{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:F5ZCUHUGEBAZ4BNSJFOMM5F6DT","short_pith_number":"pith:F5ZCUHUG","schema_version":"1.0","canonical_sha256":"2f722a1e8620419e05b2495cc674be1cfee41bf466f98450a2f064b2bbb3b861","source":{"kind":"arxiv","id":"1710.01878","version":2},"attestation_state":"computed","paper":{"title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michael Zhu, Suyog Gupta","submitted_at":"2017-10-05T04:26:49Z","abstract_excerpt":"Model pruning seeks to induce sparsity in a deep neural network's various connection matrices, thereby reducing the number of nonzero-valued parameters in the model. Recent reports (Han et al., 2015; Narang et al., 2017) prune deep networks at the cost of only a marginal loss in accuracy and achieve a sizable reduction in model size. This hints at the possibility that the baseline models in these experiments are perhaps severely over-parameterized at the outset and a viable alternative for model compression might be to simply reduce the number of hidden units while maintaining the model's dens"},"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":"1710.01878","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-05T04:26:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"193ad00b99fd0bfaa8952781158e0f014f0281c30a22af487e296a3f4ab4860b","abstract_canon_sha256":"62cac133efe7cee2d48831b3beb526dde3f01dab3c369b9110b8793dbb1c148a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:40.778623Z","signature_b64":"EBwgox/uqa+Ltodf1BYUIjt65eWqvWZpVWp/j73qKPUNuoioGr4SjMDLKgcKrmhsgSaG5bqd1wMuou7/BBxuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f722a1e8620419e05b2495cc674be1cfee41bf466f98450a2f064b2bbb3b861","last_reissued_at":"2026-05-18T00:30:40.777965Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:40.777965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michael Zhu, Suyog Gupta","submitted_at":"2017-10-05T04:26:49Z","abstract_excerpt":"Model pruning seeks to induce sparsity in a deep neural network's various connection matrices, thereby reducing the number of nonzero-valued parameters in the model. Recent reports (Han et al., 2015; Narang et al., 2017) prune deep networks at the cost of only a marginal loss in accuracy and achieve a sizable reduction in model size. This hints at the possibility that the baseline models in these experiments are perhaps severely over-parameterized at the outset and a viable alternative for model compression might be to simply reduce the number of hidden units while maintaining the model's dens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.01878","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":"1710.01878","created_at":"2026-05-18T00:30:40.778062+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.01878v2","created_at":"2026-05-18T00:30:40.778062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.01878","created_at":"2026-05-18T00:30:40.778062+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5ZCUHUGEBAZ","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5ZCUHUGEBAZ4BNS","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5ZCUHUG","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2502.07189","citing_title":"Exploring Vision Neural Network Pruning via Screening Methodology","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2505.06907","citing_title":"A Survey on Foundation Models for Personalized Federated Intelligence","ref_index":191,"is_internal_anchor":true},{"citing_arxiv_id":"2510.08008","citing_title":"Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2601.02353","citing_title":"Meta-Learning Guided Pruning for Few-Shot Plant Pathology on Edge Devices","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18331","citing_title":"Prune, Update and Trim: Robust Structured Pruning for Large Language Models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09988","citing_title":"Engineering Resource-constrained Software Systems with DNN Components: a Concept-based Pruning Approach","ref_index":97,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT","json":"https://pith.science/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT.json","graph_json":"https://pith.science/api/pith-number/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/graph.json","events_json":"https://pith.science/api/pith-number/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/events.json","paper":"https://pith.science/paper/F5ZCUHUG"},"agent_actions":{"view_html":"https://pith.science/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT","download_json":"https://pith.science/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT.json","view_paper":"https://pith.science/paper/F5ZCUHUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.01878&json=true","fetch_graph":"https://pith.science/api/pith-number/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/graph.json","fetch_events":"https://pith.science/api/pith-number/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/action/storage_attestation","attest_author":"https://pith.science/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/action/author_attestation","sign_citation":"https://pith.science/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/action/citation_signature","submit_replication":"https://pith.science/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/action/replication_record"}},"created_at":"2026-05-18T00:30:40.778062+00:00","updated_at":"2026-05-18T00:30:40.778062+00:00"}