clean up datasources

claude.md

@@ -100,8 +100,7 @@ The template (`plantilla_individual.pdf`) requires **5 chapters**. The docs/ fil
 ## Important Data Files
 
 ### Results CSV Files
-- `src/raytune_paddle_subproc_results_20251207_192320.csv` - 64 Ray Tune trials with configs and metrics
-- `results/ai_ocr_benchmark_finetune_results_20251206_113206.csv` - Per-page OCR benchmark results
+- `src/raytune_paddle_subproc_results_20251207_192320.csv` - 64 Ray Tune trials with configs and metrics (PRIMARY DATA SOURCE)
 
 ### Key Notebooks
 - `src/paddle_ocr_fine_tune_unir_raytune.ipynb` - Main Ray Tune experiment
@@ -454,7 +453,6 @@ Fuente: American Psychological Association, 2020b.
 | Data Type | Source File |
 |-----------|-------------|
 | Ray Tune 64 trials | `src/raytune_paddle_subproc_results_20251207_192320.csv` |
-| Per-page benchmark | `results/ai_ocr_benchmark_finetune_results_20251206_113206.csv` |
 | Experiment code | `src/paddle_ocr_fine_tune_unir_raytune.ipynb` |
 | Final comparison | Output cells in the notebook (baseline vs optimized) |
 
@@ -463,11 +461,11 @@ Fuente: American Psychological Association, 2020b.
 **WRONG:** "EasyOCR achieved 8.5% CER while PaddleOCR achieved 5.2% CER"
 (We don't have this comparison data in our results files)
 
-**RIGHT:** "PaddleOCR with baseline configuration achieved CER between 1.54% and 6.40% across pages 5-9 (source: `results/ai_ocr_benchmark_finetune_results_20251206_113206.csv`)"
+**RIGHT:** "The optimization reduced CER from 7.78% to 1.49%, a reduction of 80.9% (source: final comparison in `paddle_ocr_fine_tune_unir_raytune.ipynb`)"
 
 **WRONG:** "The optimization improved results by approximately 80%"
 
-**RIGHT:** "The optimization reduced CER from 7.78% to 1.49%, a reduction of 80.9% (source: final comparison in `paddle_ocr_fine_tune_unir_raytune.ipynb`)"
+**RIGHT:** "From the 64 trials in `raytune_paddle_subproc_results_20251207_192320.csv`, minimum CER achieved was 1.15%"
 
 ### When Working on Documentation