{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YCBHLKJIIQSNNC7GSGRQL5GSPR","short_pith_number":"pith:YCBHLKJI","schema_version":"1.0","canonical_sha256":"c08275a9284424d68be691a305f4d27c77b6c95527d7e37e699a53c55333407d","source":{"kind":"arxiv","id":"2607.27995","version":1},"attestation_state":"computed","paper":{"title":"Generalization and Trade-off in Adversarial Training: An RKHS Perspective via Kernel Integral Operators","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Xiaoming Huo, Yiling Xie","submitted_at":"2026-07-30T10:43:29Z","abstract_excerpt":"Adversarial training has emerged as a powerful approach for protecting models against adversarial attacks in a broad range of real-world applications. In this paper, we study adversarial training in the reproducing kernel Hilbert space (RKHS) framework through the associated kernel integral operator. We first derive source-uniform generalization error bounds for the RKHS adversarial training estimator in terms of the robustness level, sample size, source smoothness, and kernel spectrum. On a fixed polynomial-spectrum model, we further establish a matching lower bound showing that the optimally"},"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":"2607.27995","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2026-07-30T10:43:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"82c5c91f7787c649869e561ca4a1f22377399f282841e2b572f6ecff1e64840e","abstract_canon_sha256":"db7d3e6f8fe50aeacda9fdb8e778675cf1c4d36414fb9a96c07450e4798e76b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c08275a9284424d68be691a305f4d27c77b6c95527d7e37e699a53c55333407d","last_reissued_at":"2026-07-31T01:35:12.730069Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:35:12.730069Z"},"graph_snapshot":{"paper":{"title":"Generalization and Trade-off in Adversarial Training: An RKHS Perspective via Kernel Integral Operators","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Xiaoming Huo, Yiling Xie","submitted_at":"2026-07-30T10:43:29Z","abstract_excerpt":"Adversarial training has emerged as a powerful approach for protecting models against adversarial attacks in a broad range of real-world applications. In this paper, we study adversarial training in the reproducing kernel Hilbert space (RKHS) framework through the associated kernel integral operator. We first derive source-uniform generalization error bounds for the RKHS adversarial training estimator in terms of the robustness level, sample size, source smoothness, and kernel spectrum. On a fixed polynomial-spectrum model, we further establish a matching lower bound showing that the optimally"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27995","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/2607.27995/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":"2607.27995","created_at":"2026-07-31T01:35:12.733225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27995v1","created_at":"2026-07-31T01:35:12.733225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27995","created_at":"2026-07-31T01:35:12.733225+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCBHLKJIIQSN","created_at":"2026-07-31T01:35:12.733225+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCBHLKJIIQSNNC7G","created_at":"2026-07-31T01:35:12.733225+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCBHLKJI","created_at":"2026-07-31T01:35:12.733225+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/YCBHLKJIIQSNNC7GSGRQL5GSPR","json":"https://pith.science/pith/YCBHLKJIIQSNNC7GSGRQL5GSPR.json","graph_json":"https://pith.science/api/pith-number/YCBHLKJIIQSNNC7GSGRQL5GSPR/graph.json","events_json":"https://pith.science/api/pith-number/YCBHLKJIIQSNNC7GSGRQL5GSPR/events.json","paper":"https://pith.science/paper/YCBHLKJI"},"agent_actions":{"view_html":"https://pith.science/pith/YCBHLKJIIQSNNC7GSGRQL5GSPR","download_json":"https://pith.science/pith/YCBHLKJIIQSNNC7GSGRQL5GSPR.json","view_paper":"https://pith.science/paper/YCBHLKJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27995&json=true","fetch_graph":"https://pith.science/api/pith-number/YCBHLKJIIQSNNC7GSGRQL5GSPR/graph.json","fetch_events":"https://pith.science/api/pith-number/YCBHLKJIIQSNNC7GSGRQL5GSPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCBHLKJIIQSNNC7GSGRQL5GSPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCBHLKJIIQSNNC7GSGRQL5GSPR/action/storage_attestation","attest_author":"https://pith.science/pith/YCBHLKJIIQSNNC7GSGRQL5GSPR/action/author_attestation","sign_citation":"https://pith.science/pith/YCBHLKJIIQSNNC7GSGRQL5GSPR/action/citation_signature","submit_replication":"https://pith.science/pith/YCBHLKJIIQSNNC7GSGRQL5GSPR/action/replication_record"}},"created_at":"2026-07-31T01:35:12.733225+00:00","updated_at":"2026-07-31T01:35:12.733225+00:00"}