{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GEZ6FPF76WLNIXW34N4TQN3GVJ","short_pith_number":"pith:GEZ6FPF7","schema_version":"1.0","canonical_sha256":"3133e2bcbff596d45edbe379383766aa550d8feb4c7f9ad3e7f6d24b2f78bde5","source":{"kind":"arxiv","id":"2011.14660","version":4},"attestation_state":"computed","paper":{"title":"Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deng Cai, Liguang Zhou, Shuai Zhao, Tin Lun Lam, Wenxiao Wang, Yangsheng Xu","submitted_at":"2020-11-30T10:03:34Z","abstract_excerpt":"The width of a neural network matters since increasing the width will necessarily increase the model capacity. However, the performance of a network does not improve linearly with the width and soon gets saturated. In this case, we argue that increasing the number of networks (ensemble) can achieve better accuracy-efficiency trade-offs than purely increasing the width. To prove it, one large network is divided into several small ones regarding its parameters and regularization components. Each of these small networks has a fraction of the original one's parameters. We then train these small ne"},"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":"2011.14660","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-30T10:03:34Z","cross_cats_sorted":[],"title_canon_sha256":"18b5c946d2b43abd56acb654833e9e7ca7ed9855387ece521a4bcf2d2b7ae191","abstract_canon_sha256":"5561503c4ee6b9c98db88ba4bc33222e7da0daca5e35b96bbbdb72628d159902"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:44.402924Z","signature_b64":"pjMS/mAIGxk5j2j4Mpbd5h6C6c1zAfclsZkLARGhmUy1HSmJXUUomgzqG7Es0UyCuebeThYSjPWbRT8W05PaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3133e2bcbff596d45edbe379383766aa550d8feb4c7f9ad3e7f6d24b2f78bde5","last_reissued_at":"2026-07-05T04:54:44.402496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:44.402496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deng Cai, Liguang Zhou, Shuai Zhao, Tin Lun Lam, Wenxiao Wang, Yangsheng Xu","submitted_at":"2020-11-30T10:03:34Z","abstract_excerpt":"The width of a neural network matters since increasing the width will necessarily increase the model capacity. However, the performance of a network does not improve linearly with the width and soon gets saturated. In this case, we argue that increasing the number of networks (ensemble) can achieve better accuracy-efficiency trade-offs than purely increasing the width. To prove it, one large network is divided into several small ones regarding its parameters and regularization components. Each of these small networks has a fraction of the original one's parameters. We then train these small ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14660","kind":"arxiv","version":4},"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/2011.14660/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":"2011.14660","created_at":"2026-07-05T04:54:44.402558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.14660v4","created_at":"2026-07-05T04:54:44.402558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14660","created_at":"2026-07-05T04:54:44.402558+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEZ6FPF76WLN","created_at":"2026-07-05T04:54:44.402558+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEZ6FPF76WLNIXW3","created_at":"2026-07-05T04:54:44.402558+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEZ6FPF7","created_at":"2026-07-05T04:54:44.402558+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/GEZ6FPF76WLNIXW34N4TQN3GVJ","json":"https://pith.science/pith/GEZ6FPF76WLNIXW34N4TQN3GVJ.json","graph_json":"https://pith.science/api/pith-number/GEZ6FPF76WLNIXW34N4TQN3GVJ/graph.json","events_json":"https://pith.science/api/pith-number/GEZ6FPF76WLNIXW34N4TQN3GVJ/events.json","paper":"https://pith.science/paper/GEZ6FPF7"},"agent_actions":{"view_html":"https://pith.science/pith/GEZ6FPF76WLNIXW34N4TQN3GVJ","download_json":"https://pith.science/pith/GEZ6FPF76WLNIXW34N4TQN3GVJ.json","view_paper":"https://pith.science/paper/GEZ6FPF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.14660&json=true","fetch_graph":"https://pith.science/api/pith-number/GEZ6FPF76WLNIXW34N4TQN3GVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GEZ6FPF76WLNIXW34N4TQN3GVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEZ6FPF76WLNIXW34N4TQN3GVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEZ6FPF76WLNIXW34N4TQN3GVJ/action/storage_attestation","attest_author":"https://pith.science/pith/GEZ6FPF76WLNIXW34N4TQN3GVJ/action/author_attestation","sign_citation":"https://pith.science/pith/GEZ6FPF76WLNIXW34N4TQN3GVJ/action/citation_signature","submit_replication":"https://pith.science/pith/GEZ6FPF76WLNIXW34N4TQN3GVJ/action/replication_record"}},"created_at":"2026-07-05T04:54:44.402558+00:00","updated_at":"2026-07-05T04:54:44.402558+00:00"}