{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5AOJROYM6B5YJUYA4DSYVT6QQV","short_pith_number":"pith:5AOJROYM","schema_version":"1.0","canonical_sha256":"e81c98bb0cf07b84d300e0e58acfd0856e1bd641bb6f8620a3fe069e2a2437dd","source":{"kind":"arxiv","id":"2508.09550","version":1},"attestation_state":"computed","paper":{"title":"Exploring the Equivalence of Closed-Set Generative and Real Data Augmentation in Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dou Hoon Kwark, Guowei Zhang, Haiyang Xu, Haowen Wang, Xiang Zhang, Zeyuan Chen, Zhuowen Tu","submitted_at":"2025-08-13T07:14:29Z","abstract_excerpt":"In this paper, we address a key scientific problem in machine learning: Given a training set for an image classification task, can we train a generative model on this dataset to enhance the classification performance? (i.e., closed-set generative data augmentation). We start by exploring the distinctions and similarities between real images and closed-set synthetic images generated by advanced generative models. Through extensive experiments, we offer systematic insights into the effective use of closed-set synthetic data for augmentation. Notably, we empirically determine the equivalent scale"},"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":"2508.09550","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-13T07:14:29Z","cross_cats_sorted":[],"title_canon_sha256":"de3256b43d857e17e50157b5cbe3f29c9cf2cbe8aa3f8d5ba1f506cc36ef556e","abstract_canon_sha256":"22745cf8b4ad275992cb22f04b34b5ee978a63416d91125cf627bb251648be78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:16.997446Z","signature_b64":"wEdVrc3TeD6upep11IGzi9LTj1hfXYkBk8SspJGGZMi4/kUqglzO+iXJSPsDmHL7eymf5nasGeQCCamg6yfoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e81c98bb0cf07b84d300e0e58acfd0856e1bd641bb6f8620a3fe069e2a2437dd","last_reissued_at":"2026-07-05T11:53:16.996977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:16.996977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring the Equivalence of Closed-Set Generative and Real Data Augmentation in Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dou Hoon Kwark, Guowei Zhang, Haiyang Xu, Haowen Wang, Xiang Zhang, Zeyuan Chen, Zhuowen Tu","submitted_at":"2025-08-13T07:14:29Z","abstract_excerpt":"In this paper, we address a key scientific problem in machine learning: Given a training set for an image classification task, can we train a generative model on this dataset to enhance the classification performance? (i.e., closed-set generative data augmentation). We start by exploring the distinctions and similarities between real images and closed-set synthetic images generated by advanced generative models. Through extensive experiments, we offer systematic insights into the effective use of closed-set synthetic data for augmentation. Notably, we empirically determine the equivalent scale"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09550","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/2508.09550/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":"2508.09550","created_at":"2026-07-05T11:53:16.997050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09550v1","created_at":"2026-07-05T11:53:16.997050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09550","created_at":"2026-07-05T11:53:16.997050+00:00"},{"alias_kind":"pith_short_12","alias_value":"5AOJROYM6B5Y","created_at":"2026-07-05T11:53:16.997050+00:00"},{"alias_kind":"pith_short_16","alias_value":"5AOJROYM6B5YJUYA","created_at":"2026-07-05T11:53:16.997050+00:00"},{"alias_kind":"pith_short_8","alias_value":"5AOJROYM","created_at":"2026-07-05T11:53:16.997050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21291","citing_title":"Exploring the Role of Synthetic Data Augmentation in Controllable Human-Centric Video Generation","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5AOJROYM6B5YJUYA4DSYVT6QQV","json":"https://pith.science/pith/5AOJROYM6B5YJUYA4DSYVT6QQV.json","graph_json":"https://pith.science/api/pith-number/5AOJROYM6B5YJUYA4DSYVT6QQV/graph.json","events_json":"https://pith.science/api/pith-number/5AOJROYM6B5YJUYA4DSYVT6QQV/events.json","paper":"https://pith.science/paper/5AOJROYM"},"agent_actions":{"view_html":"https://pith.science/pith/5AOJROYM6B5YJUYA4DSYVT6QQV","download_json":"https://pith.science/pith/5AOJROYM6B5YJUYA4DSYVT6QQV.json","view_paper":"https://pith.science/paper/5AOJROYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09550&json=true","fetch_graph":"https://pith.science/api/pith-number/5AOJROYM6B5YJUYA4DSYVT6QQV/graph.json","fetch_events":"https://pith.science/api/pith-number/5AOJROYM6B5YJUYA4DSYVT6QQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5AOJROYM6B5YJUYA4DSYVT6QQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5AOJROYM6B5YJUYA4DSYVT6QQV/action/storage_attestation","attest_author":"https://pith.science/pith/5AOJROYM6B5YJUYA4DSYVT6QQV/action/author_attestation","sign_citation":"https://pith.science/pith/5AOJROYM6B5YJUYA4DSYVT6QQV/action/citation_signature","submit_replication":"https://pith.science/pith/5AOJROYM6B5YJUYA4DSYVT6QQV/action/replication_record"}},"created_at":"2026-07-05T11:53:16.997050+00:00","updated_at":"2026-07-05T11:53:16.997050+00:00"}