{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:Q573JYCJ52GGCTPBQGDJTQYGSM","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":"be8d2428ab8d72b46fddd955f11ba0949d7a659a1b788c3f5d4c99362d180785","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-16T22:01:51Z","title_canon_sha256":"b5dad80c36b046fa48e18b6eea4834b17777d8ec580312ff134145b24b7c22bd"},"schema_version":"1.0","source":{"id":"1906.06784","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.06784","created_at":"2026-07-05T05:08:02Z"},{"alias_kind":"arxiv_version","alias_value":"1906.06784v7","created_at":"2026-07-05T05:08:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06784","created_at":"2026-07-05T05:08:02Z"},{"alias_kind":"pith_short_12","alias_value":"Q573JYCJ52GG","created_at":"2026-07-05T05:08:02Z"},{"alias_kind":"pith_short_16","alias_value":"Q573JYCJ52GGCTPB","created_at":"2026-07-05T05:08:02Z"},{"alias_kind":"pith_short_8","alias_value":"Q573JYCJ","created_at":"2026-07-05T05:08:02Z"}],"graph_snapshots":[{"event_id":"sha256:403c516505995eabaa953b0aba1596380231b91559cdb67cebc1c81dd3574030","target":"graph","created_at":"2026-07-05T05:08:02Z","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/1906.06784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial robustness has become a central goal in deep learning, both in the theory and the practice. However, successful methods to improve the adversarial robustness (such as adversarial training) greatly hurt generalization performance on the unperturbed data. This could have a major impact on how the adversarial robustness affects real world systems (i.e. many may opt to forego robustness if it can improve accuracy on the unperturbed data). We propose Interpolated Adversarial Training, which employs recently proposed interpolation based training methods in the framework of adversarial tr","authors_text":"Alexander Matyasko, Alex Lamb, Juho Kannala, Kenji Kawaguchi, Savya Khosla, Vikas Verma, Yoshua Bengio","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-16T22:01:51Z","title":"Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06784","kind":"arxiv","version":7},"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":"sha256:7ff36c1f407828e847e8ffdf791ebad85b360f3b1b281944893fc5085b304e4a","target":"record","created_at":"2026-07-05T05:08:02Z","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":"be8d2428ab8d72b46fddd955f11ba0949d7a659a1b788c3f5d4c99362d180785","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-16T22:01:51Z","title_canon_sha256":"b5dad80c36b046fa48e18b6eea4834b17777d8ec580312ff134145b24b7c22bd"},"schema_version":"1.0","source":{"id":"1906.06784","kind":"arxiv","version":7}},"canonical_sha256":"877fb4e049ee8c614de1818699c306931fe94d5379e3aa28e70382cb90838b47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"877fb4e049ee8c614de1818699c306931fe94d5379e3aa28e70382cb90838b47","first_computed_at":"2026-07-05T05:08:02.260552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:02.260552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gUsFxAGAEOHvCeg4K5qFswIdKLKbY5vNIj89xqX0c/iFpiaoOsffKV68CCzCo4FYSxE54azSejZHHoNU+II9Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:02.260983Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.06784","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ff36c1f407828e847e8ffdf791ebad85b360f3b1b281944893fc5085b304e4a","sha256:403c516505995eabaa953b0aba1596380231b91559cdb67cebc1c81dd3574030"],"state_sha256":"4f60f24d26a3bb487276438037550481540eb4544d796b746680ab6f8ad5a680"}