{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EK65TIYKFQCTZK3XKVZ6UGXGCB","short_pith_number":"pith:EK65TIYK","schema_version":"1.0","canonical_sha256":"22bdd9a30a2c053cab775573ea1ae6107f763fa9b14b4f26aa70cc758a7a97b7","source":{"kind":"arxiv","id":"1903.09291","version":1},"attestation_state":"computed","paper":{"title":"Towards Optimal Structured CNN Pruning via Generative Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Chenqian Yan, David Doermann, Feiyue Huang, Liujuan Cao, Qixiang Ye, Rongrong Ji, Shaohui Lin","submitted_at":"2019-03-22T01:26:33Z","abstract_excerpt":"Structured pruning of filters or neurons has received increased focus for compressing convolutional neural networks. Most existing methods rely on multi-stage optimizations in a layer-wise manner for iteratively pruning and retraining which may not be optimal and may be computation intensive. Besides, these methods are designed for pruning a specific structure, such as filter or block structures without jointly pruning heterogeneous structures. In this paper, we propose an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner. To "},"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":"1903.09291","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-22T01:26:33Z","cross_cats_sorted":[],"title_canon_sha256":"0c6c9ca77c5eee568e2fc2e70d47dec4ad94105aecbb7ab6eee043928d6b759c","abstract_canon_sha256":"a1b60ccd586b7b241907682a4c3c997634ddceb11281ab3865c480fa591a4175"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:40.084872Z","signature_b64":"R1DKXxwIcJto0uoeyFJ+Od8rSS/Rxj6p4pG/AQ3vuAnVEQTmkZ2KnKXhi7Hql5DD7P1e59gyQR5bMYImKcbPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22bdd9a30a2c053cab775573ea1ae6107f763fa9b14b4f26aa70cc758a7a97b7","last_reissued_at":"2026-05-17T23:50:40.084433Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:40.084433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Optimal Structured CNN Pruning via Generative Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Chenqian Yan, David Doermann, Feiyue Huang, Liujuan Cao, Qixiang Ye, Rongrong Ji, Shaohui Lin","submitted_at":"2019-03-22T01:26:33Z","abstract_excerpt":"Structured pruning of filters or neurons has received increased focus for compressing convolutional neural networks. Most existing methods rely on multi-stage optimizations in a layer-wise manner for iteratively pruning and retraining which may not be optimal and may be computation intensive. Besides, these methods are designed for pruning a specific structure, such as filter or block structures without jointly pruning heterogeneous structures. In this paper, we propose an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner. To "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09291","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":"1903.09291","created_at":"2026-05-17T23:50:40.084501+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.09291v1","created_at":"2026-05-17T23:50:40.084501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09291","created_at":"2026-05-17T23:50:40.084501+00:00"},{"alias_kind":"pith_short_12","alias_value":"EK65TIYKFQCT","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"EK65TIYKFQCTZK3X","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"EK65TIYK","created_at":"2026-05-18T12:33:15.570797+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/EK65TIYKFQCTZK3XKVZ6UGXGCB","json":"https://pith.science/pith/EK65TIYKFQCTZK3XKVZ6UGXGCB.json","graph_json":"https://pith.science/api/pith-number/EK65TIYKFQCTZK3XKVZ6UGXGCB/graph.json","events_json":"https://pith.science/api/pith-number/EK65TIYKFQCTZK3XKVZ6UGXGCB/events.json","paper":"https://pith.science/paper/EK65TIYK"},"agent_actions":{"view_html":"https://pith.science/pith/EK65TIYKFQCTZK3XKVZ6UGXGCB","download_json":"https://pith.science/pith/EK65TIYKFQCTZK3XKVZ6UGXGCB.json","view_paper":"https://pith.science/paper/EK65TIYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.09291&json=true","fetch_graph":"https://pith.science/api/pith-number/EK65TIYKFQCTZK3XKVZ6UGXGCB/graph.json","fetch_events":"https://pith.science/api/pith-number/EK65TIYKFQCTZK3XKVZ6UGXGCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EK65TIYKFQCTZK3XKVZ6UGXGCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EK65TIYKFQCTZK3XKVZ6UGXGCB/action/storage_attestation","attest_author":"https://pith.science/pith/EK65TIYKFQCTZK3XKVZ6UGXGCB/action/author_attestation","sign_citation":"https://pith.science/pith/EK65TIYKFQCTZK3XKVZ6UGXGCB/action/citation_signature","submit_replication":"https://pith.science/pith/EK65TIYKFQCTZK3XKVZ6UGXGCB/action/replication_record"}},"created_at":"2026-05-17T23:50:40.084501+00:00","updated_at":"2026-05-17T23:50:40.084501+00:00"}