{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:M4DU7GC3QESG44ABEJ6D57XYCI","short_pith_number":"pith:M4DU7GC3","schema_version":"1.0","canonical_sha256":"67074f985b81246e7001227c3efef8121b2b8deda7cdcd1b4cbbcd4a61993b25","source":{"kind":"arxiv","id":"2310.12583","version":1},"attestation_state":"computed","paper":{"title":"Diverse Diffusion: Enhancing Image Diversity in Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Laurent Najman (LIGM), Mariia Zameshina (LIGM), Olivier Teytaud (TAU)","submitted_at":"2023-10-19T08:48:23Z","abstract_excerpt":"Latent diffusion models excel at producing high-quality images from text. Yet, concerns appear about the lack of diversity in the generated imagery. To tackle this, we introduce Diverse Diffusion, a method for boosting image diversity beyond gender and ethnicity, spanning into richer realms, including color diversity.Diverse Diffusion is a general unsupervised technique that can be applied to existing text-to-image models. Our approach focuses on finding vectors in the Stable Diffusion latent space that are distant from each other. We generate multiple vectors in the latent space until we find"},"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":"2310.12583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-19T08:48:23Z","cross_cats_sorted":[],"title_canon_sha256":"e3fcff019ccb5d48baf264a189a1649ba6c9c3b0f847a5369d72d5cddccb31cc","abstract_canon_sha256":"61d036c7e85a2b392d0a9bf051421a8fbb0ec81251d1cb928ef4b1cb8405a8d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:40.135742Z","signature_b64":"hh5MhSv65ROoSXKy9+7bON22+EhVdpMeMksUPrBgEICM1qfi5caxMABb3jGytuoQE3uBF5AguhXnokbPxAICBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67074f985b81246e7001227c3efef8121b2b8deda7cdcd1b4cbbcd4a61993b25","last_reissued_at":"2026-07-05T07:02:40.135330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:40.135330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diverse Diffusion: Enhancing Image Diversity in Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Laurent Najman (LIGM), Mariia Zameshina (LIGM), Olivier Teytaud (TAU)","submitted_at":"2023-10-19T08:48:23Z","abstract_excerpt":"Latent diffusion models excel at producing high-quality images from text. Yet, concerns appear about the lack of diversity in the generated imagery. To tackle this, we introduce Diverse Diffusion, a method for boosting image diversity beyond gender and ethnicity, spanning into richer realms, including color diversity.Diverse Diffusion is a general unsupervised technique that can be applied to existing text-to-image models. Our approach focuses on finding vectors in the Stable Diffusion latent space that are distant from each other. We generate multiple vectors in the latent space until we find"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12583","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/2310.12583/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":"2310.12583","created_at":"2026-07-05T07:02:40.135388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.12583v1","created_at":"2026-07-05T07:02:40.135388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12583","created_at":"2026-07-05T07:02:40.135388+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4DU7GC3QESG","created_at":"2026-07-05T07:02:40.135388+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4DU7GC3QESG44AB","created_at":"2026-07-05T07:02:40.135388+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4DU7GC3","created_at":"2026-07-05T07:02:40.135388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11311","citing_title":"Couple to Control: Joint Initial Noise Design in Diffusion Models","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17323","citing_title":"A Universal Avoidance Method for Diverse Multi-branch Generation","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M4DU7GC3QESG44ABEJ6D57XYCI","json":"https://pith.science/pith/M4DU7GC3QESG44ABEJ6D57XYCI.json","graph_json":"https://pith.science/api/pith-number/M4DU7GC3QESG44ABEJ6D57XYCI/graph.json","events_json":"https://pith.science/api/pith-number/M4DU7GC3QESG44ABEJ6D57XYCI/events.json","paper":"https://pith.science/paper/M4DU7GC3"},"agent_actions":{"view_html":"https://pith.science/pith/M4DU7GC3QESG44ABEJ6D57XYCI","download_json":"https://pith.science/pith/M4DU7GC3QESG44ABEJ6D57XYCI.json","view_paper":"https://pith.science/paper/M4DU7GC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.12583&json=true","fetch_graph":"https://pith.science/api/pith-number/M4DU7GC3QESG44ABEJ6D57XYCI/graph.json","fetch_events":"https://pith.science/api/pith-number/M4DU7GC3QESG44ABEJ6D57XYCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4DU7GC3QESG44ABEJ6D57XYCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4DU7GC3QESG44ABEJ6D57XYCI/action/storage_attestation","attest_author":"https://pith.science/pith/M4DU7GC3QESG44ABEJ6D57XYCI/action/author_attestation","sign_citation":"https://pith.science/pith/M4DU7GC3QESG44ABEJ6D57XYCI/action/citation_signature","submit_replication":"https://pith.science/pith/M4DU7GC3QESG44ABEJ6D57XYCI/action/replication_record"}},"created_at":"2026-07-05T07:02:40.135388+00:00","updated_at":"2026-07-05T07:02:40.135388+00:00"}