{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DCQYCOB5QPLASWGJGTKXNVEWS4","short_pith_number":"pith:DCQYCOB5","schema_version":"1.0","canonical_sha256":"18a181383d83d60958c934d576d496972f62ef722694b20610c0ca7185986cb0","source":{"kind":"arxiv","id":"2212.07070","version":1},"attestation_state":"computed","paper":{"title":"Deep Negative Correlation Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ce Zhu, Jia-Wang Bian, Joey Tianyi Zhou, Le Zhang, Qibin Hou, Xun Xu, Yun Liu","submitted_at":"2022-12-14T07:35:20Z","abstract_excerpt":"Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm. Existing deep ensemble methods usually naively train many different models and then aggregate their predictions. This is not optimal in our view from two aspects: i) Naively training multiple models adds much more computational burden, especially in the deep learning era; ii) Purely optimizing each base model without considering their interactions limits the diversity of ensemble and performance gains. We tackle these issues by proposing deep negative correlation classificatio"},"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":"2212.07070","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-14T07:35:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5683dd98825cd90965cedd4e24dad096ac20583538c55269c1e2f134caf00f53","abstract_canon_sha256":"435752e1bd36f4ea0bdb55616b40aa607f36abb87afaa7d3bac1eb84359558b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:21.032052Z","signature_b64":"QkJz1Za3UsP0FJbJzwoww4JgyahOiGo6l8T0WSKZBtfGiJg+LGzWMT2Fun+seMjqTPP3uKG8y3sTYQQ4afzUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18a181383d83d60958c934d576d496972f62ef722694b20610c0ca7185986cb0","last_reissued_at":"2026-07-05T05:25:21.031729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:21.031729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Negative Correlation Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ce Zhu, Jia-Wang Bian, Joey Tianyi Zhou, Le Zhang, Qibin Hou, Xun Xu, Yun Liu","submitted_at":"2022-12-14T07:35:20Z","abstract_excerpt":"Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm. Existing deep ensemble methods usually naively train many different models and then aggregate their predictions. This is not optimal in our view from two aspects: i) Naively training multiple models adds much more computational burden, especially in the deep learning era; ii) Purely optimizing each base model without considering their interactions limits the diversity of ensemble and performance gains. We tackle these issues by proposing deep negative correlation classificatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07070","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/2212.07070/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":"2212.07070","created_at":"2026-07-05T05:25:21.031783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.07070v1","created_at":"2026-07-05T05:25:21.031783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07070","created_at":"2026-07-05T05:25:21.031783+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCQYCOB5QPLA","created_at":"2026-07-05T05:25:21.031783+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCQYCOB5QPLASWGJ","created_at":"2026-07-05T05:25:21.031783+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCQYCOB5","created_at":"2026-07-05T05:25:21.031783+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/DCQYCOB5QPLASWGJGTKXNVEWS4","json":"https://pith.science/pith/DCQYCOB5QPLASWGJGTKXNVEWS4.json","graph_json":"https://pith.science/api/pith-number/DCQYCOB5QPLASWGJGTKXNVEWS4/graph.json","events_json":"https://pith.science/api/pith-number/DCQYCOB5QPLASWGJGTKXNVEWS4/events.json","paper":"https://pith.science/paper/DCQYCOB5"},"agent_actions":{"view_html":"https://pith.science/pith/DCQYCOB5QPLASWGJGTKXNVEWS4","download_json":"https://pith.science/pith/DCQYCOB5QPLASWGJGTKXNVEWS4.json","view_paper":"https://pith.science/paper/DCQYCOB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.07070&json=true","fetch_graph":"https://pith.science/api/pith-number/DCQYCOB5QPLASWGJGTKXNVEWS4/graph.json","fetch_events":"https://pith.science/api/pith-number/DCQYCOB5QPLASWGJGTKXNVEWS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCQYCOB5QPLASWGJGTKXNVEWS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCQYCOB5QPLASWGJGTKXNVEWS4/action/storage_attestation","attest_author":"https://pith.science/pith/DCQYCOB5QPLASWGJGTKXNVEWS4/action/author_attestation","sign_citation":"https://pith.science/pith/DCQYCOB5QPLASWGJGTKXNVEWS4/action/citation_signature","submit_replication":"https://pith.science/pith/DCQYCOB5QPLASWGJGTKXNVEWS4/action/replication_record"}},"created_at":"2026-07-05T05:25:21.031783+00:00","updated_at":"2026-07-05T05:25:21.031783+00:00"}