spec_version: 1
name: office_document_task_env
type: space
runtime: fastapi
app: server.app:app
port: 8000

# Cross-format RL environment for office-document tasks.
#
# 60 xlsx (Finch — 10 hand-curated Round-1 + 50 stratified Round-2 pull) ·
# 21 docx (OSWorld-Verified libreoffice_writer subset) ·
# 38 pptx (PPTArena evaluation_pairs_refined.json subset)
# = 119 total tasks · 97 train + 22 eval.
#
# All 119 tasks are enumerated below.  Round-1 hand-curated tasks have IDs
# task_1..task_10; Round-2 stratified pull uses finch_*; OSWorld uses
# osworld_<uuid8>; PPTArena uses pptarena_<slug>.

metadata:
  total_tasks: 119
  splits:
    train: 97
    eval: 22
  families:
    xlsx: 60
    docx: 21
    pptx: 38
  data_sources:
    - name: Finch (FinWorkBench)
      url: https://huggingface.co/datasets/FinWorkBench/Finch
      family: xlsx
      tasks: 60
      breakdown: "10 hand-curated (Round 1) + 50 stratified pull (Round 2)"
    - name: OSWorld-Verified (libreoffice_writer)
      url: https://github.com/xlang-ai/OSWorld
      family: docx
      tasks: 21
      breakdown: "21 strict-docx (skipping 1 .odt + 1 .pdf input)"
    - name: PPTArena
      url: https://github.com/michaelofengend/PPTArena
      family: pptx
      tasks: 38
      breakdown: "38 stratified across 16 edit_types incl. all 5 long-tail singletons"
  manifest_path: data/manifest.jsonl

tasks:

  # ── Hand-curated Finch tasks (Round 1) ────────────────────────

  - id: task_1
    name: 'Count Plants in Spreadsheet'
    family: xlsx
    primary_tag: 'Cross-sheet/file Retrieval'
    difficulty: easy
    task_type: QA
    max_steps: 15
    split: train
    origin: finch_hand_curated
    grader:
      type: programmatic
      description: "QA (xlsx) — extract numbers from agent's text answer, compare against reference value. 80% numeric match (5% tolerance) + 20% keyword overlap. Score 0.001-0.999."

  - id: task_2
    name: 'Retrieve TW EOL Charge'
    family: xlsx
    primary_tag: 'Cross-sheet/file Retrieval'
    difficulty: easy
    task_type: QA
    max_steps: 15
    split: train
    origin: finch_hand_curated
    grader:
      type: programmatic
      description: "QA (xlsx) — extract numbers from agent's text answer, compare against reference value. 80% numeric match (5% tolerance) + 20% keyword overlap. Score 0.001-0.999."

  - id: task_3
    name: 'Portfolio Mark-to-Market Change'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: QA
    max_steps: 15
    split: train
    origin: finch_hand_curated
    grader:
      type: programmatic
      description: "QA (xlsx) — extract numbers from agent's text answer, compare against reference value. 80% numeric match (5% tolerance) + 20% keyword overlap. Score 0.001-0.999."

  - id: task_4
    name: 'Summarize Pipeline Imbalances'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch_hand_curated
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: task_5
    name: 'Audit and Correct Formula Errors'
    family: xlsx
    primary_tag: 'Validation / Review'
    difficulty: hard
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch_hand_curated
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: task_6
    name: 'Create Table and Apply Filter'
    family: xlsx
    primary_tag: 'Structuring / Formatting'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch_hand_curated
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: task_7
    name: 'Add Weekday Row and Data Entry'
    family: xlsx
    primary_tag: 'Data Entry / Import'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch_hand_curated
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: task_8
    name: 'Balance Sheet Validation and Indicators'
    family: xlsx
    primary_tag: 'Validation / Review'
    difficulty: hard
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch_hand_curated
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: task_9
    name: 'Create Scenario3 Worksheet'
    family: xlsx
    primary_tag: 'Financial Modeling'
    difficulty: hard
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch_hand_curated
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: task_10
    name: 'Consolidate by Type and Area'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch_hand_curated
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  # ── Train split — Finch xlsx (40 tasks, stratified Round-2 pull) ─

  - id: finch_6
    name: 'Calculation: Please write a structured economic analysis report based on '
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_15
    name: 'Structuring / Formatting: Translate all Chinese text in this Excel workbook (including'
    family: xlsx
    primary_tag: 'Structuring / Formatting'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_22
    name: 'Validation / Review: Please review the pivot table on the Replacement Cost sheet '
    family: xlsx
    primary_tag: 'Validation / Review'
    difficulty: hard
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_32
    name: 'Data Entry / Import: Please prepare a summary of all groups and staffing as of Ma'
    family: xlsx
    primary_tag: 'Data Entry / Import'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_33
    name: 'Structuring / Formatting: Gather Enron North America’s Mid Year 2001 performance acros'
    family: xlsx
    primary_tag: 'Structuring / Formatting'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_47
    name: 'Calculation: Complete the Income Statement (Purchase method) by calculati'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_55
    name: 'Summary / Visualization: On the correl_graph sheet, create a time-series line chart c'
    family: xlsx
    primary_tag: 'Summary / Visualization'
    difficulty: easy
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_62
    name: "Calculation: For EDF MAN, clear the 'Line of Credit Covering Initial Marg"
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_63
    name: 'Cross-sheet/file Retrieval: Using RepIS-Qtrly as the base, please create the RepIS-Annua'
    family: xlsx
    primary_tag: 'Cross-sheet/file Retrieval'
    difficulty: easy
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_65
    name: 'Validation / Review: Review the Inv & WC Value Adj summary tab and add the missin'
    family: xlsx
    primary_tag: 'Validation / Review'
    difficulty: hard
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_66
    name: 'Calculation: Calculate the Interest Payment fpr enron and fill the corren'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_68
    name: 'Cross-sheet/file Retrieval: Complete the Summary worksheet by entering the missing data '
    family: xlsx
    primary_tag: 'Cross-sheet/file Retrieval'
    difficulty: easy
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_76
    name: 'Structuring / Formatting: Reformat the table by bolding the titles and inserting row b'
    family: xlsx
    primary_tag: 'Structuring / Formatting'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_77
    name: 'Calculation: Calculate the headcount for each of the three groups in the '
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_78
    name: 'Cross-sheet/file Retrieval: Review the summary tab against each of the individual sheets'
    family: xlsx
    primary_tag: 'Cross-sheet/file Retrieval'
    difficulty: easy
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_82
    name: "Structuring / Formatting: On the 'simplecorr' sheet, create a table whose column heade"
    family: xlsx
    primary_tag: 'Structuring / Formatting'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_86
    name: 'Data Entry / Import: Complete the asset allocation schedule using the provided as'
    family: xlsx
    primary_tag: 'Data Entry / Import'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_90
    name: 'Structuring / Formatting: Add a top border to all values in the Summary tab that are c'
    family: xlsx
    primary_tag: 'Structuring / Formatting'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_93
    name: 'Calculation: Complete both the Flat and Peak tables by using the provided'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_98
    name: 'Data Entry / Import: Use publicly available market/financial data to populate She'
    family: xlsx
    primary_tag: 'Data Entry / Import'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_99
    name: 'Structuring / Formatting: Based on the Canada – Non-Commercial roster, prepare a headc'
    family: xlsx
    primary_tag: 'Structuring / Formatting'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_105
    name: 'Data Entry / Import: Add the 2/11/2000 column on the Feb 00 tab by mirroring the '
    family: xlsx
    primary_tag: 'Data Entry / Import'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_109
    name: 'Calculation: Calculate the total FTE percentage by region and by business'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_124
    name: 'Cross-sheet/file Retrieval: Complete the content in the summary sheet based on other spr'
    family: xlsx
    primary_tag: 'Cross-sheet/file Retrieval'
    difficulty: easy
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_125
    name: 'Calculation: You are given an Excel table (Figure 1.19) showing, for IDA-'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_128
    name: 'Summary / Visualization: Prepare a stacked area chart titled "Existing and Proposed D'
    family: xlsx
    primary_tag: 'Summary / Visualization'
    difficulty: easy
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_129
    name: 'Summary / Visualization: Create a stacked area chart titled “Rolling 55 Day Payables '
    family: xlsx
    primary_tag: 'Summary / Visualization'
    difficulty: easy
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_133
    name: 'Validation / Review: Audit the consolidated 2002 plan workbook and correct the fo'
    family: xlsx
    primary_tag: 'Validation / Review'
    difficulty: hard
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_138
    name: 'Structuring / Formatting: Add a new worksheet titled “P&C” and build a Property & Casu'
    family: xlsx
    primary_tag: 'Structuring / Formatting'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_139
    name: 'Financial Modeling: Using the Cleburne Plant Damage Sensitivities, evaluate the '
    family: xlsx
    primary_tag: 'Financial Modeling'
    difficulty: hard
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_142
    name: 'Calculation: Under the assumptions of Scenario 1, calculate and populate—'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_143
    name: 'Calculation: Apply Scenario 2 to calculate the current positions, the 30-'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_144
    name: 'Calculation: Using the daily Crude Oil and Natural Gas prices recorded in'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_147
    name: 'Data Entry / Import: Fill in the cells highlighted with a blue background, and th'
    family: xlsx
    primary_tag: 'Data Entry / Import'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_153
    name: 'Structuring / Formatting: On the correlation sheet, add derived columns from the BSCTM'
    family: xlsx
    primary_tag: 'Structuring / Formatting'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_155
    name: 'Validation / Review: Revise the data of 2002 allocation in HR sheet to reflect th'
    family: xlsx
    primary_tag: 'Validation / Review'
    difficulty: hard
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_159
    name: 'Structuring / Formatting: Complete the orange-highlighted cells on the Timing Tracking'
    family: xlsx
    primary_tag: 'Structuring / Formatting'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_166
    name: 'Calculation: Finalize the Position Sensitivities for Gas (in US$) by calc'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_167
    name: 'Financial Modeling: Based on the assumptions in the table, build out a complete '
    family: xlsx
    primary_tag: 'Financial Modeling'
    difficulty: hard
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_170
    name: 'Calculation: According to the specifications in the Strips sheet, aggrega'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  # ── Train split — OSWorld docx (17 tasks) ────────────────────

  - id: osworld_0e47de2a
    name: 'has_page_numbers_in_footers: Add page number for every page at the bottom left'
    family: docx
    primary_tag: 'has_page_numbers_in_footers'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_0e763496
    name: 'compare_font_names: Change the font to "Times New Roman" throughout the text.'
    family: docx
    primary_tag: 'compare_font_names'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_3ef2b351
    name: 'is_first_line_centered: Help me center align the heading in LibreOffice.'
    family: docx
    primary_tag: 'is_first_line_centered'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_6ada715d
    name: 'compare_docx_images: Copy the screenshot 1.png from the desktop to where my curso'
    family: docx
    primary_tag: 'compare_docx_images'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_6f81754e
    name: 'compare_unique_train_records: A certain railway company in Hong Kong uses a signaling syst'
    family: docx
    primary_tag: 'compare_unique_train_records'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_72b810ef
    name: "evaluate_strike_through_last_paragraph: I am peer-reviewing my friend's course outline. I think the "
    family: docx
    primary_tag: 'evaluate_strike_through_last_paragraph'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_8472fece
    name: 'evaluate_colored_words_in_tables: I am writing a word list for a dyslexic kid. To ease things '
    family: docx
    primary_tag: 'evaluate_colored_words_in_tables'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_88fe4b2d
    name: 'compare_docx_files: I am making a guideline for students of my course and would '
    family: docx
    primary_tag: 'compare_docx_files'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_936321ce
    name: 'compare_docx_tables: Could you help me convert the text seperated by commas to a '
    family: docx
    primary_tag: 'compare_docx_tables'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_adf5e2c3
    name: 'compare_docx_files: Help me adding "Steinberg, F. M., Bearden, M. M., & Keen, C.'
    family: docx
    primary_tag: 'compare_docx_files'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_b21acd93
    name: 'compare_line_spacing: I have been practicing professional writing lately. Now I am'
    family: docx
    primary_tag: 'compare_line_spacing'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_bb8ccc78
    name: 'infeasible: Share this document with my team and let us edit it together'
    family: docx
    primary_tag: 'infeasible'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_d53ff5ee
    name: 'compare_docx_files: I am currently engaged in text processing and require assist'
    family: docx
    primary_tag: 'compare_docx_files'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_e246f6d8
    name: 'check_italic_font_size_14: I found Italic font very hard to discern from the normal tex'
    family: docx
    primary_tag: 'check_italic_font_size_14'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_e528b65e
    name: 'compare_docx_files: Please help me make the first letter of each word to upperca'
    family: docx
    primary_tag: 'compare_docx_files'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_ecc2413d
    name: 'contains_page_break: Hey, can you throw in a blank page right after this one?'
    family: docx
    primary_tag: 'contains_page_break'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_f178a4a9
    name: 'find_default_font: Make Times New Roman the default Font'
    family: docx
    primary_tag: 'find_default_font'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  # ── Train split — PPTArena pptx (30 tasks) ───────────────────

  - id: pptarena_case_100_animation_canonicalization_bullet_sequencing
    name: 'Object Animations: Case 100: Animation Canonicalization & Bullet Sequencin'
    family: pptx
    primary_tag: 'Object Animations'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_13_italicize_subheadings_d
    name: 'Text & Typography: Case 13: Italicize Subheadings (D)'
    family: pptx
    primary_tag: 'Text & Typography'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_16_curate_multi_panel_photo_layout
    name: 'Alignment, Distribution & Z-order: Case 16: Curate Multi-Panel Photo Layout'
    family: pptx
    primary_tag: 'Alignment, Distribution & Z-order'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_17_build_ensemble_category_boards
    name: 'Shapes & Drawing: Case 17: Build Ensemble Category Boards'
    family: pptx
    primary_tag: 'Shapes & Drawing'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_23_add_thank_you_slide
    name: 'Slide Layout & Placeholders: Case 23: Add Thank You Slide'
    family: pptx
    primary_tag: 'Slide Layout & Placeholders'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_27_correct_images
    name: 'Images & Pictures: Case 27: Correct Images'
    family: pptx
    primary_tag: 'Images & Pictures'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_29_convert_bar_chart_to_pie_chart
    name: 'Charts: Case 29: Convert Bar Chart to Pie Chart'
    family: pptx
    primary_tag: 'Charts'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_31_fix_text_overflow
    name: 'Text & Typography: Case 31: Fix Text Overflow'
    family: pptx
    primary_tag: 'Text & Typography'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_37_add_transitions
    name: 'Slide Transitions: Case 37: Add Transitions'
    family: pptx
    primary_tag: 'Slide Transitions'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_38_flip_theme_scheme
    name: 'Theme & Background: Case 38: Flip Theme Scheme'
    family: pptx
    primary_tag: 'Theme & Background'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_43_transitionary_slides
    name: 'Slide/Section Management & Footers: Case 43: Transitionary Slides'
    family: pptx
    primary_tag: 'Slide/Section Management & Footers'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_51_currency_symbol_swap_eurusd
    name: 'Tables: Case 51: Currency Symbol Swap (EUR→USD)'
    family: pptx
    primary_tag: 'Tables'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_58_bullets_normalize_levels
    name: 'Text & Typography: Case 58: Bullets Normalize Levels'
    family: pptx
    primary_tag: 'Text & Typography'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_59_convert_hyper_link
    name: 'Hyperlinks & Action Settings: Case 59: Convert Hyper Link'
    family: pptx
    primary_tag: 'Hyperlinks & Action Settings'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_61_sort_by_score_and_crop_image_169
    name: 'Tables: Case 61: Sort By Score And Crop Image 169'
    family: pptx
    primary_tag: 'Tables'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_63_spatial_constraint_layout
    name: 'Alignment, Distribution & Z-order: Case 63: Spatial Constraint Layout'
    family: pptx
    primary_tag: 'Alignment, Distribution & Z-order'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_67_wcag_accessibility_master_cleanup
    name: 'Accessibility & Semantics: Case 67: WCAG Accessibility & Master Cleanup'
    family: pptx
    primary_tag: 'Accessibility & Semantics'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_68_swimlane_flow_process_canonicalization
    name: 'SmartArt & Diagrams: Case 68: Swimlane Flow Process Canonicalization'
    family: pptx
    primary_tag: 'SmartArt & Diagrams'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_73_dynamic_data_label_placement
    name: 'Charts: Case 73: Dynamic Data Label Placement'
    family: pptx
    primary_tag: 'Charts'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_76_aesthetic_slide_makeover
    name: 'Theme & Background: Case 76: Aesthetic Slide Makeover'
    family: pptx
    primary_tag: 'Theme & Background'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_81_add_company_logo
    name: 'Images & Pictures: Case 81: Add Company Logo'
    family: pptx
    primary_tag: 'Images & Pictures'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_84_add_progress_bar
    name: 'Shapes & Drawing: Case 84: Add Progress Bar'
    family: pptx
    primary_tag: 'Shapes & Drawing'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_85_arabic_translate_ltr
    name: 'Text & Typography: Case 85: Arabic Translate LTR'
    family: pptx
    primary_tag: 'Text & Typography'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_87_merge_near_duplicate_slides
    name: 'Slide/Section Management & Footers: Case 87: Merge Near-Duplicate Slides'
    family: pptx
    primary_tag: 'Slide/Section Management & Footers'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_90_screenshot_to_editable_text_ub_title_slide
    name: 'Slide Layout & Placeholders: Case 90: Screenshot-to-Editable Text (UB Title Slide)'
    family: pptx
    primary_tag: 'Slide Layout & Placeholders'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_91_add_qr_code
    name: 'Images & Pictures: Case 91: Add QR Code'
    family: pptx
    primary_tag: 'Images & Pictures'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_93_multi_edit_cascade_copernicus_climate_highlights
    name: 'Charts: Case 93: Multi-Edit Cascade (Copernicus Climate Highlig'
    family: pptx
    primary_tag: 'Charts'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_95_master_layout_rebind
    name: 'Template & Master-Level Edits: Case 95: Master & Layout Rebind'
    family: pptx
    primary_tag: 'Template & Master-Level Edits'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_98_cross_slide_conditional_formatting_status_timeline
    name: 'SmartArt & Diagrams: Case 98: Cross-Slide Conditional Formatting (Status → T'
    family: pptx
    primary_tag: 'SmartArt & Diagrams'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_99_embed_configure_video_playback
    name: 'Audio & Video: Case 99: Embed & Configure Video Playback'
    family: pptx
    primary_tag: 'Audio & Video'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: train
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  # ── Eval split — Finch xlsx (10 tasks) ───────────────────────

  - id: finch_10
    name: 'Calculation: Per the headers and established formula logic, populate form'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_14
    name: 'Financial Modeling: Suppose we need to hold a 0.5-year AA(2) municipal investmen'
    family: xlsx
    primary_tag: 'Financial Modeling'
    difficulty: hard
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_35
    name: 'Calculation: Summarize the volume and dollar imbalances that exist betwee'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_38
    name: 'Calculation: Using the discount rate assumptions in the table and each Sh'
    family: xlsx
    primary_tag: 'Calculation'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_59
    name: 'Structuring / Formatting: Update the TOTAL PHYSICAL GAS tab to mirror the layout on TO'
    family: xlsx
    primary_tag: 'Structuring / Formatting'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_112
    name: 'Cross-sheet/file Retrieval: For each record, use the Frequency to place the Rent amount '
    family: xlsx
    primary_tag: 'Cross-sheet/file Retrieval'
    difficulty: easy
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_122
    name: 'Summary / Visualization: Create a new sheet named “Exp by Fun Gen Support Chart5” and'
    family: xlsx
    primary_tag: 'Summary / Visualization'
    difficulty: easy
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_154
    name: 'Data Entry / Import: Complete the missing Interreg co-financing data in the FR fi'
    family: xlsx
    primary_tag: 'Data Entry / Import'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_158
    name: 'Validation / Review: Audit the workbook and correct the formula errors in place s'
    family: xlsx
    primary_tag: 'Validation / Review'
    difficulty: hard
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  - id: finch_168
    name: 'Structuring / Formatting: Insert blank rows between adjacent tables in the workbook to'
    family: xlsx
    primary_tag: 'Structuring / Formatting'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: finch
    grader:
      type: programmatic
      description: 'MODIFY (xlsx) — 30% sheet-name match + 70% cell-level diff against gold reference (2% numeric tolerance). Score 0.001-0.999.'

  # ── Eval split — OSWorld docx (4 tasks) ──────────────────────

  - id: osworld_0810415c
    name: 'compare_line_spacing: Make the line spacing of first two paragraph into double lin'
    family: docx
    primary_tag: 'compare_line_spacing'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_0a0faba3
    name: 'check_tabstops: I would like to make the first three words of the sentence l'
    family: docx
    primary_tag: 'check_tabstops'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_0b17a146
    name: 'compare_docx_files: Help me change the 2 in "H2O" to a subscript.'
    family: docx
    primary_tag: 'compare_docx_files'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  - id: osworld_66399b0d
    name: 'compare_docx_tables: Could you help me insert a 7(columns)*5(rows) empty table at'
    family: docx
    primary_tag: 'compare_docx_tables'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: osworld
    grader:
      type: programmatic
      description: 'MODIFY (docx) — 3-layer: validity gate (python-docx parse) + 40% paragraph diff + 60% per-task OSWorld evaluator. Score 0.001-0.999.'

  # ── Eval split — PPTArena pptx (8 tasks) ─────────────────────

  - id: pptarena_case_26_match_slide_colors_to_theme
    name: 'Theme & Background: Case 26: Match Slide Colors to Theme'
    family: pptx
    primary_tag: 'Theme & Background'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_32_arrange_image_and_text
    name: 'Images & Pictures: Case 32: Arrange Image and Text'
    family: pptx
    primary_tag: 'Images & Pictures'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_35_structural_fix
    name: 'Text & Typography: Case 35: Structural Fix'
    family: pptx
    primary_tag: 'Text & Typography'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_36_add_speaker_notes
    name: 'Slide/Section Management & Footers: Case 36: Add Speaker Notes'
    family: pptx
    primary_tag: 'Slide/Section Management & Footers'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_40_hindu_center_titles
    name: 'Text & Typography: Case 40: Hindu Center Titles'
    family: pptx
    primary_tag: 'Text & Typography'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_49_normalize_thousand_separators
    name: 'Tables: Case 49: Normalize Thousand Separators'
    family: pptx
    primary_tag: 'Tables'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_60_fix_text_placement
    name: 'Alignment, Distribution & Z-order: Case 60: Fix Text Placement'
    family: pptx
    primary_tag: 'Alignment, Distribution & Z-order'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'

  - id: pptarena_case_7_update_quarter_two_data_b
    name: 'Charts: Case 7: Update Quarter Two Data (B)'
    family: pptx
    primary_tag: 'Charts'
    difficulty: medium
    task_type: MODIFY
    max_steps: 15
    split: eval
    origin: pptarena
    grader:
      type: programmatic
      description: 'MODIFY (pptx) — 2-layer: validity gate (python-pptx parse) + 20% slide-count + 80% avg per-shape composite (40% text + 20% style + 20% pos + 20% size). Score 0.001-0.999.'