{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SZHGHSK3SKCA7WW4UX77RJNWN4","short_pith_number":"pith:SZHGHSK3","schema_version":"1.0","canonical_sha256":"964e63c95b92840fdadca5fff8a5b66f0984d4e64f5a7f1289391795dce5f149","source":{"kind":"arxiv","id":"1707.06168","version":2},"attestation_state":"computed","paper":{"title":"Channel Pruning for Accelerating Very Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Sun, Xiangyu Zhang, Yihui He","submitted_at":"2017-07-19T15:52:14Z","abstract_excerpt":"In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks.Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression based channel selection and least square reconstruction. We further generalize this algorithm to multi-layer and multi-branch cases. Our method reduces the accumulated error and enhance the compatibility with various architectures. Our pruned VGG-16 achieves the state-of-the-art results by 5x speed-up along with only 0.3% increase of error. More importantly, our"},"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":"1707.06168","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-19T15:52:14Z","cross_cats_sorted":[],"title_canon_sha256":"4d7e1ccf3a900ccf552cd3cfe72aa4a8564dc908b54af841753de156000c0ada","abstract_canon_sha256":"e976041bd7d707525bee0a4ad1a37ea3e45bcc2ed80c829d5ecbd32257c527a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:44.756406Z","signature_b64":"qw00UIjdFfwIBRPdUR8hYt4B90ug7+zkiAXLcEmVo1yO4xTG+14iMR6dWeTZPhFiWrwiFmvsuOBzvTQYoSVOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"964e63c95b92840fdadca5fff8a5b66f0984d4e64f5a7f1289391795dce5f149","last_reissued_at":"2026-05-18T00:37:44.755684Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:44.755684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Channel Pruning for Accelerating Very Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Sun, Xiangyu Zhang, Yihui He","submitted_at":"2017-07-19T15:52:14Z","abstract_excerpt":"In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks.Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression based channel selection and least square reconstruction. We further generalize this algorithm to multi-layer and multi-branch cases. Our method reduces the accumulated error and enhance the compatibility with various architectures. Our pruned VGG-16 achieves the state-of-the-art results by 5x speed-up along with only 0.3% increase of error. More importantly, our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06168","kind":"arxiv","version":2},"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":"1707.06168","created_at":"2026-05-18T00:37:44.755791+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.06168v2","created_at":"2026-05-18T00:37:44.755791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06168","created_at":"2026-05-18T00:37:44.755791+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZHGHSK3SKCA","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZHGHSK3SKCA7WW4","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZHGHSK3","created_at":"2026-05-18T12:31:43.269735+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/SZHGHSK3SKCA7WW4UX77RJNWN4","json":"https://pith.science/pith/SZHGHSK3SKCA7WW4UX77RJNWN4.json","graph_json":"https://pith.science/api/pith-number/SZHGHSK3SKCA7WW4UX77RJNWN4/graph.json","events_json":"https://pith.science/api/pith-number/SZHGHSK3SKCA7WW4UX77RJNWN4/events.json","paper":"https://pith.science/paper/SZHGHSK3"},"agent_actions":{"view_html":"https://pith.science/pith/SZHGHSK3SKCA7WW4UX77RJNWN4","download_json":"https://pith.science/pith/SZHGHSK3SKCA7WW4UX77RJNWN4.json","view_paper":"https://pith.science/paper/SZHGHSK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.06168&json=true","fetch_graph":"https://pith.science/api/pith-number/SZHGHSK3SKCA7WW4UX77RJNWN4/graph.json","fetch_events":"https://pith.science/api/pith-number/SZHGHSK3SKCA7WW4UX77RJNWN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZHGHSK3SKCA7WW4UX77RJNWN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZHGHSK3SKCA7WW4UX77RJNWN4/action/storage_attestation","attest_author":"https://pith.science/pith/SZHGHSK3SKCA7WW4UX77RJNWN4/action/author_attestation","sign_citation":"https://pith.science/pith/SZHGHSK3SKCA7WW4UX77RJNWN4/action/citation_signature","submit_replication":"https://pith.science/pith/SZHGHSK3SKCA7WW4UX77RJNWN4/action/replication_record"}},"created_at":"2026-05-18T00:37:44.755791+00:00","updated_at":"2026-05-18T00:37:44.755791+00:00"}