{ "metrics_doc": { "prose_recall": "truth 段落按 '. ' 切句，归一化后 ≥4 词的句子在输出中出现的比例", "reading_order": "每段前 6 词作锚点在输出中的位置，相邻段对位置严格递增的比例；锚点缺失计 0", "table_rows_intact": "truth 每行，存在某条输出行包含该行所有单元格字符串的比例", "table_header_intact": "leaf_header（无则 header）全部单元格出现在同一输出行：1 或 0；只测叶子单元格同行，不测跨列分组语义；doc 类样本有多张表/工作表时为满足该条件的表所占比例", "table_pipe_detected": "输出是否含 markdown 表格（| 开头结尾行且下一行为分隔行）：true/false", "pages_covered": "mixed 的 page_anchors 各自出现在输出中的比例；第三个锚点在扫描页，无 OCR 时上限 2/3", "scan_text_recall": "scan 文本按 prose_recall 口径的召回；无 OCR 预期为 0", "equation_recall": "expressions 经数学标记归一化（去 $ / \\[ \\] 定界、\\mathsf{} 等字体包裹、\\{ → {、^{\\wedge} → ^、\\_ → _、去全部空白）后子串命中的比例；对所有工具同一口径，衡量数学内容是否可恢复而非输出格式", "equation_recall_exact": "expressions 仅做大小写/空白归一化的纯文本精确子串命中比例（旧口径，保留作对照：输出 LaTeX 标记的路径在此列必然偏低）", "heading_recall": "doc 类：truth 标题文字出现在某条以 # 开头的输出行里的比例（不论级别）", "heading_level_exact": "doc 类：truth 标题以恰好 level 个 # 输出的比例；truth level 为空的标题（幻灯片标题、EPUB 章名）不计入", "list_items_intact": "doc 类：truth 列表项（含幻灯片要点）出现在以 - * + 或 数字. 数字) 开头的输出行里的比例", "code_block_intact": "doc 类：truth 代码块的每一行都出现在 ``` / ~~~ 围栏内的比例（按块计）", "boilerplate_excluded": "doc 类：导航、标语、Cookie 横幅、页脚等样板字符串没有出现在输出中的比例；越高说明正文抽取越干净", "slide_order": "doc 类：幻灯片标题按 reading_order 口径（前 6 词锚点）相邻对位置严格递增的比例", "notes_recall": "doc 类：幻灯片演讲者备注全文出现在输出中的比例", "sheet_coverage": "doc 类：至少有一行数据按 table_rows_intact 口径完整出现的工作表所占比例", "elapsed_s": "lab_run 实测耗时（秒），透传", "error": "lab_run 记录的异常文本，透传；无异常为 null" }, "tools": { "markovo": { "version": "2026-09-19.v3-media-unified", "device": null, "elapsed_s": 0.0, "error": null }, "pandoc": { "version": "3.11", "device": "cpu", "elapsed_s": 0.0, "error": null, "skipped": [ "deck", "equation", "mixed", "prose-single", "rotated-header", "scan-image", "sheet", "table-merged-header", "table-simple", "two-column" ] }, "docling": { "version": "2.133.0", "device": "mps", "elapsed_s": 0.0, "error": null, "skipped": [ "book" ] }, "marker": { "version": "2.0.0", "device": "mps", "elapsed_s": 0.0, "error": null, "skipped": [ "article", "book", "deck", "report", "sheet" ] }, "markitdown": { "version": "0.1.8", "device": "cpu", "elapsed_s": 0.1875, "error": null }, "pymupdf4llm": { "version": "1.28.2", "device": "cpu", "elapsed_s": 1.3969, "error": null } }, "python": "3.11.14", "date": "2026-10-18", "cells": [ { "tool": "pandoc", "sample": "article", "kind": "doc", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": 1.0, "heading_level_exact": 1.0, "list_items_intact": null, "code_block_intact": 1.0, "boilerplate_excluded": 1.0, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "pandoc", "sample": "book", "kind": "doc", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": 1.0, "heading_level_exact": null, "list_items_intact": 1.0, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "pandoc", "sample": "report", "kind": "doc", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": 1.0, "heading_level_exact": 1.0, "list_items_intact": 1.0, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "docling", "sample": "article", "kind": "doc", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": 1.0, "heading_level_exact": 1.0, "list_items_intact": null, "code_block_intact": 1.0, "boilerplate_excluded": 1.0, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "docling", "sample": "deck", "kind": "doc", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": 1.0, "heading_level_exact": null, "list_items_intact": 1.0, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": 1.0, "notes_recall": 0.0, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "docling", "sample": "equation", "kind": "equation", "prose_recall": null, "reading_order": null, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": 1.0, "equation_recall_exact": 0.75, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "docling", "sample": "mixed", "kind": "mixed", "prose_recall": 1.0, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": 0.6667, "scan_text_recall": 0.0, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "docling", "sample": "prose-single", "kind": "prose", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "docling", "sample": "report", "kind": "doc", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": 1.0, "heading_level_exact": 0.0, "list_items_intact": 1.0, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "docling", "sample": "rotated-header", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "docling", "sample": "scan-image", "kind": "scan", "prose_recall": null, "reading_order": null, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": 0.0, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "docling", "sample": "sheet", "kind": "doc", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": 1.0, "elapsed_s": 0.0, "error": null }, { "tool": "docling", "sample": "table-merged-header", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "docling", "sample": "table-simple", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "docling", "sample": "two-column", "kind": "columns", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "marker", "sample": "equation", "kind": "equation", "prose_recall": null, "reading_order": null, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": 1.0, "equation_recall_exact": 0.75, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "marker", "sample": "mixed", "kind": "mixed", "prose_recall": 1.0, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": 1.0, "scan_text_recall": 1.0, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "marker", "sample": "prose-single", "kind": "prose", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "marker", "sample": "rotated-header", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "marker", "sample": "scan-image", "kind": "scan", "prose_recall": null, "reading_order": null, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": 1.0, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "marker", "sample": "table-merged-header", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "marker", "sample": "table-simple", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "marker", "sample": "two-column", "kind": "columns", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "markovo", "sample": "article", "kind": "doc", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": 1.0, "heading_level_exact": 1.0, "list_items_intact": null, "code_block_intact": 1.0, "boilerplate_excluded": 1.0, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "markovo", "sample": "book", "kind": "doc", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": 1.0, "heading_level_exact": null, "list_items_intact": 1.0, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "markovo", "sample": "deck", "kind": "doc", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": 1.0, "heading_level_exact": null, "list_items_intact": 0.0, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": 1.0, "notes_recall": 1.0, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "markovo", "sample": "equation", "kind": "equation", "prose_recall": null, "reading_order": null, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": 0.5, "equation_recall_exact": 0.0, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "markovo", "sample": "mixed", "kind": "mixed", "prose_recall": 1.0, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": false, "pages_covered": 1.0, "scan_text_recall": 1.0, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "markovo", "sample": "prose-single", "kind": "prose", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "markovo", "sample": "report", "kind": "doc", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": 1.0, "heading_level_exact": 1.0, "list_items_intact": 1.0, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "markovo", "sample": "rotated-header", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": false, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "markovo", "sample": "scan-image", "kind": "scan", "prose_recall": null, "reading_order": null, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": 1.0, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "markovo", "sample": "sheet", "kind": "doc", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": 1.0, "elapsed_s": 0.0, "error": null }, { "tool": "markovo", "sample": "table-merged-header", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": false, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "markovo", "sample": "table-simple", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": false, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "markovo", "sample": "two-column", "kind": "columns", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0, "error": null }, { "tool": "markitdown", "sample": "equation", "kind": "equation", "prose_recall": null, "reading_order": null, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": 1.0, "equation_recall_exact": 1.0, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0605, "error": null }, { "tool": "markitdown", "sample": "mixed", "kind": "mixed", "prose_recall": 1.0, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": 0.6667, "scan_text_recall": 0.0, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0267, "error": null }, { "tool": "markitdown", "sample": "prose-single", "kind": "prose", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0206, "error": null }, { "tool": "markitdown", "sample": "rotated-header", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 0.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0107, "error": null }, { "tool": "markitdown", "sample": "scan-image", "kind": "scan", "prose_recall": null, "reading_order": null, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": 0.0, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0088, "error": null }, { "tool": "markitdown", "sample": "table-merged-header", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 0.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0132, "error": null }, { "tool": "markitdown", "sample": "table-simple", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0115, "error": null }, { "tool": "markitdown", "sample": "two-column", "kind": "columns", "prose_recall": 0.1111, "reading_order": 0.8, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.0355, "error": null }, { "tool": "pymupdf4llm", "sample": "equation", "kind": "equation", "prose_recall": null, "reading_order": null, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": 0.75, "equation_recall_exact": 0.75, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.1992, "error": null }, { "tool": "pymupdf4llm", "sample": "mixed", "kind": "mixed", "prose_recall": 1.0, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": 0.6667, "scan_text_recall": 0.0, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.2945, "error": null }, { "tool": "pymupdf4llm", "sample": "prose-single", "kind": "prose", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.1297, "error": null }, { "tool": "pymupdf4llm", "sample": "rotated-header", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 0.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.1471, "error": null }, { "tool": "pymupdf4llm", "sample": "scan-image", "kind": "scan", "prose_recall": null, "reading_order": null, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": 0.0, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.1872, "error": null }, { "tool": "pymupdf4llm", "sample": "table-merged-header", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 0.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.1466, "error": null }, { "tool": "pymupdf4llm", "sample": "table-simple", "kind": "table", "prose_recall": null, "reading_order": null, "table_rows_intact": 1.0, "table_header_intact": 1.0, "table_pipe_detected": true, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.1497, "error": null }, { "tool": "pymupdf4llm", "sample": "two-column", "kind": "columns", "prose_recall": 1.0, "reading_order": 1.0, "table_rows_intact": null, "table_header_intact": null, "table_pipe_detected": null, "pages_covered": null, "scan_text_recall": null, "equation_recall": null, "equation_recall_exact": null, "heading_recall": null, "heading_level_exact": null, "list_items_intact": null, "code_block_intact": null, "boilerplate_excluded": null, "slide_order": null, "notes_recall": null, "sheet_coverage": null, "elapsed_s": 0.1429, "error": null } ] }