{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QO762SNXO6UDSRSKJTMZYUCD6N","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"40b31e4d9e3dc255d0862f3d93bc3b0aec8c70218204e7a22fd8368066221b9f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T09:53:04Z","title_canon_sha256":"931708a0d11dfb43f46c2716507e1fd3db7fc1a075e5317d51fb9033ea9f33cf"},"schema_version":"1.0","source":{"id":"2205.13863","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13863","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13863v3","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13863","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"QO762SNXO6UD","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"QO762SNXO6UDSRSK","created_at":"2026-07-05T05:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"QO762SNX","created_at":"2026-07-05T05:06:31Z"}],"graph_snapshots":[{"event_id":"sha256:9204277bd153499ff064364f87fbdfa3873c06a8cfb9ca30e3566e0f8e128c26","target":"graph","created_at":"2026-07-05T05:06:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2205.13863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is well-known that modern neural networks are vulnerable to adversarial examples. To mitigate this problem, a series of robust learning algorithms have been proposed. However, although the robust training error can be near zero via some methods, all existing algorithms lead to a high robust generalization error. In this paper, we provide a theoretical understanding of this puzzling phenomenon from the perspective of expressive power for deep neural networks. Specifically, for binary classification problems with well-separated data, we show that, for ReLU networks, while mild over-parameteri","authors_text":"Binghui Li, Han Zhong, Jikai Jin, John E. Hopcroft, Liwei Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T09:53:04Z","title":"Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13863","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a5edb5064979c3dd1f2677c5d00a0f2f6a9c5b01479d4e8eca70050903ffe43f","target":"record","created_at":"2026-07-05T05:06:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"40b31e4d9e3dc255d0862f3d93bc3b0aec8c70218204e7a22fd8368066221b9f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T09:53:04Z","title_canon_sha256":"931708a0d11dfb43f46c2716507e1fd3db7fc1a075e5317d51fb9033ea9f33cf"},"schema_version":"1.0","source":{"id":"2205.13863","kind":"arxiv","version":3}},"canonical_sha256":"83bfed49b777a839464a4cd99c5043f35587c6fa1783f766a55e7523db39eeac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83bfed49b777a839464a4cd99c5043f35587c6fa1783f766a55e7523db39eeac","first_computed_at":"2026-07-05T05:06:31.737133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:31.737133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AwIl7fQ61VGw0OzXfynaudPKgbpLKqnJML+6Nwafk9x7N61zZrx42Ty7tt8d3tOcvZ7mY+NnPsQLp1qfCc89Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:31.737642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.13863","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5edb5064979c3dd1f2677c5d00a0f2f6a9c5b01479d4e8eca70050903ffe43f","sha256:9204277bd153499ff064364f87fbdfa3873c06a8cfb9ca30e3566e0f8e128c26"],"state_sha256":"8d134a5d284bfdcda600bce8cc0fca5cdcf04fead13d71888574c8e5ac6db209"}