diff --git a/olmocr/bench/sample_data/dataset.jsonl b/olmocr/bench/sample_data/dataset.jsonl index 4986402..d3ea5eb 100644 --- a/olmocr/bench/sample_data/dataset.jsonl +++ b/olmocr/bench/sample_data/dataset.jsonl @@ -84,3 +84,7 @@ {"pdf": "math_2503_04086.pdf", "page": 1, "id": "math_2503_04086_03", "type": "math", "math": "\\lambda_{g}=\\sum_{i=1}^{k} c\\left(g, R / \\operatorname{Ann}_{R}\\left(x_{i}\\right)\\right)"} {"pdf": "math_2503_04086.pdf", "page": 1, "id": "math_2503_04086_04", "type": "present", "text": "We also thank Ján Mináč for his constant encouragement and support."} {"pdf": "math_2503_04086.pdf", "page": 1, "id": "math_2503_04086_05", "type": "present", "text": "Allgemeine theorie der Gaußschen Summen in endlichen kommutativen Ringe"} + +{"pdf": "test-graphical-text.pdf", "page": 1, "id": "test_graphical_text_00", "type": "present", "text": "THE VISION"} +{"pdf": "test-graphical-text.pdf", "page": 1, "id": "test_graphical_text_01", "type": "present", "text": "by FutureSkill"} +{"pdf": "test-graphical-text.pdf", "page": 1, "id": "test_graphical_text_02", "type": "present", "text": "THE POWER OF STORYTELLING"} diff --git a/olmocr/bench/sample_data/pdfs/test-graphical-text.pdf b/olmocr/bench/sample_data/pdfs/test-graphical-text.pdf new file mode 100644 index 0000000..a120efc Binary files /dev/null and b/olmocr/bench/sample_data/pdfs/test-graphical-text.pdf differ