{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KRSYR2ESIQI7AC6OVK7N2BBD5W","short_pith_number":"pith:KRSYR2ES","schema_version":"1.0","canonical_sha256":"546588e8924411f00bceaabedd0423ed83577e36c29e043ca296297e02f3b2da","source":{"kind":"arxiv","id":"2606.20924","version":1},"attestation_state":"computed","paper":{"title":"ELDiff: When Evidential Learning Meets Text-to-Image Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Ji, Kai Ye, Qingtao Pan, Shuo Li, Zhihao Dou","submitted_at":"2026-06-18T20:33:20Z","abstract_excerpt":"In multi-object text-to-image (T2I) diffusion, ensuring semantic consistency between textual prompts and generated visual content is crucial for image synthesis. However, such consistency constraint is often underemphasized in the denoising process of diffusion models. Although token supervised diffusion models can mitigate this issue by learning object-wise consistency between the image content and object segmentation maps, it tends to suffer from the problems of segmentation map bias and semantic overlap conflict, especially when involving multiple objects. In this paper, we propose ELDiff, "},"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":"2606.20924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T20:33:20Z","cross_cats_sorted":[],"title_canon_sha256":"d5b493ba928f8d0d24d4e67b2a3993e7b55c896214f79631ba3b03699a2f4129","abstract_canon_sha256":"2ece2fcce1a16db0d137c6b8f4d757b0da7a9178255c7ddaf9f5b5388f987a13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:22.202022Z","signature_b64":"BVe9tY71waHcRPMi5ao/omEtdxsUKk5aKcJZnENOkQsqLl1lL6yNIopnl2GXDp0ZJQKkXhJJzM7hHz/8sjFWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"546588e8924411f00bceaabedd0423ed83577e36c29e043ca296297e02f3b2da","last_reissued_at":"2026-06-23T01:12:22.201495Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:22.201495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ELDiff: When Evidential Learning Meets Text-to-Image Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Ji, Kai Ye, Qingtao Pan, Shuo Li, Zhihao Dou","submitted_at":"2026-06-18T20:33:20Z","abstract_excerpt":"In multi-object text-to-image (T2I) diffusion, ensuring semantic consistency between textual prompts and generated visual content is crucial for image synthesis. However, such consistency constraint is often underemphasized in the denoising process of diffusion models. Although token supervised diffusion models can mitigate this issue by learning object-wise consistency between the image content and object segmentation maps, it tends to suffer from the problems of segmentation map bias and semantic overlap conflict, especially when involving multiple objects. In this paper, we propose ELDiff, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20924","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/2606.20924/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":"2606.20924","created_at":"2026-06-23T01:12:22.201565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20924v1","created_at":"2026-06-23T01:12:22.201565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20924","created_at":"2026-06-23T01:12:22.201565+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRSYR2ESIQI7","created_at":"2026-06-23T01:12:22.201565+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRSYR2ESIQI7AC6O","created_at":"2026-06-23T01:12:22.201565+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRSYR2ES","created_at":"2026-06-23T01:12:22.201565+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KRSYR2ESIQI7AC6OVK7N2BBD5W","json":"https://pith.science/pith/KRSYR2ESIQI7AC6OVK7N2BBD5W.json","graph_json":"https://pith.science/api/pith-number/KRSYR2ESIQI7AC6OVK7N2BBD5W/graph.json","events_json":"https://pith.science/api/pith-number/KRSYR2ESIQI7AC6OVK7N2BBD5W/events.json","paper":"https://pith.science/paper/KRSYR2ES"},"agent_actions":{"view_html":"https://pith.science/pith/KRSYR2ESIQI7AC6OVK7N2BBD5W","download_json":"https://pith.science/pith/KRSYR2ESIQI7AC6OVK7N2BBD5W.json","view_paper":"https://pith.science/paper/KRSYR2ES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20924&json=true","fetch_graph":"https://pith.science/api/pith-number/KRSYR2ESIQI7AC6OVK7N2BBD5W/graph.json","fetch_events":"https://pith.science/api/pith-number/KRSYR2ESIQI7AC6OVK7N2BBD5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRSYR2ESIQI7AC6OVK7N2BBD5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRSYR2ESIQI7AC6OVK7N2BBD5W/action/storage_attestation","attest_author":"https://pith.science/pith/KRSYR2ESIQI7AC6OVK7N2BBD5W/action/author_attestation","sign_citation":"https://pith.science/pith/KRSYR2ESIQI7AC6OVK7N2BBD5W/action/citation_signature","submit_replication":"https://pith.science/pith/KRSYR2ESIQI7AC6OVK7N2BBD5W/action/replication_record"}},"created_at":"2026-06-23T01:12:22.201565+00:00","updated_at":"2026-06-23T01:12:22.201565+00:00"}