{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CP633HS6ASRC3RTRSBX2G674PI","short_pith_number":"pith:CP633HS6","schema_version":"1.0","canonical_sha256":"13fdbd9e5e04a22dc671906fa37bfc7a24571d1f5c9154228ba1ecc246e0de8c","source":{"kind":"arxiv","id":"2301.03962","version":3},"attestation_state":"computed","paper":{"title":"A Unified Theory of Diversity in Ensemble Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Webb, Danny Wood, Gavin Brown, Henry Reeve, Mikel Luj\\'an, Tingting Mu","submitted_at":"2023-01-10T13:51:07Z","abstract_excerpt":"We present a theory of ensemble diversity, explaining the nature of diversity for a wide range of supervised learning scenarios. This challenge has been referred to as the holy grail of ensemble learning, an open research issue for over 30 years. Our framework reveals that diversity is in fact a hidden dimension in the bias-variance decomposition of the ensemble loss. We prove a family of exact bias-variance-diversity decompositions, for a wide range of losses in both regression and classification, e.g., squared, cross-entropy, and Poisson losses. For losses where an additive bias-variance dec"},"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":"2301.03962","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-10T13:51:07Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ae44dedb499ff9bd3bdcc88864b6e319cfbdd5c34393a869b19f1752ce611749","abstract_canon_sha256":"319f068566faff5b2a7295067203b6183b64cd6803fbc0f301c0294c74f51680"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:16.120578Z","signature_b64":"sU53UinsoOolNumebecUXiPg4xy+pylE5HZD8L5C7ICahHYFQnvK9pB4XtRt/W3ql92YSe5bpu7ddnghp4RUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13fdbd9e5e04a22dc671906fa37bfc7a24571d1f5c9154228ba1ecc246e0de8c","last_reissued_at":"2026-07-05T07:42:16.120113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:16.120113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Theory of Diversity in Ensemble Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Webb, Danny Wood, Gavin Brown, Henry Reeve, Mikel Luj\\'an, Tingting Mu","submitted_at":"2023-01-10T13:51:07Z","abstract_excerpt":"We present a theory of ensemble diversity, explaining the nature of diversity for a wide range of supervised learning scenarios. This challenge has been referred to as the holy grail of ensemble learning, an open research issue for over 30 years. Our framework reveals that diversity is in fact a hidden dimension in the bias-variance decomposition of the ensemble loss. We prove a family of exact bias-variance-diversity decompositions, for a wide range of losses in both regression and classification, e.g., squared, cross-entropy, and Poisson losses. For losses where an additive bias-variance dec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.03962","kind":"arxiv","version":3},"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/2301.03962/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":"2301.03962","created_at":"2026-07-05T07:42:16.120169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.03962v3","created_at":"2026-07-05T07:42:16.120169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.03962","created_at":"2026-07-05T07:42:16.120169+00:00"},{"alias_kind":"pith_short_12","alias_value":"CP633HS6ASRC","created_at":"2026-07-05T07:42:16.120169+00:00"},{"alias_kind":"pith_short_16","alias_value":"CP633HS6ASRC3RTR","created_at":"2026-07-05T07:42:16.120169+00:00"},{"alias_kind":"pith_short_8","alias_value":"CP633HS6","created_at":"2026-07-05T07:42:16.120169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27288","citing_title":"When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CP633HS6ASRC3RTRSBX2G674PI","json":"https://pith.science/pith/CP633HS6ASRC3RTRSBX2G674PI.json","graph_json":"https://pith.science/api/pith-number/CP633HS6ASRC3RTRSBX2G674PI/graph.json","events_json":"https://pith.science/api/pith-number/CP633HS6ASRC3RTRSBX2G674PI/events.json","paper":"https://pith.science/paper/CP633HS6"},"agent_actions":{"view_html":"https://pith.science/pith/CP633HS6ASRC3RTRSBX2G674PI","download_json":"https://pith.science/pith/CP633HS6ASRC3RTRSBX2G674PI.json","view_paper":"https://pith.science/paper/CP633HS6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.03962&json=true","fetch_graph":"https://pith.science/api/pith-number/CP633HS6ASRC3RTRSBX2G674PI/graph.json","fetch_events":"https://pith.science/api/pith-number/CP633HS6ASRC3RTRSBX2G674PI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CP633HS6ASRC3RTRSBX2G674PI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CP633HS6ASRC3RTRSBX2G674PI/action/storage_attestation","attest_author":"https://pith.science/pith/CP633HS6ASRC3RTRSBX2G674PI/action/author_attestation","sign_citation":"https://pith.science/pith/CP633HS6ASRC3RTRSBX2G674PI/action/citation_signature","submit_replication":"https://pith.science/pith/CP633HS6ASRC3RTRSBX2G674PI/action/replication_record"}},"created_at":"2026-07-05T07:42:16.120169+00:00","updated_at":"2026-07-05T07:42:16.120169+00:00"}