assertion_sentence_has_number

Assertion: sentence has number

This classifier was trained for EduBehaviors: Assertion-based schemas for auditable dialogue coding and is usable through the Python package EduBehaviors-kit. This classifier was trained on an LLM-annotated subset of teacher utterances from the TalkMoves Dataset. See the Datasets section below for more information.

---

Training Details

Datasets

This model's columns are assertion_sentence_has_number and split_sentence_has_number.

Base rate (share of rows labeled as True): 25.5% overall — 24.4% train, 28.1% dev, 26.1% test.

Labels and annotation

Labels were generated with LLM annotators. Krippendorff's alpha for this assertion is 0.755.

Hyperparameters

---

Evaluation

Results

Limitations

• Labels come from LLM annotators, not human coders. Agreement between annotators with Krippendorff's Alpha is 0.755.
• Trained on teacher utterances only. Behaviour on student speech is untested.

---

How to Use

Message Structure

The model was trained on text built as:

{utterance}

The utterance is passed through as-is.

Running instructions

pip install setfit

from setfit import SetFitModel

model = SetFitModel.from_pretrained("StanfordSCALE/assertion_sentence_has_number")

text = 'Take 30 seconds talk to your group and then were going to come back and kind of put up all the words we think of when we think of modeling'
model.predict([text])        # -> array([1]) when the assertion holds
model.predict_proba([text])  # -> [[P(no), P(yes)]]

Citation

@misc{assertion_sentence_has_number,
  author = {Stanford SCALE Initiative},
  title  = {Assertion classifier: sentence has number},
  year   = {2026},
  url    = {https://huggingface.co/StanfordSCALE/assertion_sentence_has_number}
}