{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HVOJSZDH5TTRABKVNCJWKQPUJM","short_pith_number":"pith:HVOJSZDH","schema_version":"1.0","canonical_sha256":"3d5c996467ece710055568936541f44b35a46c46e0b13f4dabf130faebebdc09","source":{"kind":"arxiv","id":"1908.11091","version":1},"attestation_state":"computed","paper":{"title":"Deep Neural Network Ensembles against Deception: Ensemble Diversity, Accuracy and Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Emre Gursoy, Ka-Ho Chow, Ling Liu, Margaret Loper, Stacey Truex, Wenqi Wei, Yanzhao Wu","submitted_at":"2019-08-29T08:22:05Z","abstract_excerpt":"Ensemble learning is a methodology that integrates multiple DNN learners for improving prediction performance of individual learners. Diversity is greater when the errors of the ensemble prediction is more uniformly distributed. Greater diversity is highly correlated with the increase in ensemble accuracy. Another attractive property of diversity optimized ensemble learning is its robustness against deception: an adversarial perturbation attack can mislead one DNN model to misclassify but may not fool other ensemble DNN members consistently. In this paper we first give an overview of the conce"},"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":"1908.11091","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-29T08:22:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e7f5a7d35e5e636d441e742e5e52d29b45e10f9f79af0134ca1242a88300433e","abstract_canon_sha256":"9ee196fd593199006b963a4106b5dd2730e01a7d0413ce65559d1272ca52d67f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:00:30.439519Z","signature_b64":"JAIhT39+O6pzcnKLO06T94IYXKliwzGhH45J+PWkt2N9Ve2JvAkOJAmKMKkwAul8pzqYaW9oA+AIM0LRBVMLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d5c996467ece710055568936541f44b35a46c46e0b13f4dabf130faebebdc09","last_reissued_at":"2026-07-05T00:00:30.438989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:00:30.438989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Neural Network Ensembles against Deception: Ensemble Diversity, Accuracy and Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Emre Gursoy, Ka-Ho Chow, Ling Liu, Margaret Loper, Stacey Truex, Wenqi Wei, Yanzhao Wu","submitted_at":"2019-08-29T08:22:05Z","abstract_excerpt":"Ensemble learning is a methodology that integrates multiple DNN learners for improving prediction performance of individual learners. Diversity is greater when the errors of the ensemble prediction is more uniformly distributed. Greater diversity is highly correlated with the increase in ensemble accuracy. Another attractive property of diversity optimized ensemble learning is its robustness against deception: an adversarial perturbation attack can mislead one DNN model to misclassify but may not fool other ensemble DNN members consistently. In this paper we first give an overview of the conce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.11091","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/1908.11091/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":"1908.11091","created_at":"2026-07-05T00:00:30.439048+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.11091v1","created_at":"2026-07-05T00:00:30.439048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.11091","created_at":"2026-07-05T00:00:30.439048+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVOJSZDH5TTR","created_at":"2026-07-05T00:00:30.439048+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVOJSZDH5TTRABKV","created_at":"2026-07-05T00:00:30.439048+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVOJSZDH","created_at":"2026-07-05T00:00:30.439048+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/HVOJSZDH5TTRABKVNCJWKQPUJM","json":"https://pith.science/pith/HVOJSZDH5TTRABKVNCJWKQPUJM.json","graph_json":"https://pith.science/api/pith-number/HVOJSZDH5TTRABKVNCJWKQPUJM/graph.json","events_json":"https://pith.science/api/pith-number/HVOJSZDH5TTRABKVNCJWKQPUJM/events.json","paper":"https://pith.science/paper/HVOJSZDH"},"agent_actions":{"view_html":"https://pith.science/pith/HVOJSZDH5TTRABKVNCJWKQPUJM","download_json":"https://pith.science/pith/HVOJSZDH5TTRABKVNCJWKQPUJM.json","view_paper":"https://pith.science/paper/HVOJSZDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.11091&json=true","fetch_graph":"https://pith.science/api/pith-number/HVOJSZDH5TTRABKVNCJWKQPUJM/graph.json","fetch_events":"https://pith.science/api/pith-number/HVOJSZDH5TTRABKVNCJWKQPUJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVOJSZDH5TTRABKVNCJWKQPUJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVOJSZDH5TTRABKVNCJWKQPUJM/action/storage_attestation","attest_author":"https://pith.science/pith/HVOJSZDH5TTRABKVNCJWKQPUJM/action/author_attestation","sign_citation":"https://pith.science/pith/HVOJSZDH5TTRABKVNCJWKQPUJM/action/citation_signature","submit_replication":"https://pith.science/pith/HVOJSZDH5TTRABKVNCJWKQPUJM/action/replication_record"}},"created_at":"2026-07-05T00:00:30.439048+00:00","updated_at":"2026-07-05T00:00:30.439048+00:00"}