{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Y4VTROTSP6KHT22U5J5NS233PH","short_pith_number":"pith:Y4VTROTS","schema_version":"1.0","canonical_sha256":"c72b38ba727f9479eb54ea7ad96b7b79c8960c35ed0c09d0c95ca269fbefcc61","source":{"kind":"arxiv","id":"2001.08565","version":3},"attestation_state":"computed","paper":{"title":"Channel Pruning via Automatic Structure Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Mingbao Lin, Rongrong Ji, Yonghong Tian, Yongjian Wu, Yuxin Zhang","submitted_at":"2020-01-23T14:51:19Z","abstract_excerpt":"Channel pruning is among the predominant approaches to compress deep neural networks. To this end, most existing pruning methods focus on selecting channels (filters) by importance/optimization or regularization based on rule-of-thumb designs, which defects in sub-optimal pruning. In this paper, we propose a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner, which aims to efficiently find optimal pruned structure, i.e., channel number in each layer, rather than selecting \"important\" channels as previous works did. To solve the intractably huge combi"},"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":"2001.08565","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-23T14:51:19Z","cross_cats_sorted":[],"title_canon_sha256":"9ce51d925156d1d1cc9124906f4b7f78989c2e008d5e1aee03b590a6ec6bd9aa","abstract_canon_sha256":"b548bb3f099bf516bf03ffc3abb6012e8b8f0ca1b9d53cf2dc9a0341129d0e3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:57.586714Z","signature_b64":"e3PYUL19uBAuhk2YGHf58zKI9H/YDia6QV2oEBGRWKmm9xSzLh7aq7Z7LPSt34GNwuibWJIKyojIRIV5CNFACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c72b38ba727f9479eb54ea7ad96b7b79c8960c35ed0c09d0c95ca269fbefcc61","last_reissued_at":"2026-07-05T01:13:57.586198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:57.586198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Channel Pruning via Automatic Structure Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Mingbao Lin, Rongrong Ji, Yonghong Tian, Yongjian Wu, Yuxin Zhang","submitted_at":"2020-01-23T14:51:19Z","abstract_excerpt":"Channel pruning is among the predominant approaches to compress deep neural networks. To this end, most existing pruning methods focus on selecting channels (filters) by importance/optimization or regularization based on rule-of-thumb designs, which defects in sub-optimal pruning. In this paper, we propose a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner, which aims to efficiently find optimal pruned structure, i.e., channel number in each layer, rather than selecting \"important\" channels as previous works did. To solve the intractably huge combi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.08565","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/2001.08565/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":"2001.08565","created_at":"2026-07-05T01:13:57.586261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.08565v3","created_at":"2026-07-05T01:13:57.586261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.08565","created_at":"2026-07-05T01:13:57.586261+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y4VTROTSP6KH","created_at":"2026-07-05T01:13:57.586261+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y4VTROTSP6KHT22U","created_at":"2026-07-05T01:13:57.586261+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y4VTROTS","created_at":"2026-07-05T01:13:57.586261+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20669","citing_title":"GSA-YOLO: A High-Efficiency Framework via Structured Sparsity and Adaptive Knowledge Distillation for Real-Time X-ray Security Inspection","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y4VTROTSP6KHT22U5J5NS233PH","json":"https://pith.science/pith/Y4VTROTSP6KHT22U5J5NS233PH.json","graph_json":"https://pith.science/api/pith-number/Y4VTROTSP6KHT22U5J5NS233PH/graph.json","events_json":"https://pith.science/api/pith-number/Y4VTROTSP6KHT22U5J5NS233PH/events.json","paper":"https://pith.science/paper/Y4VTROTS"},"agent_actions":{"view_html":"https://pith.science/pith/Y4VTROTSP6KHT22U5J5NS233PH","download_json":"https://pith.science/pith/Y4VTROTSP6KHT22U5J5NS233PH.json","view_paper":"https://pith.science/paper/Y4VTROTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.08565&json=true","fetch_graph":"https://pith.science/api/pith-number/Y4VTROTSP6KHT22U5J5NS233PH/graph.json","fetch_events":"https://pith.science/api/pith-number/Y4VTROTSP6KHT22U5J5NS233PH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y4VTROTSP6KHT22U5J5NS233PH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y4VTROTSP6KHT22U5J5NS233PH/action/storage_attestation","attest_author":"https://pith.science/pith/Y4VTROTSP6KHT22U5J5NS233PH/action/author_attestation","sign_citation":"https://pith.science/pith/Y4VTROTSP6KHT22U5J5NS233PH/action/citation_signature","submit_replication":"https://pith.science/pith/Y4VTROTSP6KHT22U5J5NS233PH/action/replication_record"}},"created_at":"2026-07-05T01:13:57.586261+00:00","updated_at":"2026-07-05T01:13:57.586261+00:00"}