{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IMHNTJ4O2T745CRJ5TPTBTITZ5","short_pith_number":"pith:IMHNTJ4O","schema_version":"1.0","canonical_sha256":"430ed9a78ed4ffce8a29ecdf30cd13cf41d4d12957e46f115a6570a01402f1e8","source":{"kind":"arxiv","id":"2108.13728","version":1},"attestation_state":"computed","paper":{"title":"Pruning with Compensation: Efficient Channel Pruning for Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duanbing Chen, Junlin Zhou, Shengzhao Tian, Yan Fu, Zhouyang Xie","submitted_at":"2021-08-31T10:17:36Z","abstract_excerpt":"Channel pruning is a promising technique to compress the parameters of deep convolutional neural networks(DCNN) and to speed up the inference. This paper aims to address the long-standing inefficiency of channel pruning. Most channel pruning methods recover the prediction accuracy by re-training the pruned model from the remaining parameters or random initialization. This re-training process is heavily dependent on the sufficiency of computational resources, training data, and human interference(tuning the training strategy). In this paper, a highly efficient pruning method is proposed to sign"},"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":"2108.13728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-31T10:17:36Z","cross_cats_sorted":[],"title_canon_sha256":"f2166e81614987bb250fd3608504e28268d8fd9f17f6139bc54e85da28a3de69","abstract_canon_sha256":"ecb1b0f0c2675df027d643c85bcc613f02f1ce3f5efc4fba48a1a2e7c497d57b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:10:17.220023Z","signature_b64":"nrXO2pEJDT7lDrwhi+j98OSbFOlFa9CFMNj7x90brLqwoObYxy8qOKBLZ2g/4BZkLMyAZno18VelKMO3swCjCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"430ed9a78ed4ffce8a29ecdf30cd13cf41d4d12957e46f115a6570a01402f1e8","last_reissued_at":"2026-07-05T03:10:17.219555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:10:17.219555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pruning with Compensation: Efficient Channel Pruning for Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duanbing Chen, Junlin Zhou, Shengzhao Tian, Yan Fu, Zhouyang Xie","submitted_at":"2021-08-31T10:17:36Z","abstract_excerpt":"Channel pruning is a promising technique to compress the parameters of deep convolutional neural networks(DCNN) and to speed up the inference. This paper aims to address the long-standing inefficiency of channel pruning. Most channel pruning methods recover the prediction accuracy by re-training the pruned model from the remaining parameters or random initialization. This re-training process is heavily dependent on the sufficiency of computational resources, training data, and human interference(tuning the training strategy). In this paper, a highly efficient pruning method is proposed to sign"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.13728","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/2108.13728/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":"2108.13728","created_at":"2026-07-05T03:10:17.219611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.13728v1","created_at":"2026-07-05T03:10:17.219611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.13728","created_at":"2026-07-05T03:10:17.219611+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMHNTJ4O2T74","created_at":"2026-07-05T03:10:17.219611+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMHNTJ4O2T745CRJ","created_at":"2026-07-05T03:10:17.219611+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMHNTJ4O","created_at":"2026-07-05T03:10:17.219611+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/IMHNTJ4O2T745CRJ5TPTBTITZ5","json":"https://pith.science/pith/IMHNTJ4O2T745CRJ5TPTBTITZ5.json","graph_json":"https://pith.science/api/pith-number/IMHNTJ4O2T745CRJ5TPTBTITZ5/graph.json","events_json":"https://pith.science/api/pith-number/IMHNTJ4O2T745CRJ5TPTBTITZ5/events.json","paper":"https://pith.science/paper/IMHNTJ4O"},"agent_actions":{"view_html":"https://pith.science/pith/IMHNTJ4O2T745CRJ5TPTBTITZ5","download_json":"https://pith.science/pith/IMHNTJ4O2T745CRJ5TPTBTITZ5.json","view_paper":"https://pith.science/paper/IMHNTJ4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.13728&json=true","fetch_graph":"https://pith.science/api/pith-number/IMHNTJ4O2T745CRJ5TPTBTITZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/IMHNTJ4O2T745CRJ5TPTBTITZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMHNTJ4O2T745CRJ5TPTBTITZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMHNTJ4O2T745CRJ5TPTBTITZ5/action/storage_attestation","attest_author":"https://pith.science/pith/IMHNTJ4O2T745CRJ5TPTBTITZ5/action/author_attestation","sign_citation":"https://pith.science/pith/IMHNTJ4O2T745CRJ5TPTBTITZ5/action/citation_signature","submit_replication":"https://pith.science/pith/IMHNTJ4O2T745CRJ5TPTBTITZ5/action/replication_record"}},"created_at":"2026-07-05T03:10:17.219611+00:00","updated_at":"2026-07-05T03:10:17.219611+00:00"}