{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WC4ME6L3WNH4XVYEBH6GBJR7IX","short_pith_number":"pith:WC4ME6L3","schema_version":"1.0","canonical_sha256":"b0b8c2797bb34fcbd70409fc60a63f45d2d5b90b8df66fc4391c71d7f1817ee8","source":{"kind":"arxiv","id":"2305.00562","version":2},"attestation_state":"computed","paper":{"title":"Class-Balancing Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Huangjie Zheng, Jiangchao Yao, Mingyuan Zhou, Ya Zhang, Yiming Qin","submitted_at":"2023-04-30T20:00:14Z","abstract_excerpt":"Diffusion-based models have shown the merits of generating high-quality visual data while preserving better diversity in recent studies. However, such observation is only justified with curated data distribution, where the data samples are nicely pre-processed to be uniformly distributed in terms of their labels. In practice, a long-tailed data distribution appears more common and how diffusion models perform on such class-imbalanced data remains unknown. In this work, we first investigate this problem and observe significant degradation in both diversity and fidelity when the diffusion model "},"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":"2305.00562","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-30T20:00:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e57456455f53f0c8cc928118c2280149d90e89b5de46323f2a0e564bc2bed671","abstract_canon_sha256":"aa0692201d53a731bb495c0177965a144a04a2f99ec048d258af9b674e4fbe19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:43.432111Z","signature_b64":"b7iMZMLlkTmIFj95XkqzpJrWFlu8XByy2gIPHl/IbZZF3nEOtPPUg/bVEpjJItPhiKmGR3MIT1VDqd+/I/8UDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0b8c2797bb34fcbd70409fc60a63f45d2d5b90b8df66fc4391c71d7f1817ee8","last_reissued_at":"2026-07-05T06:20:43.431638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:43.431638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class-Balancing Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Huangjie Zheng, Jiangchao Yao, Mingyuan Zhou, Ya Zhang, Yiming Qin","submitted_at":"2023-04-30T20:00:14Z","abstract_excerpt":"Diffusion-based models have shown the merits of generating high-quality visual data while preserving better diversity in recent studies. However, such observation is only justified with curated data distribution, where the data samples are nicely pre-processed to be uniformly distributed in terms of their labels. In practice, a long-tailed data distribution appears more common and how diffusion models perform on such class-imbalanced data remains unknown. In this work, we first investigate this problem and observe significant degradation in both diversity and fidelity when the diffusion model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00562","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/2305.00562/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":"2305.00562","created_at":"2026-07-05T06:20:43.431694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.00562v2","created_at":"2026-07-05T06:20:43.431694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00562","created_at":"2026-07-05T06:20:43.431694+00:00"},{"alias_kind":"pith_short_12","alias_value":"WC4ME6L3WNH4","created_at":"2026-07-05T06:20:43.431694+00:00"},{"alias_kind":"pith_short_16","alias_value":"WC4ME6L3WNH4XVYE","created_at":"2026-07-05T06:20:43.431694+00:00"},{"alias_kind":"pith_short_8","alias_value":"WC4ME6L3","created_at":"2026-07-05T06:20:43.431694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.04749","citing_title":"Mitigating Long-Tail Bias via Prompt-Controlled Diffusion Augmentation","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WC4ME6L3WNH4XVYEBH6GBJR7IX","json":"https://pith.science/pith/WC4ME6L3WNH4XVYEBH6GBJR7IX.json","graph_json":"https://pith.science/api/pith-number/WC4ME6L3WNH4XVYEBH6GBJR7IX/graph.json","events_json":"https://pith.science/api/pith-number/WC4ME6L3WNH4XVYEBH6GBJR7IX/events.json","paper":"https://pith.science/paper/WC4ME6L3"},"agent_actions":{"view_html":"https://pith.science/pith/WC4ME6L3WNH4XVYEBH6GBJR7IX","download_json":"https://pith.science/pith/WC4ME6L3WNH4XVYEBH6GBJR7IX.json","view_paper":"https://pith.science/paper/WC4ME6L3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.00562&json=true","fetch_graph":"https://pith.science/api/pith-number/WC4ME6L3WNH4XVYEBH6GBJR7IX/graph.json","fetch_events":"https://pith.science/api/pith-number/WC4ME6L3WNH4XVYEBH6GBJR7IX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WC4ME6L3WNH4XVYEBH6GBJR7IX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WC4ME6L3WNH4XVYEBH6GBJR7IX/action/storage_attestation","attest_author":"https://pith.science/pith/WC4ME6L3WNH4XVYEBH6GBJR7IX/action/author_attestation","sign_citation":"https://pith.science/pith/WC4ME6L3WNH4XVYEBH6GBJR7IX/action/citation_signature","submit_replication":"https://pith.science/pith/WC4ME6L3WNH4XVYEBH6GBJR7IX/action/replication_record"}},"created_at":"2026-07-05T06:20:43.431694+00:00","updated_at":"2026-07-05T06:20:43.431694+00:00"}