GRITWORKS INDIAN LANGUAGES - REVIEW COPY

Bengali, Hindi and Marathi source forms with original handwriting and scripts. Starter: five two-page forms, each clean + negative. Full archive: all six supplied forms. These are separate applicant cases, with identical data within each clean/negative pair.

10 input PDFs: five clean + five negative. Annotated PDFs and the remaining variants are in the separate complete archive.

FORMATS
Each input PDF has .json expected answers, .boxes.json field boxes in PDF points
(top-left origin), and _bbox.json normalized vertices and 96-DPI pixel boxes.
The full archive includes clean annotated PDFs; click a rectangle for key/value.
Boxes cover selected populated fields, not every label or static word.
Clean/variant bodies are rasterized. Negative PDFs contain no hidden text layer.
Expected values do not change when a field is obscured or clipped.
Geometric captures carry forward homographies, projected polygons and clipped
rectangles. Visibility means clipping, not an assertion of OCR legibility.
No OCR confidence is asserted. Word boxes are supplied for the Indian-language
source forms; other authored/variant files provide field boxes only.
Keep JSON and annotated PDFs out of extraction-model inputs.

17 STANDARD CAPTURES
blur, jpeg_artifacts, black_white_threshold, scan_border, scan_lines, bleedthrough, scanner_bw_dithered, old_fax_noise_threshold, old_scanner_rollers, grayscale, photocopy, low_ink, bad_photo, fax_low_contrast, coffee_stain, scanner_color, fax_blur_noise

PROVENANCE
Sarvam-Samples (1).zip: six original Bengali, Hindi and Marathi form PDFs and accompanying expected-answer / field-box JSON. Body artwork and script preserved. No translation or new identity content introduced.

All files are review samples. Source files and the website remain unchanged.
