{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BEWLC6LOZTRZZ6G3E7M66F7DJH","short_pith_number":"pith:BEWLC6LO","schema_version":"1.0","canonical_sha256":"092cb1796ecce39cf8db27d9ef17e349f7e8e7c43bea39989d09471344980e96","source":{"kind":"arxiv","id":"1903.10258","version":3},"attestation_state":"computed","paper":{"title":"MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyuan Mu, Jian Sun, Tim Kwang-Ting Cheng, Xiangyu Zhang, Xin Yang, Zechun Liu, Zichao Guo","submitted_at":"2019-03-25T12:05:27Z","abstract_excerpt":"In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks. We first train a PruningNet, a kind of meta network, which is able to generate weight parameters for any pruned structure given the target network. We use a simple stochastic structure sampling method for training the PruningNet. Then, we apply an evolutionary procedure to search for good-performing pruned networks. The search is highly efficient because the weights are directly generated by the trained PruningNet and we do not need any finetuning at search time. With a single P"},"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":"1903.10258","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-25T12:05:27Z","cross_cats_sorted":[],"title_canon_sha256":"81911356f7b13d11b548ed213e4a2bff8e0c943f57919af2279579ff394e58c2","abstract_canon_sha256":"e4f5e722b9d352debf44d5200ff4c509c4eb05d2530b5e2a8f676f6426da3d6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:55:55.363174Z","signature_b64":"9fWiBxEUEZpKDaGPF/TOnOKWMdxOfyoalPgMOhlsIVTQU6Z8jTpshvza6W7dFfw08dLd0s1PiW1pSHCyZ07cBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"092cb1796ecce39cf8db27d9ef17e349f7e8e7c43bea39989d09471344980e96","last_reissued_at":"2026-07-04T23:55:55.362632Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:55:55.362632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyuan Mu, Jian Sun, Tim Kwang-Ting Cheng, Xiangyu Zhang, Xin Yang, Zechun Liu, Zichao Guo","submitted_at":"2019-03-25T12:05:27Z","abstract_excerpt":"In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks. We first train a PruningNet, a kind of meta network, which is able to generate weight parameters for any pruned structure given the target network. We use a simple stochastic structure sampling method for training the PruningNet. Then, we apply an evolutionary procedure to search for good-performing pruned networks. The search is highly efficient because the weights are directly generated by the trained PruningNet and we do not need any finetuning at search time. With a single P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10258","kind":"arxiv","version":3},"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/1903.10258/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":"1903.10258","created_at":"2026-07-04T23:55:55.362689+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.10258v3","created_at":"2026-07-04T23:55:55.362689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10258","created_at":"2026-07-04T23:55:55.362689+00:00"},{"alias_kind":"pith_short_12","alias_value":"BEWLC6LOZTRZ","created_at":"2026-07-04T23:55:55.362689+00:00"},{"alias_kind":"pith_short_16","alias_value":"BEWLC6LOZTRZZ6G3","created_at":"2026-07-04T23:55:55.362689+00:00"},{"alias_kind":"pith_short_8","alias_value":"BEWLC6LO","created_at":"2026-07-04T23:55:55.362689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.10526","citing_title":"Resource-Aware Neural Network Pruning Using Graph-based Reinforcement Learning","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BEWLC6LOZTRZZ6G3E7M66F7DJH","json":"https://pith.science/pith/BEWLC6LOZTRZZ6G3E7M66F7DJH.json","graph_json":"https://pith.science/api/pith-number/BEWLC6LOZTRZZ6G3E7M66F7DJH/graph.json","events_json":"https://pith.science/api/pith-number/BEWLC6LOZTRZZ6G3E7M66F7DJH/events.json","paper":"https://pith.science/paper/BEWLC6LO"},"agent_actions":{"view_html":"https://pith.science/pith/BEWLC6LOZTRZZ6G3E7M66F7DJH","download_json":"https://pith.science/pith/BEWLC6LOZTRZZ6G3E7M66F7DJH.json","view_paper":"https://pith.science/paper/BEWLC6LO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.10258&json=true","fetch_graph":"https://pith.science/api/pith-number/BEWLC6LOZTRZZ6G3E7M66F7DJH/graph.json","fetch_events":"https://pith.science/api/pith-number/BEWLC6LOZTRZZ6G3E7M66F7DJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BEWLC6LOZTRZZ6G3E7M66F7DJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BEWLC6LOZTRZZ6G3E7M66F7DJH/action/storage_attestation","attest_author":"https://pith.science/pith/BEWLC6LOZTRZZ6G3E7M66F7DJH/action/author_attestation","sign_citation":"https://pith.science/pith/BEWLC6LOZTRZZ6G3E7M66F7DJH/action/citation_signature","submit_replication":"https://pith.science/pith/BEWLC6LOZTRZZ6G3E7M66F7DJH/action/replication_record"}},"created_at":"2026-07-04T23:55:55.362689+00:00","updated_at":"2026-07-04T23:55:55.362689+00:00"}