Function appendix_evidence_category

scripts/extract_evidence.py:143–187

(sentence: str)

def appendix_evidence_category(sentence: str) -> str:
    lower = sentence.lower()
    if any(token in lower for token in ["ablation", "without", "w/o", "remove", "removing"]):
        if any(token in lower for token in ["drop", "decrease", "worse", "unstable", "fail", "%"]):
            return "ablation"
    if any(
        token in lower
        for token in [
            "learning rate",
            "batch size",
            "optimizer",
            "epoch",
            "hardware",
            "gpu",
            "hyperparameter",
            "implementation",
            "prompt",
            "temperature",
        ]
    ):
        return "implementation_details"
    if re.search(r"\d", sentence) and any(
        token in lower
        for token in ["accuracy", "f1", "auc", "auprc", "score", "result", "outperform", "improv"]
    ):
        return "extra_results"
    if any(
        token in lower
        for token in [
            "dataset",
            "split",
            "training set",
            "validation",
            "test set",
            "annotation",
            "annotator",
            "corpus",
            "participants",
            "samples",
        ]
    ):
        return "dataset_details"
    if any(token in lower for token in ["case study", "qualitative", "example", "failure case"]):
        return "qualitative_examples"
    return ""


def appendix_section_for_page(appendix_index: dict, page_number: int) -> str: