{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JTOIO3S2AXCKOQ4GPRSK34BFRY","short_pith_number":"pith:JTOIO3S2","schema_version":"1.0","canonical_sha256":"4cdc876e5a05c4a743867c64adf0258e1956dd9c89924175633b46bac3ea8de7","source":{"kind":"arxiv","id":"2403.00570","version":2},"attestation_state":"computed","paper":{"title":"Rethinking cluster-conditioned diffusion models for label-free image synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Felix Michels, Markus Kollmann, Nikolas Adaloglou, Tim Kaiser","submitted_at":"2024-03-01T14:47:46Z","abstract_excerpt":"Diffusion-based image generation models can enhance image quality when conditioned on ground truth labels. Here, we conduct a comprehensive experimental study on image-level conditioning for diffusion models using cluster assignments. We investigate how individual clustering determinants, such as the number of clusters and the clustering method, impact image synthesis across three different datasets. Given the optimal number of clusters with respect to image synthesis, we show that cluster-conditioning can achieve state-of-the-art performance, with an FID of 1.67 for CIFAR10 and 2.17 for CIFAR"},"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":"2403.00570","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T14:47:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b6135127a27296b1fab47318c47a9ad33acdf04a736909cb3387ffe9c2a12fd6","abstract_canon_sha256":"8b05c2eb09a2c62afaa6115184c012edd389b28275f63c0c176434f9fa58bba5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:07.143135Z","signature_b64":"Vu4SQdat29IyIILN5gzO72hGdFQq9BFXQvdONVyfL9rGVB+QMCMYZdci8L0TMrukgA4g8r9Fee8L/9zVPiIbCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cdc876e5a05c4a743867c64adf0258e1956dd9c89924175633b46bac3ea8de7","last_reissued_at":"2026-07-05T09:37:07.142666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:07.142666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking cluster-conditioned diffusion models for label-free image synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Felix Michels, Markus Kollmann, Nikolas Adaloglou, Tim Kaiser","submitted_at":"2024-03-01T14:47:46Z","abstract_excerpt":"Diffusion-based image generation models can enhance image quality when conditioned on ground truth labels. Here, we conduct a comprehensive experimental study on image-level conditioning for diffusion models using cluster assignments. We investigate how individual clustering determinants, such as the number of clusters and the clustering method, impact image synthesis across three different datasets. Given the optimal number of clusters with respect to image synthesis, we show that cluster-conditioning can achieve state-of-the-art performance, with an FID of 1.67 for CIFAR10 and 2.17 for CIFAR"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00570","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/2403.00570/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":"2403.00570","created_at":"2026-07-05T09:37:07.142724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00570v2","created_at":"2026-07-05T09:37:07.142724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00570","created_at":"2026-07-05T09:37:07.142724+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTOIO3S2AXCK","created_at":"2026-07-05T09:37:07.142724+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTOIO3S2AXCKOQ4G","created_at":"2026-07-05T09:37:07.142724+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTOIO3S2","created_at":"2026-07-05T09:37:07.142724+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.13419","citing_title":"Diffusion Models Memorize in Training -- and Generalize in Inference","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTOIO3S2AXCKOQ4GPRSK34BFRY","json":"https://pith.science/pith/JTOIO3S2AXCKOQ4GPRSK34BFRY.json","graph_json":"https://pith.science/api/pith-number/JTOIO3S2AXCKOQ4GPRSK34BFRY/graph.json","events_json":"https://pith.science/api/pith-number/JTOIO3S2AXCKOQ4GPRSK34BFRY/events.json","paper":"https://pith.science/paper/JTOIO3S2"},"agent_actions":{"view_html":"https://pith.science/pith/JTOIO3S2AXCKOQ4GPRSK34BFRY","download_json":"https://pith.science/pith/JTOIO3S2AXCKOQ4GPRSK34BFRY.json","view_paper":"https://pith.science/paper/JTOIO3S2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00570&json=true","fetch_graph":"https://pith.science/api/pith-number/JTOIO3S2AXCKOQ4GPRSK34BFRY/graph.json","fetch_events":"https://pith.science/api/pith-number/JTOIO3S2AXCKOQ4GPRSK34BFRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTOIO3S2AXCKOQ4GPRSK34BFRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTOIO3S2AXCKOQ4GPRSK34BFRY/action/storage_attestation","attest_author":"https://pith.science/pith/JTOIO3S2AXCKOQ4GPRSK34BFRY/action/author_attestation","sign_citation":"https://pith.science/pith/JTOIO3S2AXCKOQ4GPRSK34BFRY/action/citation_signature","submit_replication":"https://pith.science/pith/JTOIO3S2AXCKOQ4GPRSK34BFRY/action/replication_record"}},"created_at":"2026-07-05T09:37:07.142724+00:00","updated_at":"2026-07-05T09:37:07.142724+00:00"}