_json":"https://pith.science/api/pith-number/TNOOF7K3D26NTULXYFHPFI6T7Y/events.json","paper":"https://pith.science/paper/TNOOF7K3"},"agent_actions":{"view_html":"https://pith.science/pith/TNOOF7K3D26NTULXYFHPFI6T7Y","download_json":"https://pith.science/pith/TNOOF7K3D26NTULXYFHPFI6T7Y.json","view_paper":"https://pith.science/paper/TNOOF7K3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02535&json=true","fetch_graph":"https://pith.science/api/pith-number/TNOOF7K3D26NTULXYFHPFI6T7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/TNOOF7K3D26NTULXYFHPFI6T7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNOOF7K3D26NTULXYFHPFI6T7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNOOF7K3D26NTULXYFHPFI6T7Y/action/storage_attestation","attest_author":"https://pith.science/pith/TNOOF7K3D26NTULXYFHPFI6T7Y/action/author_attestation","sign_citation":"https://pith.science/pith/TNOOF7K3D26NTULXYFHPFI6T7Y/action/citation_signature","submit_replication":"https://pith.science/pith/TNOOF7K3D26NTULXYFHPFI6T7Y/action/replication_record"}},"created_at":"2026-05-17T23:44:00.856685+00:00","updated_at":"2026-05-17T23:44:00.856685+00:00"}