Add solve rate eval script

Add comprehensive eval script

Add agent solve rate script

add deep verification results

clean rewrite of deep verification script

fix unbuffered output syntax

add unbuffered output for HF job

print results to stdout for HF job logs

fix encoding in deep verification script

upload deep verification script

add analyze.py reproduction script

update poster.html with corrected numbers

update poster_embed.html with full self-contained HTML and data-logbook-target attributes

add claim_analysis_results.json from deep analysis

add results.json from analysis

Upload deep_analysis.py with huggingface_hub

Upload poster_preview.png with huggingface_hub

Upload poster_preview.pdf with huggingface_hub

Upload poster_embed.html with huggingface_hub

initial commit