{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7AYROEZ2HFRXZPAAF4NV2K2FJK","short_pith_number":"pith:7AYROEZ2","schema_version":"1.0","canonical_sha256":"f83117133a39637cbc002f1b5d2b454aae36cdf74c7163f0d5b4933a6567ecaa","source":{"kind":"arxiv","id":"2308.04018","version":1},"attestation_state":"computed","paper":{"title":"Improving Performance of Semi-Supervised Learning by Adversarial Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongyoon Yang, Kunwoong Kim, Yongdai Kim","submitted_at":"2023-08-08T03:29:43Z","abstract_excerpt":"Semi-supervised learning (SSL) algorithm is a setup built upon a realistic assumption that access to a large amount of labeled data is tough. In this study, we present a generalized framework, named SCAR, standing for Selecting Clean samples with Adversarial Robustness, for improving the performance of recent SSL algorithms. By adversarially attacking pre-trained models with semi-supervision, our framework shows substantial advances in classifying images. We introduce how adversarial attacks successfully select high-confident unlabeled data to be labeled with current predictions. On CIFAR10, t"},"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":"2308.04018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-08T03:29:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d4f5a1baf547e6427ce6ee7c4e2454b94aa8789414a199ea3f70aecd268fb051","abstract_canon_sha256":"661a0b10f3f18c0ab19a9c632c12be2e4f65dd0c0315d2169f6a8be4a2d50c8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:21.044242Z","signature_b64":"xGXT8HchRBgz+VNTq+6XXT8km0RqC0LoPkg5jnEHlipFCKrmaAvRRFnldaq403U1CfsDxJnIdbruY5gEAA6HCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f83117133a39637cbc002f1b5d2b454aae36cdf74c7163f0d5b4933a6567ecaa","last_reissued_at":"2026-07-05T06:39:21.043676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:21.043676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Performance of Semi-Supervised Learning by Adversarial Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongyoon Yang, Kunwoong Kim, Yongdai Kim","submitted_at":"2023-08-08T03:29:43Z","abstract_excerpt":"Semi-supervised learning (SSL) algorithm is a setup built upon a realistic assumption that access to a large amount of labeled data is tough. In this study, we present a generalized framework, named SCAR, standing for Selecting Clean samples with Adversarial Robustness, for improving the performance of recent SSL algorithms. By adversarially attacking pre-trained models with semi-supervision, our framework shows substantial advances in classifying images. We introduce how adversarial attacks successfully select high-confident unlabeled data to be labeled with current predictions. On CIFAR10, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04018","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2308.04018/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2308.04018","created_at":"2026-07-05T06:39:21.043732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.04018v1","created_at":"2026-07-05T06:39:21.043732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04018","created_at":"2026-07-05T06:39:21.043732+00:00"},{"alias_kind":"pith_short_12","alias_value":"7AYROEZ2HFRX","created_at":"2026-07-05T06:39:21.043732+00:00"},{"alias_kind":"pith_short_16","alias_value":"7AYROEZ2HFRXZPAA","created_at":"2026-07-05T06:39:21.043732+00:00"},{"alias_kind":"pith_short_8","alias_value":"7AYROEZ2","created_at":"2026-07-05T06:39:21.043732+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/7AYROEZ2HFRXZPAAF4NV2K2FJK","json":"https://pith.science/pith/7AYROEZ2HFRXZPAAF4NV2K2FJK.json","graph_json":"https://pith.science/api/pith-number/7AYROEZ2HFRXZPAAF4NV2K2FJK/graph.json","events_json":"https://pith.science/api/pith-number/7AYROEZ2HFRXZPAAF4NV2K2FJK/events.json","paper":"https://pith.science/paper/7AYROEZ2"},"agent_actions":{"view_html":"https://pith.science/pith/7AYROEZ2HFRXZPAAF4NV2K2FJK","download_json":"https://pith.science/pith/7AYROEZ2HFRXZPAAF4NV2K2FJK.json","view_paper":"https://pith.science/paper/7AYROEZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.04018&json=true","fetch_graph":"https://pith.science/api/pith-number/7AYROEZ2HFRXZPAAF4NV2K2FJK/graph.json","fetch_events":"https://pith.science/api/pith-number/7AYROEZ2HFRXZPAAF4NV2K2FJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7AYROEZ2HFRXZPAAF4NV2K2FJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7AYROEZ2HFRXZPAAF4NV2K2FJK/action/storage_attestation","attest_author":"https://pith.science/pith/7AYROEZ2HFRXZPAAF4NV2K2FJK/action/author_attestation","sign_citation":"https://pith.science/pith/7AYROEZ2HFRXZPAAF4NV2K2FJK/action/citation_signature","submit_replication":"https://pith.science/pith/7AYROEZ2HFRXZPAAF4NV2K2FJK/action/replication_record"}},"created_at":"2026-07-05T06:39:21.043732+00:00","updated_at":"2026-07-05T06:39:21.043732+00:00"}