{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FAH7OIBYZEC5W5CF2RYSULPU77","short_pith_number":"pith:FAH7OIBY","schema_version":"1.0","canonical_sha256":"280ff72038c905db7445d4712a2df4fffbcc9e89a9336b6e8287e0d9a65c3459","source":{"kind":"arxiv","id":"2310.02237","version":1},"attestation_state":"computed","paper":{"title":"Exploring Model Learning Heterogeneity for Boosting Ensemble Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ka-Ho Chow, Ling Liu, Wenqi Wei, Yanzhao Wu","submitted_at":"2023-10-03T17:47:25Z","abstract_excerpt":"Deep neural network ensembles hold the potential of improving generalization performance for complex learning tasks. This paper presents formal analysis and empirical evaluation to show that heterogeneous deep ensembles with high ensemble diversity can effectively leverage model learning heterogeneity to boost ensemble robustness. We first show that heterogeneous DNN models trained for solving the same learning problem, e.g., object detection, can significantly strengthen the mean average precision (mAP) through our weighted bounding box ensemble consensus method. Second, we further compose en"},"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":"2310.02237","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-03T17:47:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ae387273f2d185fd803bd1835dbde77e82c182ad3adfed1cf323c2fc213fd811","abstract_canon_sha256":"dd382f7e2a93a827ce9726c92581f21e6746786ec805ccf16f9d6999d6182d90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:51.748884Z","signature_b64":"9T9du+K8Zs5MqkG/4o/miXcOd8gqFfl+dzfNP8uKYs5333Pb6MMXB5CFj0CFxbCJD1AkN80TtOzAO42K5pKyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"280ff72038c905db7445d4712a2df4fffbcc9e89a9336b6e8287e0d9a65c3459","last_reissued_at":"2026-07-05T06:56:51.748399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:51.748399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Model Learning Heterogeneity for Boosting Ensemble Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ka-Ho Chow, Ling Liu, Wenqi Wei, Yanzhao Wu","submitted_at":"2023-10-03T17:47:25Z","abstract_excerpt":"Deep neural network ensembles hold the potential of improving generalization performance for complex learning tasks. This paper presents formal analysis and empirical evaluation to show that heterogeneous deep ensembles with high ensemble diversity can effectively leverage model learning heterogeneity to boost ensemble robustness. We first show that heterogeneous DNN models trained for solving the same learning problem, e.g., object detection, can significantly strengthen the mean average precision (mAP) through our weighted bounding box ensemble consensus method. Second, we further compose en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02237","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/2310.02237/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":"2310.02237","created_at":"2026-07-05T06:56:51.748464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02237v1","created_at":"2026-07-05T06:56:51.748464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02237","created_at":"2026-07-05T06:56:51.748464+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAH7OIBYZEC5","created_at":"2026-07-05T06:56:51.748464+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAH7OIBYZEC5W5CF","created_at":"2026-07-05T06:56:51.748464+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAH7OIBY","created_at":"2026-07-05T06:56:51.748464+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/FAH7OIBYZEC5W5CF2RYSULPU77","json":"https://pith.science/pith/FAH7OIBYZEC5W5CF2RYSULPU77.json","graph_json":"https://pith.science/api/pith-number/FAH7OIBYZEC5W5CF2RYSULPU77/graph.json","events_json":"https://pith.science/api/pith-number/FAH7OIBYZEC5W5CF2RYSULPU77/events.json","paper":"https://pith.science/paper/FAH7OIBY"},"agent_actions":{"view_html":"https://pith.science/pith/FAH7OIBYZEC5W5CF2RYSULPU77","download_json":"https://pith.science/pith/FAH7OIBYZEC5W5CF2RYSULPU77.json","view_paper":"https://pith.science/paper/FAH7OIBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02237&json=true","fetch_graph":"https://pith.science/api/pith-number/FAH7OIBYZEC5W5CF2RYSULPU77/graph.json","fetch_events":"https://pith.science/api/pith-number/FAH7OIBYZEC5W5CF2RYSULPU77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAH7OIBYZEC5W5CF2RYSULPU77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAH7OIBYZEC5W5CF2RYSULPU77/action/storage_attestation","attest_author":"https://pith.science/pith/FAH7OIBYZEC5W5CF2RYSULPU77/action/author_attestation","sign_citation":"https://pith.science/pith/FAH7OIBYZEC5W5CF2RYSULPU77/action/citation_signature","submit_replication":"https://pith.science/pith/FAH7OIBYZEC5W5CF2RYSULPU77/action/replication_record"}},"created_at":"2026-07-05T06:56:51.748464+00:00","updated_at":"2026-07-05T06:56:51.748464+00:00"}