{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IT64VSFABVUSUVF3PNUYDIWZOX","short_pith_number":"pith:IT64VSFA","schema_version":"1.0","canonical_sha256":"44fdcac8a00d692a54bb7b6981a2d975d99123b79cac29c9fbfcbeca2ecdb3af","source":{"kind":"arxiv","id":"1711.09681","version":2},"attestation_state":"computed","paper":{"title":"Butterfly Effect: Bidirectional Control of Classification Performance by Small Additive Perturbation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junyoung Choi, Nojun Kwak, Sangdoo Yun, Seonguk Park, Youngjoon Yoo","submitted_at":"2017-11-27T13:32:45Z","abstract_excerpt":"This paper proposes a new algorithm for controlling classification results by generating a small additive perturbation without changing the classifier network. Our work is inspired by existing works generating adversarial perturbation that worsens classification performance. In contrast to the existing methods, our work aims to generate perturbations that can enhance overall classification performance. To solve this performance enhancement problem, we newly propose a perturbation generation network (PGN) influenced by the adversarial learning strategy. In our problem, the information in a larg"},"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":"1711.09681","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-27T13:32:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ff3822e94fb6fb809ca3212f1712a71bce936689ad8af615423bb1982baaa8c2","abstract_canon_sha256":"c25b6a97511b0b36b3a420bdbbd5618f5866b0c43ab8b0312285b845e0d73a18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:00.857543Z","signature_b64":"diOCBth9kmEkbRw953332rE9ITqCjwm9pmtc6qiVdbdR04KxjRf46RfDSqQXjlUkKQnf/uDxZMURWEiIH9DtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44fdcac8a00d692a54bb7b6981a2d975d99123b79cac29c9fbfcbeca2ecdb3af","last_reissued_at":"2026-05-18T00:29:00.857041Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:00.857041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Butterfly Effect: Bidirectional Control of Classification Performance by Small Additive Perturbation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junyoung Choi, Nojun Kwak, Sangdoo Yun, Seonguk Park, Youngjoon Yoo","submitted_at":"2017-11-27T13:32:45Z","abstract_excerpt":"This paper proposes a new algorithm for controlling classification results by generating a small additive perturbation without changing the classifier network. Our work is inspired by existing works generating adversarial perturbation that worsens classification performance. In contrast to the existing methods, our work aims to generate perturbations that can enhance overall classification performance. To solve this performance enhancement problem, we newly propose a perturbation generation network (PGN) influenced by the adversarial learning strategy. In our problem, the information in a larg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.09681","kind":"arxiv","version":2},"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":"1711.09681","created_at":"2026-05-18T00:29:00.857121+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.09681v2","created_at":"2026-05-18T00:29:00.857121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.09681","created_at":"2026-05-18T00:29:00.857121+00:00"},{"alias_kind":"pith_short_12","alias_value":"IT64VSFABVUS","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IT64VSFABVUSUVF3","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IT64VSFA","created_at":"2026-05-18T12:31:21.493067+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/IT64VSFABVUSUVF3PNUYDIWZOX","json":"https://pith.science/pith/IT64VSFABVUSUVF3PNUYDIWZOX.json","graph_json":"https://pith.science/api/pith-number/IT64VSFABVUSUVF3PNUYDIWZOX/graph.json","events_json":"https://pith.science/api/pith-number/IT64VSFABVUSUVF3PNUYDIWZOX/events.json","paper":"https://pith.science/paper/IT64VSFA"},"agent_actions":{"view_html":"https://pith.science/pith/IT64VSFABVUSUVF3PNUYDIWZOX","download_json":"https://pith.science/pith/IT64VSFABVUSUVF3PNUYDIWZOX.json","view_paper":"https://pith.science/paper/IT64VSFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.09681&json=true","fetch_graph":"https://pith.science/api/pith-number/IT64VSFABVUSUVF3PNUYDIWZOX/graph.json","fetch_events":"https://pith.science/api/pith-number/IT64VSFABVUSUVF3PNUYDIWZOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IT64VSFABVUSUVF3PNUYDIWZOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IT64VSFABVUSUVF3PNUYDIWZOX/action/storage_attestation","attest_author":"https://pith.science/pith/IT64VSFABVUSUVF3PNUYDIWZOX/action/author_attestation","sign_citation":"https://pith.science/pith/IT64VSFABVUSUVF3PNUYDIWZOX/action/citation_signature","submit_replication":"https://pith.science/pith/IT64VSFABVUSUVF3PNUYDIWZOX/action/replication_record"}},"created_at":"2026-05-18T00:29:00.857121+00:00","updated_at":"2026-05-18T00:29:00.857121+00:00"}