Prompt
The image alone, with no system prompt or text, scaled so its longest edge is at most 2048 pixels; thinking
disabled, temperature 0, up to 16,000 new tokens.
Training
LoRA (rank 16, alpha 32) on every language-model projection, the vision encoder frozen; 3 epochs at learning
rate 1e-4 on 995 table crops from 107 publication series (UK public-sector reports, US federal and historical
statistics, German budget annexes and others), digital and scanned. The targets are GPT-6.1 Terra
transcriptions that parse into tables without blocking issues; they were not reviewed by a person. The training
crops include some that the scannedtables
dataset holds back for rights or privacy reasons. The adapter is merged into the bf16 weights.
Evaluation
1,006 validation crops from series not seen in training, scored as the share of printed values whose row path,
column path and text match the reference transcription exactly (metric records-1):
Table with columns: All, Digital PDFs, Scans| All | Digital PDFs | Scans |
|---|
| 0.797 | 0.835 | 0.511 |
72% of crops are read without a difference. The model does not yet answer NOT_A_TABLE for crops without a
table, and scans read much worse than digital PDFs. A self-training round on 7,698 of its own
transcriptions did not improve these scores.
License
Apache 2.0, as the base model.