{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:66QAS4EMJZB5ZDQEKABTC4AJSC","short_pith_number":"pith:66QAS4EM","schema_version":"1.0","canonical_sha256":"f7a009708c4e43dc8e04500331700990b8f0f8ce51b84050f9c2e526fc0ad852","source":{"kind":"arxiv","id":"2308.00994","version":3},"attestation_state":"computed","paper":{"title":"SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Moon Ye-Bin, Nam Hyeon-Woo, Nayeong Kim, Suha Kwak, Tae-Hyun Oh, Wonseok Choi","submitted_at":"2023-08-02T07:59:25Z","abstract_excerpt":"Data imbalance in training data often leads to biased predictions from trained models, which in turn causes ethical and social issues. A straightforward solution is to carefully curate training data, but given the enormous scale of modern neural networks, this is prohibitively labor-intensive and thus impractical. Inspired by recent developments in generative models, this paper explores the potential of synthetic data to address the data imbalance problem. To be specific, our method, dubbed SYNAuG, leverages synthetic data to equalize the unbalanced distribution of training data. Our experimen"},"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":"2308.00994","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-02T07:59:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1ea71e4bb27e910cc3bbe553245ce64ac64b0e7c17c3751e6d1a48411736ada7","abstract_canon_sha256":"7f7ab0aa5447284df12b2d140bdc6882465aab9071dcf79b5e62993ab889c339"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:53.664486Z","signature_b64":"fvrfk4LirKB+aENGaDsYYs+ef65YoCxiEcHWQQKkac6F5LO2r12u1Fu+Cxx7kM4ZmnaUH2DJgTvV1Kh5ZRzFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7a009708c4e43dc8e04500331700990b8f0f8ce51b84050f9c2e526fc0ad852","last_reissued_at":"2026-07-05T08:11:53.663888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:53.663888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Moon Ye-Bin, Nam Hyeon-Woo, Nayeong Kim, Suha Kwak, Tae-Hyun Oh, Wonseok Choi","submitted_at":"2023-08-02T07:59:25Z","abstract_excerpt":"Data imbalance in training data often leads to biased predictions from trained models, which in turn causes ethical and social issues. A straightforward solution is to carefully curate training data, but given the enormous scale of modern neural networks, this is prohibitively labor-intensive and thus impractical. Inspired by recent developments in generative models, this paper explores the potential of synthetic data to address the data imbalance problem. To be specific, our method, dubbed SYNAuG, leverages synthetic data to equalize the unbalanced distribution of training data. Our experimen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.00994","kind":"arxiv","version":3},"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/2308.00994/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":"2308.00994","created_at":"2026-07-05T08:11:53.663950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.00994v3","created_at":"2026-07-05T08:11:53.663950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.00994","created_at":"2026-07-05T08:11:53.663950+00:00"},{"alias_kind":"pith_short_12","alias_value":"66QAS4EMJZB5","created_at":"2026-07-05T08:11:53.663950+00:00"},{"alias_kind":"pith_short_16","alias_value":"66QAS4EMJZB5ZDQE","created_at":"2026-07-05T08:11:53.663950+00:00"},{"alias_kind":"pith_short_8","alias_value":"66QAS4EM","created_at":"2026-07-05T08:11:53.663950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10088","citing_title":"Towards High Supervised Learning Utility Training Data Generation: Data Pruning and Column Reordering","ref_index":75,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66QAS4EMJZB5ZDQEKABTC4AJSC","json":"https://pith.science/pith/66QAS4EMJZB5ZDQEKABTC4AJSC.json","graph_json":"https://pith.science/api/pith-number/66QAS4EMJZB5ZDQEKABTC4AJSC/graph.json","events_json":"https://pith.science/api/pith-number/66QAS4EMJZB5ZDQEKABTC4AJSC/events.json","paper":"https://pith.science/paper/66QAS4EM"},"agent_actions":{"view_html":"https://pith.science/pith/66QAS4EMJZB5ZDQEKABTC4AJSC","download_json":"https://pith.science/pith/66QAS4EMJZB5ZDQEKABTC4AJSC.json","view_paper":"https://pith.science/paper/66QAS4EM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.00994&json=true","fetch_graph":"https://pith.science/api/pith-number/66QAS4EMJZB5ZDQEKABTC4AJSC/graph.json","fetch_events":"https://pith.science/api/pith-number/66QAS4EMJZB5ZDQEKABTC4AJSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66QAS4EMJZB5ZDQEKABTC4AJSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66QAS4EMJZB5ZDQEKABTC4AJSC/action/storage_attestation","attest_author":"https://pith.science/pith/66QAS4EMJZB5ZDQEKABTC4AJSC/action/author_attestation","sign_citation":"https://pith.science/pith/66QAS4EMJZB5ZDQEKABTC4AJSC/action/citation_signature","submit_replication":"https://pith.science/pith/66QAS4EMJZB5ZDQEKABTC4AJSC/action/replication_record"}},"created_at":"2026-07-05T08:11:53.663950+00:00","updated_at":"2026-07-05T08:11:53.663950+00:00"}