{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DVHYHE3B3MDQMXDWOZ24IVNOL3","short_pith_number":"pith:DVHYHE3B","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"},"canonical_sha256":"1d4f839361db07065c767675c455ae5ec77575588ebcb84aa1d595ad031b8134","source":{"kind":"arxiv","id":"2404.13766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.13766","created_at":"2026-07-05T08:10:36Z"},{"alias_kind":"arxiv_version","alias_value":"2404.13766v1","created_at":"2026-07-05T08:10:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13766","created_at":"2026-07-05T08:10:36Z"},{"alias_kind":"pith_short_12","alias_value":"DVHYHE3B3MDQ","created_at":"2026-07-05T08:10:36Z"},{"alias_kind":"pith_short_16","alias_value":"DVHYHE3B3MDQMXDW","created_at":"2026-07-05T08:10:36Z"},{"alias_kind":"pith_short_8","alias_value":"DVHYHE3B","created_at":"2026-07-05T08:10:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DVHYHE3B3MDQMXDWOZ24IVNOL3","target":"record","payload":{"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"},"canonical_sha256":"1d4f839361db07065c767675c455ae5ec77575588ebcb84aa1d595ad031b8134","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"},"source_kind":"arxiv","source_id":"2404.13766","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:10:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"25nVdse2Mek1MtRQKrHlfqPIPSRpgZxs1Ox03u/ezxn2voIFX40gPiDfU6zOvskJ7T7ac64Yxp9cTWipy1XgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:24:29.932809Z"},"content_sha256":"3138bb3feb85ea4cd66522ba8e9ccec7dfc9d508e3a585dcc9ea672290df6ca9","schema_version":"1.0","event_id":"sha256:3138bb3feb85ea4cd66522ba8e9ccec7dfc9d508e3a585dcc9ea672290df6ca9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DVHYHE3B3MDQMXDWOZ24IVNOL3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:10:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q43NqISgzP46ksdYWtL8fopckHjBCH6q4j4EjrUIxIbn646B59FqVSEpXB5yESgF4Bun+s9x/fOn6fi5dNQOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:24:29.933760Z"},"content_sha256":"1f1991cfb63191753db1f9b713f0745eb4fe5247392e09fa2d0043fae44821e4","schema_version":"1.0","event_id":"sha256:1f1991cfb63191753db1f9b713f0745eb4fe5247392e09fa2d0043fae44821e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3/bundle.json","state_url":"https://pith.science/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T17:24:29Z","links":{"resolver":"https://pith.science/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3","bundle":"https://pith.science/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3/bundle.json","state":"https://pith.science/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DVHYHE3B3MDQMXDWOZ24IVNOL3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DVHYHE3B3MDQMXDWOZ24IVNOL3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"acb96a2f8cca5a0bb14bfa458b17e2d4576962f185258cb7c087806777d885c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-21T20:26:46Z","title_canon_sha256":"7c542f772572e80ae0aa22a2b1b39c88bc7c2fa221b77529338a513a8ddce27c"},"schema_version":"1.0","source":{"id":"2404.13766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.13766","created_at":"2026-07-05T08:10:36Z"},{"alias_kind":"arxiv_version","alias_value":"2404.13766v1","created_at":"2026-07-05T08:10:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13766","created_at":"2026-07-05T08:10:36Z"},{"alias_kind":"pith_short_12","alias_value":"DVHYHE3B3MDQ","created_at":"2026-07-05T08:10:36Z"},{"alias_kind":"pith_short_16","alias_value":"DVHYHE3B3MDQMXDW","created_at":"2026-07-05T08:10:36Z"},{"alias_kind":"pith_short_8","alias_value":"DVHYHE3B","created_at":"2026-07-05T08:10:36Z"}],"graph_snapshots":[{"event_id":"sha256:1f1991cfb63191753db1f9b713f0745eb4fe5247392e09fa2d0043fae44821e4","target":"graph","created_at":"2026-07-05T08:10:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.13766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jonathan Thomm, Maria Mihaela Trusca, Marie-Francine Moens, Robert Honig, Thomas Hofmann, Tinne Tuytelaars, Wolf Nuyts","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-21T20:26:46Z","title":"Object-Attribute Binding in Text-to-Image Generation: Evaluation and Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13766","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3138bb3feb85ea4cd66522ba8e9ccec7dfc9d508e3a585dcc9ea672290df6ca9","target":"record","created_at":"2026-07-05T08:10:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"acb96a2f8cca5a0bb14bfa458b17e2d4576962f185258cb7c087806777d885c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-21T20:26:46Z","title_canon_sha256":"7c542f772572e80ae0aa22a2b1b39c88bc7c2fa221b77529338a513a8ddce27c"},"schema_version":"1.0","source":{"id":"2404.13766","kind":"arxiv","version":1}},"canonical_sha256":"1d4f839361db07065c767675c455ae5ec77575588ebcb84aa1d595ad031b8134","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d4f839361db07065c767675c455ae5ec77575588ebcb84aa1d595ad031b8134","first_computed_at":"2026-07-05T08:10:36.890878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:36.890878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jei6yaQ7foZPAePTiOjV4j0LHpWbnvi8BK6JVK9UIXm4muBZ1EtRC+4od7LKSxD+puA4WynT0qyj+uE+OJfKAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:36.891246Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.13766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3138bb3feb85ea4cd66522ba8e9ccec7dfc9d508e3a585dcc9ea672290df6ca9","sha256:1f1991cfb63191753db1f9b713f0745eb4fe5247392e09fa2d0043fae44821e4"],"state_sha256":"30a9adb7676c1d551145b70e2dab8c24b633c68ce1169a9c405e062f82836125"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3SHSAqzyz4+P47ZmlZzMHDoioxBEgqg7vV4L955WQveEB3iK3AxLJYtKWUZoAmWOgweJ1lv0GbiEF3EaGpDFAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:24:29.941266Z","bundle_sha256":"7f8c367e63926243566663cf26f5a0e97a6acfccdfe83ef32f284e857c7917ad"}}