{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MQ5E3IKHJMOHSSWJGZV63KBUIJ","short_pith_number":"pith:MQ5E3IKH","schema_version":"1.0","canonical_sha256":"643a4da1474b1c794ac9366beda8344251c29bf23c1188c04b86de58abad8851","source":{"kind":"arxiv","id":"1902.11019","version":1},"attestation_state":"computed","paper":{"title":"Towards Understanding Adversarial Examples Systematically: Exploring Data Size, Task and Model Factors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ke Sun, Zhanxing Zhu, Zhouchen Lin","submitted_at":"2019-02-28T11:14:45Z","abstract_excerpt":"Most previous works usually explained adversarial examples from several specific perspectives, lacking relatively integral comprehension about this problem. In this paper, we present a systematic study on adversarial examples from three aspects: the amount of training data, task-dependent and model-specific factors. Particularly, we show that adversarial generalization (i.e. test accuracy on adversarial examples) for standard training requires more data than standard generalization (i.e. test accuracy on clean examples); and uncover the global relationship between generalization and robustness"},"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":"1902.11019","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-28T11:14:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6d1f7448571fe00d79b0cf5fcc6baec0e087646880e1961782a81b55ba5d13b2","abstract_canon_sha256":"afd6ae3d0c03771716190cd13739205ea3113a1b77db0cdec64f076063e058b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:26.029311Z","signature_b64":"nkvjxnmDEoZeSvI5X35n4E5cfD4YWuD4jJ5eN7D5hfEdSQwja8E2yO5zfgt+6m/BmvbdkHx13WzA29lwQpJmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"643a4da1474b1c794ac9366beda8344251c29bf23c1188c04b86de58abad8851","last_reissued_at":"2026-05-17T23:52:26.028661Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:26.028661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Understanding Adversarial Examples Systematically: Exploring Data Size, Task and Model Factors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ke Sun, Zhanxing Zhu, Zhouchen Lin","submitted_at":"2019-02-28T11:14:45Z","abstract_excerpt":"Most previous works usually explained adversarial examples from several specific perspectives, lacking relatively integral comprehension about this problem. In this paper, we present a systematic study on adversarial examples from three aspects: the amount of training data, task-dependent and model-specific factors. Particularly, we show that adversarial generalization (i.e. test accuracy on adversarial examples) for standard training requires more data than standard generalization (i.e. test accuracy on clean examples); and uncover the global relationship between generalization and robustness"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.11019","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":""},"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":"1902.11019","created_at":"2026-05-17T23:52:26.028790+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.11019v1","created_at":"2026-05-17T23:52:26.028790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.11019","created_at":"2026-05-17T23:52:26.028790+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQ5E3IKHJMOH","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQ5E3IKHJMOHSSWJ","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQ5E3IKH","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.01560","citing_title":"GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attacks","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQ5E3IKHJMOHSSWJGZV63KBUIJ","json":"https://pith.science/pith/MQ5E3IKHJMOHSSWJGZV63KBUIJ.json","graph_json":"https://pith.science/api/pith-number/MQ5E3IKHJMOHSSWJGZV63KBUIJ/graph.json","events_json":"https://pith.science/api/pith-number/MQ5E3IKHJMOHSSWJGZV63KBUIJ/events.json","paper":"https://pith.science/paper/MQ5E3IKH"},"agent_actions":{"view_html":"https://pith.science/pith/MQ5E3IKHJMOHSSWJGZV63KBUIJ","download_json":"https://pith.science/pith/MQ5E3IKHJMOHSSWJGZV63KBUIJ.json","view_paper":"https://pith.science/paper/MQ5E3IKH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.11019&json=true","fetch_graph":"https://pith.science/api/pith-number/MQ5E3IKHJMOHSSWJGZV63KBUIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/MQ5E3IKHJMOHSSWJGZV63KBUIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQ5E3IKHJMOHSSWJGZV63KBUIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQ5E3IKHJMOHSSWJGZV63KBUIJ/action/storage_attestation","attest_author":"https://pith.science/pith/MQ5E3IKHJMOHSSWJGZV63KBUIJ/action/author_attestation","sign_citation":"https://pith.science/pith/MQ5E3IKHJMOHSSWJGZV63KBUIJ/action/citation_signature","submit_replication":"https://pith.science/pith/MQ5E3IKHJMOHSSWJGZV63KBUIJ/action/replication_record"}},"created_at":"2026-05-17T23:52:26.028790+00:00","updated_at":"2026-05-17T23:52:26.028790+00:00"}