{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W7YOSSCQBAAQOPTJ3D5GKBBKLG","short_pith_number":"pith:W7YOSSCQ","schema_version":"1.0","canonical_sha256":"b7f0e948500801073e69d8fa65042a59b70bc3e0389d3bdf106bc48cc95ea9b9","source":{"kind":"arxiv","id":"2406.07844","version":2},"attestation_state":"computed","paper":{"title":"Improving Compositional Attribute Binding in Text-to-Image Generative Models via Enhanced Text Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arman Zarei, Keivan Rezaei, Mazda Moayeri, Mehrdad Saberi, Priyatham Kattakinda, Samyadeep Basu, Soheil Feizi","submitted_at":"2024-06-12T03:21:34Z","abstract_excerpt":"Text-to-image diffusion-based generative models have the stunning ability to generate photo-realistic images and achieve state-of-the-art low FID scores on challenging image generation benchmarks. However, one of the primary failure modes of these text-to-image generative models is in composing attributes, objects, and their associated relationships accurately into an image. In our paper, we investigate compositional attribute binding failures, where the model fails to correctly associate descriptive attributes (such as color, shape, or texture) with the corresponding objects in the generated "},"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":"2406.07844","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T03:21:34Z","cross_cats_sorted":[],"title_canon_sha256":"a7efdcbbc7dfb4f719094330ac8c8cd4911e7953b8132c7e2daba2d025279b5b","abstract_canon_sha256":"63fe976431db118cbd562806ec44a6b233cd1d68b020e83303095078b344373c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:34.111138Z","signature_b64":"Dkk/OvUYERxu+jYc6FtLxM08OerOUQorBNdhG/mtGReLr+/qWryZvrefk79fwsj5987uCgzWAZaqRXAxSczFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7f0e948500801073e69d8fa65042a59b70bc3e0389d3bdf106bc48cc95ea9b9","last_reissued_at":"2026-07-05T10:38:34.110684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:34.110684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Compositional Attribute Binding in Text-to-Image Generative Models via Enhanced Text Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arman Zarei, Keivan Rezaei, Mazda Moayeri, Mehrdad Saberi, Priyatham Kattakinda, Samyadeep Basu, Soheil Feizi","submitted_at":"2024-06-12T03:21:34Z","abstract_excerpt":"Text-to-image diffusion-based generative models have the stunning ability to generate photo-realistic images and achieve state-of-the-art low FID scores on challenging image generation benchmarks. However, one of the primary failure modes of these text-to-image generative models is in composing attributes, objects, and their associated relationships accurately into an image. In our paper, we investigate compositional attribute binding failures, where the model fails to correctly associate descriptive attributes (such as color, shape, or texture) with the corresponding objects in the generated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07844","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/2406.07844/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":"2406.07844","created_at":"2026-07-05T10:38:34.110732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07844v2","created_at":"2026-07-05T10:38:34.110732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07844","created_at":"2026-07-05T10:38:34.110732+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7YOSSCQBAAQ","created_at":"2026-07-05T10:38:34.110732+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7YOSSCQBAAQOPTJ","created_at":"2026-07-05T10:38:34.110732+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7YOSSCQ","created_at":"2026-07-05T10:38:34.110732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.15357","citing_title":"MaskAttn-SDXL: Controllable Region-Level Text-To-Image Generation","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W7YOSSCQBAAQOPTJ3D5GKBBKLG","json":"https://pith.science/pith/W7YOSSCQBAAQOPTJ3D5GKBBKLG.json","graph_json":"https://pith.science/api/pith-number/W7YOSSCQBAAQOPTJ3D5GKBBKLG/graph.json","events_json":"https://pith.science/api/pith-number/W7YOSSCQBAAQOPTJ3D5GKBBKLG/events.json","paper":"https://pith.science/paper/W7YOSSCQ"},"agent_actions":{"view_html":"https://pith.science/pith/W7YOSSCQBAAQOPTJ3D5GKBBKLG","download_json":"https://pith.science/pith/W7YOSSCQBAAQOPTJ3D5GKBBKLG.json","view_paper":"https://pith.science/paper/W7YOSSCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07844&json=true","fetch_graph":"https://pith.science/api/pith-number/W7YOSSCQBAAQOPTJ3D5GKBBKLG/graph.json","fetch_events":"https://pith.science/api/pith-number/W7YOSSCQBAAQOPTJ3D5GKBBKLG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7YOSSCQBAAQOPTJ3D5GKBBKLG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7YOSSCQBAAQOPTJ3D5GKBBKLG/action/storage_attestation","attest_author":"https://pith.science/pith/W7YOSSCQBAAQOPTJ3D5GKBBKLG/action/author_attestation","sign_citation":"https://pith.science/pith/W7YOSSCQBAAQOPTJ3D5GKBBKLG/action/citation_signature","submit_replication":"https://pith.science/pith/W7YOSSCQBAAQOPTJ3D5GKBBKLG/action/replication_record"}},"created_at":"2026-07-05T10:38:34.110732+00:00","updated_at":"2026-07-05T10:38:34.110732+00:00"}