{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OKRY25Y4I6VWWLAD72BKK66LWH","short_pith_number":"pith:OKRY25Y4","schema_version":"1.0","canonical_sha256":"72a38d771c47ab6b2c03fe82a57bcbb1c3ba8b8a9aee68ce8ee28ebb840d35ee","source":{"kind":"arxiv","id":"2309.14976","version":4},"attestation_state":"computed","paper":{"title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kemal Oksuz, Puneet K. Dokania, Selim Kuzucu, Tom Joy","submitted_at":"2023-09-26T14:52:51Z","abstract_excerpt":"Combining the strengths of many existing predictors to obtain a Mixture of Experts which is superior to its individual components is an effective way to improve the performance without having to develop new architectures or train a model from scratch. However, surprisingly, we find that na\\\"ively combining expert object detectors in a similar way to Deep Ensembles, can often lead to degraded performance. We identify that the primary cause of this issue is that the predictions of the experts do not match their performance, a term referred to as miscalibration. Consequently, the most confident d"},"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":"2309.14976","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-26T14:52:51Z","cross_cats_sorted":[],"title_canon_sha256":"043bbf3af6e757c625fa6a898c311aa6c27c613621993e84e347428c9b1e7e51","abstract_canon_sha256":"51bf12d12eb3b8d135bb43e1a17decd3908e9948f5dcc95e6d1bb7ab2eda7504"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:02.248358Z","signature_b64":"A+nKnZ2Hd62Rn3Ss2w9c4hch/q1laiViyBts8Aarakprkab59jOebFERwlwtsMtVw+YKTUHiTslRcaEblE4ADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72a38d771c47ab6b2c03fe82a57bcbb1c3ba8b8a9aee68ce8ee28ebb840d35ee","last_reissued_at":"2026-07-05T07:40:02.247885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:02.247885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kemal Oksuz, Puneet K. Dokania, Selim Kuzucu, Tom Joy","submitted_at":"2023-09-26T14:52:51Z","abstract_excerpt":"Combining the strengths of many existing predictors to obtain a Mixture of Experts which is superior to its individual components is an effective way to improve the performance without having to develop new architectures or train a model from scratch. However, surprisingly, we find that na\\\"ively combining expert object detectors in a similar way to Deep Ensembles, can often lead to degraded performance. We identify that the primary cause of this issue is that the predictions of the experts do not match their performance, a term referred to as miscalibration. Consequently, the most confident d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14976","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/2309.14976/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":"2309.14976","created_at":"2026-07-05T07:40:02.247941+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.14976v4","created_at":"2026-07-05T07:40:02.247941+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14976","created_at":"2026-07-05T07:40:02.247941+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKRY25Y4I6VW","created_at":"2026-07-05T07:40:02.247941+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKRY25Y4I6VWWLAD","created_at":"2026-07-05T07:40:02.247941+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKRY25Y4","created_at":"2026-07-05T07:40:02.247941+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08250","citing_title":"On the Design of Mixture-of-Experts for Dynamic Gaussian Splatting","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2606.32040","citing_title":"FaceMoE: Mixture of Experts for Low-Resolution Face Recognition","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19016","citing_title":"AlignCultura: Towards Culturally Aligned Large Language Models?","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04908","citing_title":"HI-MoE: Hierarchical Instance-Conditioned Mixture-of-Experts for Object Detection","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKRY25Y4I6VWWLAD72BKK66LWH","json":"https://pith.science/pith/OKRY25Y4I6VWWLAD72BKK66LWH.json","graph_json":"https://pith.science/api/pith-number/OKRY25Y4I6VWWLAD72BKK66LWH/graph.json","events_json":"https://pith.science/api/pith-number/OKRY25Y4I6VWWLAD72BKK66LWH/events.json","paper":"https://pith.science/paper/OKRY25Y4"},"agent_actions":{"view_html":"https://pith.science/pith/OKRY25Y4I6VWWLAD72BKK66LWH","download_json":"https://pith.science/pith/OKRY25Y4I6VWWLAD72BKK66LWH.json","view_paper":"https://pith.science/paper/OKRY25Y4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.14976&json=true","fetch_graph":"https://pith.science/api/pith-number/OKRY25Y4I6VWWLAD72BKK66LWH/graph.json","fetch_events":"https://pith.science/api/pith-number/OKRY25Y4I6VWWLAD72BKK66LWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKRY25Y4I6VWWLAD72BKK66LWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKRY25Y4I6VWWLAD72BKK66LWH/action/storage_attestation","attest_author":"https://pith.science/pith/OKRY25Y4I6VWWLAD72BKK66LWH/action/author_attestation","sign_citation":"https://pith.science/pith/OKRY25Y4I6VWWLAD72BKK66LWH/action/citation_signature","submit_replication":"https://pith.science/pith/OKRY25Y4I6VWWLAD72BKK66LWH/action/replication_record"}},"created_at":"2026-07-05T07:40:02.247941+00:00","updated_at":"2026-07-05T07:40:02.247941+00:00"}