{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YBH7LGBZL6DEGO37MPAPEJKTC5","short_pith_number":"pith:YBH7LGBZ","schema_version":"1.0","canonical_sha256":"c04ff598395f86433b7f63c0f225531765bf86282b24593a928700d7eeef0a74","source":{"kind":"arxiv","id":"2503.13730","version":1},"attestation_state":"computed","paper":{"title":"TextInVision: Text and Prompt Complexity Driven Visual Text Generation Benchmark","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Agneet Chatterjee, Chitta Baral, Forouzan Fallah, Maitreya Patel, Vlad I. Morariu, Yezhou Yang","submitted_at":"2025-03-17T21:36:31Z","abstract_excerpt":"Generating images with embedded text is crucial for the automatic production of visual and multimodal documents, such as educational materials and advertisements. However, existing diffusion-based text-to-image models often struggle to accurately embed text within images, facing challenges in spelling accuracy, contextual relevance, and visual coherence. Evaluating the ability of such models to embed text within a generated image is complicated due to the lack of comprehensive benchmarks. In this work, we introduce TextInVision, a large-scale, text and prompt complexity driven benchmark design"},"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":"2503.13730","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T21:36:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"38f9fc5c20d03c5db79982a13725c291b0d22cb5908204058c4d418b8a217735","abstract_canon_sha256":"e8af41e1e93731952a348a0a606534be97b501f2b840157f4e8fd79aeb1e0e73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:17.025472Z","signature_b64":"W+WB/YBdBx0qWMHwoOfjXB5o0lCoWIbd+FFUFOE694RIgWiEBCIfIkMiG01xoHkRL94+RxhK/6eYvHcGXzw2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c04ff598395f86433b7f63c0f225531765bf86282b24593a928700d7eeef0a74","last_reissued_at":"2026-07-05T10:33:17.024095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:17.024095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextInVision: Text and Prompt Complexity Driven Visual Text Generation Benchmark","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Agneet Chatterjee, Chitta Baral, Forouzan Fallah, Maitreya Patel, Vlad I. Morariu, Yezhou Yang","submitted_at":"2025-03-17T21:36:31Z","abstract_excerpt":"Generating images with embedded text is crucial for the automatic production of visual and multimodal documents, such as educational materials and advertisements. However, existing diffusion-based text-to-image models often struggle to accurately embed text within images, facing challenges in spelling accuracy, contextual relevance, and visual coherence. Evaluating the ability of such models to embed text within a generated image is complicated due to the lack of comprehensive benchmarks. In this work, we introduce TextInVision, a large-scale, text and prompt complexity driven benchmark design"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13730","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/2503.13730/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":"2503.13730","created_at":"2026-07-05T10:33:17.024290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13730v1","created_at":"2026-07-05T10:33:17.024290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13730","created_at":"2026-07-05T10:33:17.024290+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBH7LGBZL6DE","created_at":"2026-07-05T10:33:17.024290+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBH7LGBZL6DEGO37","created_at":"2026-07-05T10:33:17.024290+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBH7LGBZ","created_at":"2026-07-05T10:33:17.024290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19708","citing_title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YBH7LGBZL6DEGO37MPAPEJKTC5","json":"https://pith.science/pith/YBH7LGBZL6DEGO37MPAPEJKTC5.json","graph_json":"https://pith.science/api/pith-number/YBH7LGBZL6DEGO37MPAPEJKTC5/graph.json","events_json":"https://pith.science/api/pith-number/YBH7LGBZL6DEGO37MPAPEJKTC5/events.json","paper":"https://pith.science/paper/YBH7LGBZ"},"agent_actions":{"view_html":"https://pith.science/pith/YBH7LGBZL6DEGO37MPAPEJKTC5","download_json":"https://pith.science/pith/YBH7LGBZL6DEGO37MPAPEJKTC5.json","view_paper":"https://pith.science/paper/YBH7LGBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13730&json=true","fetch_graph":"https://pith.science/api/pith-number/YBH7LGBZL6DEGO37MPAPEJKTC5/graph.json","fetch_events":"https://pith.science/api/pith-number/YBH7LGBZL6DEGO37MPAPEJKTC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBH7LGBZL6DEGO37MPAPEJKTC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBH7LGBZL6DEGO37MPAPEJKTC5/action/storage_attestation","attest_author":"https://pith.science/pith/YBH7LGBZL6DEGO37MPAPEJKTC5/action/author_attestation","sign_citation":"https://pith.science/pith/YBH7LGBZL6DEGO37MPAPEJKTC5/action/citation_signature","submit_replication":"https://pith.science/pith/YBH7LGBZL6DEGO37MPAPEJKTC5/action/replication_record"}},"created_at":"2026-07-05T10:33:17.024290+00:00","updated_at":"2026-07-05T10:33:17.024290+00:00"}