Model card wording

README.md

@@ -37,7 +37,7 @@ disabled, temperature 0, up to 16,000 new tokens.
 
 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), scanned and born-digital. The targets are GPT-6.1 Terra
+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](https://huggingface.co/datasets/lschiemanowski/scannedtables)
 dataset holds back for rights or privacy reasons. The adapter is merged into the bf16 weights.
@@ -47,12 +47,12 @@ dataset holds back for rights or privacy reasons. The adapter is merged into the
 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`):
 
-| All | Born-digital | Scanned |
+| 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 born-digital pages. A self-training round on 7,698 of its own
+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