{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R355QMKXU7YRCGFS64PTFFAYR7","short_pith_number":"pith:R355QMKX","schema_version":"1.0","canonical_sha256":"8efbd83157a7f11118b2f71f3294188fe9df2bb0a353198574af6ec8800a765d","source":{"kind":"arxiv","id":"2402.02263","version":5},"attestation_state":"computed","paper":{"title":"MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Mo Zhou, Somayeh Sojoudi, Vishal M. Patel, Yatong Bai","submitted_at":"2024-02-03T21:12:36Z","abstract_excerpt":"Adversarial robustness often comes at the cost of degraded accuracy, impeding real-life applications of robust classification models. Training-based solutions for better trade-offs are limited by incompatibilities with already-trained high-performance large models, necessitating the exploration of training-free ensemble approaches. Observing that robust models are more confident in correct predictions than in incorrect ones on clean and adversarial data alike, we speculate amplifying this \"benign confidence property\" can reconcile accuracy and robustness in an ensemble setting. To achieve so, "},"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":"2402.02263","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-03T21:12:36Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"a92f6e7e36f1f1a5d5d9104008711ac57a8ace2a6391f344687a3e45f289361f","abstract_canon_sha256":"58fbd1eeb9830f3b9a846dd922f3f146b859b263fdca5db83b3100c20dd3553b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:02.476591Z","signature_b64":"hUhN14feQvhQLH78VFGuY832xaq1m6kcAQUggZyuw6HFEag65MjMWuVehfSWQNLjRKkAvZxUCt987RpbCBQsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8efbd83157a7f11118b2f71f3294188fe9df2bb0a353198574af6ec8800a765d","last_reissued_at":"2026-07-05T09:21:02.476069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:02.476069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Mo Zhou, Somayeh Sojoudi, Vishal M. Patel, Yatong Bai","submitted_at":"2024-02-03T21:12:36Z","abstract_excerpt":"Adversarial robustness often comes at the cost of degraded accuracy, impeding real-life applications of robust classification models. Training-based solutions for better trade-offs are limited by incompatibilities with already-trained high-performance large models, necessitating the exploration of training-free ensemble approaches. Observing that robust models are more confident in correct predictions than in incorrect ones on clean and adversarial data alike, we speculate amplifying this \"benign confidence property\" can reconcile accuracy and robustness in an ensemble setting. To achieve so, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02263","kind":"arxiv","version":5},"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/2402.02263/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":"2402.02263","created_at":"2026-07-05T09:21:02.476144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02263v5","created_at":"2026-07-05T09:21:02.476144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02263","created_at":"2026-07-05T09:21:02.476144+00:00"},{"alias_kind":"pith_short_12","alias_value":"R355QMKXU7YR","created_at":"2026-07-05T09:21:02.476144+00:00"},{"alias_kind":"pith_short_16","alias_value":"R355QMKXU7YRCGFS","created_at":"2026-07-05T09:21:02.476144+00:00"},{"alias_kind":"pith_short_8","alias_value":"R355QMKX","created_at":"2026-07-05T09:21:02.476144+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06832","citing_title":"Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R355QMKXU7YRCGFS64PTFFAYR7","json":"https://pith.science/pith/R355QMKXU7YRCGFS64PTFFAYR7.json","graph_json":"https://pith.science/api/pith-number/R355QMKXU7YRCGFS64PTFFAYR7/graph.json","events_json":"https://pith.science/api/pith-number/R355QMKXU7YRCGFS64PTFFAYR7/events.json","paper":"https://pith.science/paper/R355QMKX"},"agent_actions":{"view_html":"https://pith.science/pith/R355QMKXU7YRCGFS64PTFFAYR7","download_json":"https://pith.science/pith/R355QMKXU7YRCGFS64PTFFAYR7.json","view_paper":"https://pith.science/paper/R355QMKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02263&json=true","fetch_graph":"https://pith.science/api/pith-number/R355QMKXU7YRCGFS64PTFFAYR7/graph.json","fetch_events":"https://pith.science/api/pith-number/R355QMKXU7YRCGFS64PTFFAYR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R355QMKXU7YRCGFS64PTFFAYR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R355QMKXU7YRCGFS64PTFFAYR7/action/storage_attestation","attest_author":"https://pith.science/pith/R355QMKXU7YRCGFS64PTFFAYR7/action/author_attestation","sign_citation":"https://pith.science/pith/R355QMKXU7YRCGFS64PTFFAYR7/action/citation_signature","submit_replication":"https://pith.science/pith/R355QMKXU7YRCGFS64PTFFAYR7/action/replication_record"}},"created_at":"2026-07-05T09:21:02.476144+00:00","updated_at":"2026-07-05T09:21:02.476144+00:00"}