Card: quick start with the idealens package (classify, extract, score)

README.md

@@ -34,16 +34,25 @@ idealens run docs.jsonl -o scores.jsonl --model IdeaLens-LogisticClassifier-PerI
 
 Input is JSONL with a `text` field per document. To score outlines you already have, use `idealens score outlines.jsonl -o scores.jsonl --model IdeaLens-LogisticClassifier-PerItem`. Score outlines as extracted; the paraphrasing step is only for training data.
 
-In Python:
+In Python, step by step:
 
 ```python
 import idealens as il
 
+texts = [open("document.txt").read()]
+formats = il.classify(texts)                  # one of the eight formats per document
+outlines = il.extract(texts, formats)         # role-labelled outlines
 with il.Detector("IdeaLens-LogisticClassifier-PerItem") as det:
-    records = il.run(texts, det)   # classify, extract and score
-print(records[0]["p_human"], records[0]["verdict"]["ai"])
+    records = det.score_outlines(outlines, format=formats)
+
+r = records[0]
+print(r["p_human"], r["verdict"]["ai"])       # P(human); flagged at the 1% global cut?
+print(r["item_p_human"])                      # each item's own P(human)
+print(outlines[0].render())                   # the outline that was scored
 ```
 
+Or in one call: `records = il.run(texts, det)`. `classify` and `extract` use Gemini 3.7 Flash, the extractor the thresholds were fitted with (`GEMINI_API_KEY`); pass `provider=idealens.providers.make(...)` to use Vertex, OpenAI, Anthropic, OpenRouter or a local server. The [package README](https://github.com/RishanthRajendhran/IdeaLens#ways-to-use-idealens) covers the other ways to run it.
+
 ## Thresholds
 
 `thresholds.json` holds this model's cuts at 0.1%, 0.5%, 1%, 2% and 5% false-positive rates, fitted on the 80,000 human