{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:P4VTAWI5OSXAI2DLZWQ22SE6JO","short_pith_number":"pith:P4VTAWI5","schema_version":"1.0","canonical_sha256":"7f2b30591d74ae04686bcda1ad489e4b97588148a6cf3e82cab07970824d16d8","source":{"kind":"arxiv","id":"2201.10908","version":1},"attestation_state":"computed","paper":{"title":"Improving robustness and calibration in ensembles with diversity regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anirban Mukhopadhyay, Camila Gonz\\'alez, Hendrik Alexander Mehrtens","submitted_at":"2022-01-26T12:51:11Z","abstract_excerpt":"Calibration and uncertainty estimation are crucial topics in high-risk environments. We introduce a new diversity regularizer for classification tasks that uses out-of-distribution samples and increases the overall accuracy, calibration and out-of-distribution detection capabilities of ensembles. Following the recent interest in the diversity of ensembles, we systematically evaluate the viability of explicitly regularizing ensemble diversity to improve calibration on in-distribution data as well as under dataset shift. We demonstrate that diversity regularization is highly beneficial in archit"},"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":"2201.10908","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-26T12:51:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9a8a7205f3d96a8ddf91046e1f1757a4fe4dd408ebc25c4373b33d616352bf37","abstract_canon_sha256":"518cab56183b90afd9316c2755031da71a6f5a421a0b54661a95c5427db96000"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:26.164509Z","signature_b64":"opZPtOzNDzqF6BKhNvCI1Ln1AuI5TxbXXWdDULBsEVSCmr3qWco5H9uFDgJABvGjBJWE+37R/U1UW04GYiiBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f2b30591d74ae04686bcda1ad489e4b97588148a6cf3e82cab07970824d16d8","last_reissued_at":"2026-07-05T05:08:26.164155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:26.164155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving robustness and calibration in ensembles with diversity regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anirban Mukhopadhyay, Camila Gonz\\'alez, Hendrik Alexander Mehrtens","submitted_at":"2022-01-26T12:51:11Z","abstract_excerpt":"Calibration and uncertainty estimation are crucial topics in high-risk environments. We introduce a new diversity regularizer for classification tasks that uses out-of-distribution samples and increases the overall accuracy, calibration and out-of-distribution detection capabilities of ensembles. Following the recent interest in the diversity of ensembles, we systematically evaluate the viability of explicitly regularizing ensemble diversity to improve calibration on in-distribution data as well as under dataset shift. We demonstrate that diversity regularization is highly beneficial in archit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10908","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/2201.10908/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":"2201.10908","created_at":"2026-07-05T05:08:26.164216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.10908v1","created_at":"2026-07-05T05:08:26.164216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10908","created_at":"2026-07-05T05:08:26.164216+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4VTAWI5OSXA","created_at":"2026-07-05T05:08:26.164216+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4VTAWI5OSXAI2DL","created_at":"2026-07-05T05:08:26.164216+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4VTAWI5","created_at":"2026-07-05T05:08:26.164216+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/P4VTAWI5OSXAI2DLZWQ22SE6JO","json":"https://pith.science/pith/P4VTAWI5OSXAI2DLZWQ22SE6JO.json","graph_json":"https://pith.science/api/pith-number/P4VTAWI5OSXAI2DLZWQ22SE6JO/graph.json","events_json":"https://pith.science/api/pith-number/P4VTAWI5OSXAI2DLZWQ22SE6JO/events.json","paper":"https://pith.science/paper/P4VTAWI5"},"agent_actions":{"view_html":"https://pith.science/pith/P4VTAWI5OSXAI2DLZWQ22SE6JO","download_json":"https://pith.science/pith/P4VTAWI5OSXAI2DLZWQ22SE6JO.json","view_paper":"https://pith.science/paper/P4VTAWI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.10908&json=true","fetch_graph":"https://pith.science/api/pith-number/P4VTAWI5OSXAI2DLZWQ22SE6JO/graph.json","fetch_events":"https://pith.science/api/pith-number/P4VTAWI5OSXAI2DLZWQ22SE6JO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4VTAWI5OSXAI2DLZWQ22SE6JO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4VTAWI5OSXAI2DLZWQ22SE6JO/action/storage_attestation","attest_author":"https://pith.science/pith/P4VTAWI5OSXAI2DLZWQ22SE6JO/action/author_attestation","sign_citation":"https://pith.science/pith/P4VTAWI5OSXAI2DLZWQ22SE6JO/action/citation_signature","submit_replication":"https://pith.science/pith/P4VTAWI5OSXAI2DLZWQ22SE6JO/action/replication_record"}},"created_at":"2026-07-05T05:08:26.164216+00:00","updated_at":"2026-07-05T05:08:26.164216+00:00"}