{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YBH7LGBZL6DEGO37MPAPEJKTC5","short_pith_number":"pith:YBH7LGBZ","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"},"canonical_sha256":"c04ff598395f86433b7f63c0f225531765bf86282b24593a928700d7eeef0a74","source":{"kind":"arxiv","id":"2503.13730","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13730","created_at":"2026-07-05T10:33:17Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13730v1","created_at":"2026-07-05T10:33:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13730","created_at":"2026-07-05T10:33:17Z"},{"alias_kind":"pith_short_12","alias_value":"YBH7LGBZL6DE","created_at":"2026-07-05T10:33:17Z"},{"alias_kind":"pith_short_16","alias_value":"YBH7LGBZL6DEGO37","created_at":"2026-07-05T10:33:17Z"},{"alias_kind":"pith_short_8","alias_value":"YBH7LGBZ","created_at":"2026-07-05T10:33:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YBH7LGBZL6DEGO37MPAPEJKTC5","target":"record","payload":{"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"},"canonical_sha256":"c04ff598395f86433b7f63c0f225531765bf86282b24593a928700d7eeef0a74","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"},"source_kind":"arxiv","source_id":"2503.13730","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":"2026-07-05T10:33:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zQFE76r+q4FPmCFJ6s0afYSVpoQYZrutvEjvaAM22M7ldfE8RPA7EBfqJa7CHwQysWrJEWyav/8rVT3aZCYsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:25:08.336342Z"},"content_sha256":"83faa7044c5296142e9840960a85728e75e8ad9697d51aeef4c53b85e055952a","schema_version":"1.0","event_id":"sha256:83faa7044c5296142e9840960a85728e75e8ad9697d51aeef4c53b85e055952a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YBH7LGBZL6DEGO37MPAPEJKTC5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:33:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YTwAGRrsv8pxctC/NEpM1ZJ3OG0X/oresHAB+iJjHKmng4KOQsBMAQBGAjsgK596IiFUzti9E3IqKyYm+nKABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:25:08.337634Z"},"content_sha256":"e9d43a3f2f24cb90d4fd246f51645d2f0de2c257a792b6e2c9cc57cb576b3ddb","schema_version":"1.0","event_id":"sha256:e9d43a3f2f24cb90d4fd246f51645d2f0de2c257a792b6e2c9cc57cb576b3ddb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YBH7LGBZL6DEGO37MPAPEJKTC5/bundle.json","state_url":"https://pith.science/pith/YBH7LGBZL6DEGO37MPAPEJKTC5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YBH7LGBZL6DEGO37MPAPEJKTC5/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":"2026-08-18T14:25:08Z","links":{"resolver":"https://pith.science/pith/YBH7LGBZL6DEGO37MPAPEJKTC5","bundle":"https://pith.science/pith/YBH7LGBZL6DEGO37MPAPEJKTC5/bundle.json","state":"https://pith.science/pith/YBH7LGBZL6DEGO37MPAPEJKTC5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YBH7LGBZL6DEGO37MPAPEJKTC5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YBH7LGBZL6DEGO37MPAPEJKTC5","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":"e8af41e1e93731952a348a0a606534be97b501f2b840157f4e8fd79aeb1e0e73","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T21:36:31Z","title_canon_sha256":"38f9fc5c20d03c5db79982a13725c291b0d22cb5908204058c4d418b8a217735"},"schema_version":"1.0","source":{"id":"2503.13730","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13730","created_at":"2026-07-05T10:33:17Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13730v1","created_at":"2026-07-05T10:33:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13730","created_at":"2026-07-05T10:33:17Z"},{"alias_kind":"pith_short_12","alias_value":"YBH7LGBZL6DE","created_at":"2026-07-05T10:33:17Z"},{"alias_kind":"pith_short_16","alias_value":"YBH7LGBZL6DEGO37","created_at":"2026-07-05T10:33:17Z"},{"alias_kind":"pith_short_8","alias_value":"YBH7LGBZ","created_at":"2026-07-05T10:33:17Z"}],"graph_snapshots":[{"event_id":"sha256:e9d43a3f2f24cb90d4fd246f51645d2f0de2c257a792b6e2c9cc57cb576b3ddb","target":"graph","created_at":"2026-07-05T10:33:17Z","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/2503.13730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Agneet Chatterjee, Chitta Baral, Forouzan Fallah, Maitreya Patel, Vlad I. Morariu, Yezhou Yang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T21:36:31Z","title":"TextInVision: Text and Prompt Complexity Driven Visual Text Generation Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13730","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":"sha256:83faa7044c5296142e9840960a85728e75e8ad9697d51aeef4c53b85e055952a","target":"record","created_at":"2026-07-05T10:33:17Z","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":"e8af41e1e93731952a348a0a606534be97b501f2b840157f4e8fd79aeb1e0e73","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T21:36:31Z","title_canon_sha256":"38f9fc5c20d03c5db79982a13725c291b0d22cb5908204058c4d418b8a217735"},"schema_version":"1.0","source":{"id":"2503.13730","kind":"arxiv","version":1}},"canonical_sha256":"c04ff598395f86433b7f63c0f225531765bf86282b24593a928700d7eeef0a74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c04ff598395f86433b7f63c0f225531765bf86282b24593a928700d7eeef0a74","first_computed_at":"2026-07-05T10:33:17.024095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:17.024095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W+WB/YBdBx0qWMHwoOfjXB5o0lCoWIbd+FFUFOE694RIgWiEBCIfIkMiG01xoHkRL94+RxhK/6eYvHcGXzw2DA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:17.025472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13730","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83faa7044c5296142e9840960a85728e75e8ad9697d51aeef4c53b85e055952a","sha256:e9d43a3f2f24cb90d4fd246f51645d2f0de2c257a792b6e2c9cc57cb576b3ddb"],"state_sha256":"7f98486304e84d658f848d4e41c6d4e5c38f874a4d96bb772260677df264dd51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JJjzmHZTamd8Tx7izB8NpN0VuyMzxkWmf2ohWCzFtpGwVAhYyrPzoJXnNcXZFHLJlL/Lp2VINz3MDLH0Ks/yBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T14:25:08.347198Z","bundle_sha256":"754c43675ac239d5263618e0934103ea0682c2f0a6c5872e1208a745ad2640ed"}}