calib·HumanEval/23
This is one (task, candidate response) pair flowing through the full PANOPTES pipeline. Each section below is a stage of the analysis: the task itself, the candidate solution being evaluated, every judge's score + rationale, the sampling-pass dispersion that captures within-judge noise, and the uncertainty-quantification metrics computed on top.
The function signature + docstring presented to both the model under test and to every judge. The entry-point name was obfuscated from strlen to fn_4719e7e500 so the judges can't pattern-match a memorized HumanEval solution.
def fn_4719e7e500(string: str) -> int:
""" Return length of given string
>>> fn_4719e7e500('')
0
>>> fn_4719e7e500('abc')
3
"""
The full solution every judge is grading. For these runs the candidate is the reference solution prepended with the task signature so it parses as a complete program.
def fn_4719e7e500(string: str) -> int:
""" Return length of given string
>>> fn_4719e7e500('')
0
>>> fn_4719e7e500('abc')
3
"""
return len(string)
One call per judge at temperature=0. This is the "best single guess" each judge has. Disagreement here is structural. The judges literally see this candidate differently.
n draws per judge at temperature=1. Dots are individual draws; vertical bar is the mean; shaded band is ±1σ. Wide band = the judge is uncertain even with itself; narrow band = it's consistent.
Three statistical methods computed on top of the raw scores above. Each one tells you something different about how much to trust the headline number.
How to read these: self-consistency = does the judge agree with itself when resampled? Narrower CI means more consistent. Semantic entropy = do the judge's rationales cluster into one meaning, or several? Higher entropy means the judge is internally conflicted about why. Decomposition = how much of the total variance comes from within-judge sampling noise (aleatoric, hard to fix) vs between-judge disagreement (epistemic, fixable by calling more judges).
The natural-language explanation each judge gave alongside its score. These are produced via tool-use structured output, so the score and the rationale are guaranteed to come from the same forward pass.
The solution correctly uses Python's built-in `len()` function to return the length of the string. It handles both the empty string edge case (returns 0) and normal strings (returns correct length). The implementation is idiomatic, concise, and correct for all plausible inputs.
The candidate solution correctly implements the function to return the length of a given string using Python's built-in `len()` function. It passes the provided examples, including an empty string and a non-empty string, which are typical edge cases for this task. The solution is idiomatic, clear, and handles all plausible edge cases effectively.