{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XEN4OKIOB3B24RTGO2E3AZXSM4","short_pith_number":"pith:XEN4OKIO","schema_version":"1.0","canonical_sha256":"b91bc7290e0ec3ae46667689b066f267184928c5c45b0d72d2164fbdbcc4f29d","source":{"kind":"arxiv","id":"2504.07426","version":2},"attestation_state":"computed","paper":{"title":"Conditional Data Synthesis Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Xiaotong Shen, Xinyu Tian","submitted_at":"2025-04-10T03:38:11Z","abstract_excerpt":"Reliable machine learning and statistical analysis rely on diverse, well-distributed training data. However, real-world datasets are often limited in size and exhibit underrepresentation across key subpopulations, leading to biased predictions and reduced performance, particularly in supervised tasks such as classification. To address these challenges, we propose Conditional Data Synthesis Augmentation (CoDSA), a novel framework that leverages generative models, such as diffusion models, to synthesize high-fidelity data for improving model performance across multimodal domains including tabula"},"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":"2504.07426","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-04-10T03:38:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c630494fe3bb809ff864f75b21a61f70dc2e5f8a786145f4a419bb3a081da3e7","abstract_canon_sha256":"de1a51ba10da8e213d91148ff60b4745d0c0e3a91e14dd1570805e637fea6273"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:30.572311Z","signature_b64":"smkIA20bL1gfpJaQeMXsxrPU9d6ID18S4WDFFAFPOcB9FY2rai88OWR6u20O+xK+Vl51gCg8Fcys3LR1nh4bAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b91bc7290e0ec3ae46667689b066f267184928c5c45b0d72d2164fbdbcc4f29d","last_reissued_at":"2026-07-05T11:36:30.571841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:30.571841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional Data Synthesis Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Xiaotong Shen, Xinyu Tian","submitted_at":"2025-04-10T03:38:11Z","abstract_excerpt":"Reliable machine learning and statistical analysis rely on diverse, well-distributed training data. However, real-world datasets are often limited in size and exhibit underrepresentation across key subpopulations, leading to biased predictions and reduced performance, particularly in supervised tasks such as classification. To address these challenges, we propose Conditional Data Synthesis Augmentation (CoDSA), a novel framework that leverages generative models, such as diffusion models, to synthesize high-fidelity data for improving model performance across multimodal domains including tabula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07426","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.07426/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":"2504.07426","created_at":"2026-07-05T11:36:30.571897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07426v2","created_at":"2026-07-05T11:36:30.571897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07426","created_at":"2026-07-05T11:36:30.571897+00:00"},{"alias_kind":"pith_short_12","alias_value":"XEN4OKIOB3B2","created_at":"2026-07-05T11:36:30.571897+00:00"},{"alias_kind":"pith_short_16","alias_value":"XEN4OKIOB3B24RTG","created_at":"2026-07-05T11:36:30.571897+00:00"},{"alias_kind":"pith_short_8","alias_value":"XEN4OKIO","created_at":"2026-07-05T11:36:30.571897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26053","citing_title":"When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XEN4OKIOB3B24RTGO2E3AZXSM4","json":"https://pith.science/pith/XEN4OKIOB3B24RTGO2E3AZXSM4.json","graph_json":"https://pith.science/api/pith-number/XEN4OKIOB3B24RTGO2E3AZXSM4/graph.json","events_json":"https://pith.science/api/pith-number/XEN4OKIOB3B24RTGO2E3AZXSM4/events.json","paper":"https://pith.science/paper/XEN4OKIO"},"agent_actions":{"view_html":"https://pith.science/pith/XEN4OKIOB3B24RTGO2E3AZXSM4","download_json":"https://pith.science/pith/XEN4OKIOB3B24RTGO2E3AZXSM4.json","view_paper":"https://pith.science/paper/XEN4OKIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07426&json=true","fetch_graph":"https://pith.science/api/pith-number/XEN4OKIOB3B24RTGO2E3AZXSM4/graph.json","fetch_events":"https://pith.science/api/pith-number/XEN4OKIOB3B24RTGO2E3AZXSM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XEN4OKIOB3B24RTGO2E3AZXSM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XEN4OKIOB3B24RTGO2E3AZXSM4/action/storage_attestation","attest_author":"https://pith.science/pith/XEN4OKIOB3B24RTGO2E3AZXSM4/action/author_attestation","sign_citation":"https://pith.science/pith/XEN4OKIOB3B24RTGO2E3AZXSM4/action/citation_signature","submit_replication":"https://pith.science/pith/XEN4OKIOB3B24RTGO2E3AZXSM4/action/replication_record"}},"created_at":"2026-07-05T11:36:30.571897+00:00","updated_at":"2026-07-05T11:36:30.571897+00:00"}