Reproducibility package for Scaling Up Classroom Observation With Large Language Models: A Reliability Study Of The World Bank's Teach Framework In Peru

2026

Get Reproducibility Package

Reference ID

RR_PER_2026_700

DOI

https://doi.org/10.60572/mjc8-rk86

Author(s)

Carolina Lopez, Ezequiel Molina, Matthew D. Krasnow, Jostin Kitmang, Carolina Moreira Vasquez, William J. Krasnow

Collections

World Bank Policy Research Working Papers

Metadata

JSON

Created on

Aug 17, 2026

Last modified

Aug 17, 2026

Page views

Downloads

Download related resources

Other Materials

README for the reproducibility package for Scaling up classroom observation with large language models: A reliability study of the World Bank's Teach framework in Peru

Download [PDF, 369.02 KB]

Download	https://reproducibility.worldbank.org//catalog/630/download/1872

Reproducibility verification for Scaling up classroom observation with large language models: A reliability study of the World Bank's Teach framework in Peru

Download [PDF, 138.92 KB]

Download	https://reproducibility.worldbank.org//catalog/630/download/1873

Reproducibility package for Scaling up classroom observation with large language models: A reliability study of the World Bank's Teach framework in Peru

Download [ZIP, 2.59 MB]

Download	https://reproducibility.worldbank.org//catalog/630/download/1874
Zip preview	RR_PER_2026_700 data_hash_report.csv LICENSE.txt README.pdf Reproducibility package code 00_master.py 01_video_assignment.ipynb 02_audio_conversion.ipynb 03_transcript_generation.ipynb 04_cleaning_and_eda.ipynb 05_evaluation.ipynb 06_performance.ipynb 07_statistical_analysis.ipynb figures figure2.py figure3.py figure4.py figure5.py models AI.py control control.py PromptTemplates.py README.md timestamped timestamped.py _context create_low_no_na_rubric.py create_low_priors_rubric.py create_policy_rubric.py Highest_Teach_1.json high_Teach_1.json low_priors_no_na_Teach_1.json low_priors_Teach_1.json low_Teach_1.json med_Teach_1.json no_rubric_TEACH_1.json policy_high_Teach_1.json policy_medium_Teach_1.json README.md Teach Training Manual 1.0.md teach_1_manual.py Teach_Manual_English 1.0.md requirements.txt tables generate_tables_s1_s5.py table2.py table3.py table4.py table5.py table6.py verify_numerics.py output figures figure1.tex figure2.pdf figure2.png figure3.pdf figure3.png figure4.pdf figure4.png figure5.pdf figure5.png reports 0-TEST-Control_report.md 13-Short-Reasoner-No-Priors-No-NAs_report.md 17-Long-Non-Reasoner-Priors-No-NAs_report.md 2-TEST-Medium-Rubric_report.md 3-TEST-High-Rubric_report.md 4-TEST-High-Rubric-Reasoning_report.md 5-TEST-High-Rubric-Timestamped_report.md 9-policy-high_report.md monte_carlo_bar_chart_ci.png monte_carlo_pie_charts.png reliability_exam_summary.txt segment_pass_dashboard.png tables supp_tables.xlsx table1.tex table2.tex table3.tex table4.tex table5.tex table6.tex table_s1.csv table_s1.tex table_s2.csv table_s2.tex table_s3.csv table_s3.tex table_s4.csv table_s4.tex table_s5.csv table_s5.tex table_s5_clip_distribution.csv table_s5_clip_distribution.tex reproducibility_report_RR_PER_2026_700.pdf WB-IGO-RIDER.txt

Back to Catalog