{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZDOEJ2YE4PA4YLLHKYXDVSVMPZ","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":"614d4a639384a08f26db276db1b5a7d8bc8220a302641172b65f6952c66f382f","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-02T17:47:58Z","title_canon_sha256":"45471e4284a4779e05c508bf77035b96a498fcc5176f2bdd811355f761ab962b"},"schema_version":"1.0","source":{"id":"2103.01895","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.01895","created_at":"2026-07-05T03:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2103.01895v3","created_at":"2026-07-05T03:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.01895","created_at":"2026-07-05T03:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"ZDOEJ2YE4PA4","created_at":"2026-07-05T03:38:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZDOEJ2YE4PA4YLLH","created_at":"2026-07-05T03:38:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZDOEJ2YE","created_at":"2026-07-05T03:38:59Z"}],"graph_snapshots":[{"event_id":"sha256:17fbcd3913c8f46cc9f880d914edbe3bb012514c6aac6b9a4249bc6bf8fd65c8","target":"graph","created_at":"2026-07-05T03:38:59Z","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/2103.01895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial examples causing evasive predictions are widely used to evaluate and improve the robustness of machine learning models. However, current studies focus on supervised learning tasks, relying on the ground-truth data label, a targeted objective, or supervision from a trained classifier. In this paper, we propose a framework of generating adversarial examples for unsupervised models and demonstrate novel applications to data augmentation. Our framework exploits a mutual information neural estimator as an information-theoretic similarity measure to generate adversarial examples without ","authors_text":"Chia-Mu Yu, Chia-Yi Hsu, Pin-Yu Chen, Sijia Liu, Songtao Lu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-02T17:47:58Z","title":"Adversarial Examples can be Effective Data Augmentation for Unsupervised Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.01895","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:c9e6ffcb1d49cbed70fbf44817ce0d4e457a7b02e91c0233c0ef13b9963746fc","target":"record","created_at":"2026-07-05T03:38:59Z","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":"614d4a639384a08f26db276db1b5a7d8bc8220a302641172b65f6952c66f382f","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-02T17:47:58Z","title_canon_sha256":"45471e4284a4779e05c508bf77035b96a498fcc5176f2bdd811355f761ab962b"},"schema_version":"1.0","source":{"id":"2103.01895","kind":"arxiv","version":3}},"canonical_sha256":"c8dc44eb04e3c1cc2d67562e3acaac7e4d9488a6637fe787c601d78508ad0898","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8dc44eb04e3c1cc2d67562e3acaac7e4d9488a6637fe787c601d78508ad0898","first_computed_at":"2026-07-05T03:38:59.392021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:38:59.392021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XQXMG9UYEEwE2aK08uPd2IzxYpQrgX+D899ibZ3htgD/vCowFVwnnleN3blgKCGf2amnJAFlhJTIgki84r2ACg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:38:59.392374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.01895","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9e6ffcb1d49cbed70fbf44817ce0d4e457a7b02e91c0233c0ef13b9963746fc","sha256:17fbcd3913c8f46cc9f880d914edbe3bb012514c6aac6b9a4249bc6bf8fd65c8"],"state_sha256":"32a356af2c6fc6a393708ef3da4c4deae06857752b789cf80431c8117269ebc8"}