Sample 158

Evaluation Instructions

Important: Models were tasked with extracting evidence from documents. Some outputs may be low quality and should be scored accordingly.

Your task: Compare the model-generated prediction (right panel) against the ground truth criteria (left panel).

Clean view: Shows formatted, readable text for easy comparison
Diff view: Highlights differences between ground truth and prediction
Raw view: Shows original unformatted text as it appears in the dataset

Evaluation scale (0-4):

0 = No match: Prediction is unrelated or contradicts the target criteria
1 = Poor match: Minimal overlap with ground truth, major errors or omissions
2 = Partial match: Some key elements captured, but notable gaps or inaccuracies
3 = Good match: Most elements correct, minor differences or formatting issues
4 = Excellent match: Essentially identical content, fully correct capture

Consider both content accuracy and completeness. Some predictions may be technically "correct" but incomplete or out of order.

Ground Truth

INCLUSION CRITERIA

  1. Is 8 to 17 years of age, inclusive, at the time of randomization/initiation of study drug administration.
  2. Has received a diagnosis of type 1 diabetes (T1D) according to the criteria from the American Diabetes Association.
  3. Is able to be randomized and initiate study drug within 6 weeks (42 days) of the formal T1D diagnosis.
  4. Has a peak stimulated C-peptide of ≥0.2 pmol/mL from a mixed meal tolerance test (MMTT) at screening.
  5. Has a positive result on testing for T1D-related autoantibodies.

EXCLUSION CRITERIA

  1. Has any autoimmune disease other than T1D with the exception of stable thyroid or celiac disease.
  2. Has an active infection and/or fever.
  3. Has a history of or serologic evidence at screening of current or past infection with human immunodeficiency virus (HIV), hepatitis B virus (HBV), or hepatitis C virus (HCV).
  4. An individual who has a medical, psychological or social condition that, in the opinion of the Principal Investigator, would interfere with safe and proper completion of the trial.

Prediction

Modified Eligibility Criteria (version 33)

INCLUSION CRITERIA

  1. Is 8 to 17 years of age, inclusive, at the time of randomization/initiation of study drug administration.
  2. Has received a diagnosis of T1D according to the criteria from the American Diabetes Association.
  3. Is able to be randomized and initiate study drug within 6 weeks (42 days) of the formal T1D diagnosis.
  4. Has a peak stimulated C-peptide of ≥0.2 pmol/mL from a mixed meal tolerance test (MMTT) at screening.
  5. Has a positive result on testing for T1D-related autoantibodies.
  6. Has received non-infectious vaccines within 2 weeks before through 6 weeks after each dosing course.

EXCLUSION CRITERIA

  1. Has any autoimmune disease other than T1D, with the exception of stable thyroid or celiac disease.
  2. Has an active infection and/or fever.
  3. Has a history of or serologic evidence at screening of current or past infection with human immunodeficiency virus (HIV), hepatitis B virus (HBV), or hepatitis C virus (HCV).
  4. An individual who has a medical, psychological, or social condition that, in the opinion of the Principal Investigator, would interfere with safe and proper completion of the trial.
  5. Has a clinically active infection with Epstein-Barr virus (EBV) or cytomegalovirus (CMV) or a viral load of ≥10,000 copies per mL or per 106 lymphocytes at screening.
  6. Has a diagnosis of significant liver disease or alanine aminotransferase (ALT) and/or aspartate aminotransferase (AST) >2X upper limit of normal (ULN) or total bilirubin (TBili) >1.5X ULN, except for subjects with Gilbert’s syndrome with normal ALT and AST with approval of the Medical Monitor.