{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DVHYHE3B3MDQMXDWOZ24IVNOL3","short_pith_number":"pith:DVHYHE3B","schema_version":"1.0","canonical_sha256":"1d4f839361db07065c767675c455ae5ec77575588ebcb84aa1d595ad031b8134","source":{"kind":"arxiv","id":"2404.13766","version":1},"attestation_state":"computed","paper":{"title":"Object-Attribute Binding in Text-to-Image Generation: Evaluation and Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jonathan Thomm, Maria Mihaela Trusca, Marie-Francine Moens, Robert Honig, Thomas Hofmann, Tinne Tuytelaars, Wolf Nuyts","submitted_at":"2024-04-21T20:26:46Z","abstract_excerpt":"Current diffusion models create photorealistic images given a text prompt as input but struggle to correctly bind attributes mentioned in the text to the right objects in the image. This is evidenced by our novel image-graph alignment model called EPViT (Edge Prediction Vision Transformer) for the evaluation of image-text alignment. To alleviate the above problem, we propose focused cross-attention (FCA) that controls the visual attention maps by syntactic constraints found in the input sentence. Additionally, the syntax structure of the prompt helps to disentangle the multimodal CLIP embeddin"},"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":"2404.13766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-21T20:26:46Z","cross_cats_sorted":[],"title_canon_sha256":"7c542f772572e80ae0aa22a2b1b39c88bc7c2fa221b77529338a513a8ddce27c","abstract_canon_sha256":"acb96a2f8cca5a0bb14bfa458b17e2d4576962f185258cb7c087806777d885c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:36.891246Z","signature_b64":"jei6yaQ7foZPAePTiOjV4j0LHpWbnvi8BK6JVK9UIXm4muBZ1EtRC+4od7LKSxD+puA4WynT0qyj+uE+OJfKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d4f839361db07065c767675c455ae5ec77575588ebcb84aa1d595ad031b8134","last_reissued_at":"2026-07-05T08:10:36.890878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:36.890878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Object-Attribute Binding in Text-to-Image Generation: Evaluation and Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jonathan Thomm, Maria Mihaela Trusca, Marie-Francine Moens, Robert Honig, Thomas Hofmann, Tinne Tuytelaars, Wolf Nuyts","submitted_at":"2024-04-21T20:26:46Z","abstract_excerpt":"Current diffusion models create photorealistic images given a text prompt as input but struggle to correctly bind attributes mentioned in the text to the right objects in the image. This is evidenced by our novel image-graph alignment model called EPViT (Edge Prediction Vision Transformer) for the evaluation of image-text alignment. To alleviate the above problem, we propose focused cross-attention (FCA) that controls the visual attention maps by syntactic constraints found in the input sentence. Additionally, the syntax structure of the prompt helps to disentangle the multimodal CLIP embeddin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13766","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/2404.13766/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":"2404.13766","created_at":"2026-07-05T08:10:36.890937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13766v1","created_at":"2026-07-05T08:10:36.890937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13766","created_at":"2026-07-05T08:10:36.890937+00:00"},{"alias_kind":"pith_short_12","alias_value":"DVHYHE3B3MDQ","created_at":"2026-07-05T08:10:36.890937+00:00"},{"alias_kind":"pith_short_16","alias_value":"DVHYHE3B3MDQMXDW","created_at":"2026-07-05T08:10:36.890937+00:00"},{"alias_kind":"pith_short_8","alias_value":"DVHYHE3B","created_at":"2026-07-05T08:10:36.890937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30262","citing_title":"Intermediate Text Representation Guided Text-to-Image Generation for Enhancing One-and-Only Alignment","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3","json":"https://pith.science/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3.json","graph_json":"https://pith.science/api/pith-number/DVHYHE3B3MDQMXDWOZ24IVNOL3/graph.json","events_json":"https://pith.science/api/pith-number/DVHYHE3B3MDQMXDWOZ24IVNOL3/events.json","paper":"https://pith.science/paper/DVHYHE3B"},"agent_actions":{"view_html":"https://pith.science/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3","download_json":"https://pith.science/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3.json","view_paper":"https://pith.science/paper/DVHYHE3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13766&json=true","fetch_graph":"https://pith.science/api/pith-number/DVHYHE3B3MDQMXDWOZ24IVNOL3/graph.json","fetch_events":"https://pith.science/api/pith-number/DVHYHE3B3MDQMXDWOZ24IVNOL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3/action/storage_attestation","attest_author":"https://pith.science/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3/action/author_attestation","sign_citation":"https://pith.science/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3/action/citation_signature","submit_replication":"https://pith.science/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3/action/replication_record"}},"created_at":"2026-07-05T08:10:36.890937+00:00","updated_at":"2026-07-05T08:10:36.890937+00:00"}