Understand the failure.
Verify the repair.
Small, reproducible software failures. The broken implementation, the fix that didn’t work, and the one that passed—preserved together.
Explore the cases ↓How results are verified ↗WHAT THE ARCHIVE CONTAINS
100840 executable cases. 20168 are open.
Every case records the implementation that fails, the fix that did not work, and the repair that passed its checks—with recorded outputs and source hashes. This release adds 100840 cases across 20168 failure mechanisms and 254 domains.
The open tier gives you the failure and the unsuccessful fix for one case in every mechanism. The remaining 80672 cases, 5 variants per mechanism, are member-only: the verified repair, its recorded checks, and the full fixture suite are held in the member archive. Read the methodology ↗
A RECORD OF WHAT WENT WRONG
Browse the archive / 100840
Frequency symmetric trim mean: Trimming treats each compressed row as one observation. · case 01
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: Trimming treats each compressed row as one observation. · case 02
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: Trimming treats each compressed row as one observation. · case 03
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: Trimming treats each compressed row as one observation. · case 04
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: Trimming treats each compressed row as one observation. · case 05
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: The trimmed total is divided by the original population size. · case 01
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: The trimmed total is divided by the original population size. · case 02
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: The trimmed total is divided by the original population size. · case 03
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: The trimmed total is divided by the original population size. · case 04
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: The trimmed total is divided by the original population size. · case 05
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: Both removed tails are taken from the lower end. · case 01
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: Both removed tails are taken from the lower end. · case 02
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: Both removed tails are taken from the lower end. · case 03
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: Both removed tails are taken from the lower end. · case 04
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: Both removed tails are taken from the lower end. · case 05
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: A negative zero slice end removes all untrimmed observations. · case 01
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: A negative zero slice end removes all untrimmed observations. · case 02
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: A negative zero slice end removes all untrimmed observations. · case 03
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: A negative zero slice end removes all untrimmed observations. · case 04
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: A negative zero slice end removes all untrimmed observations. · case 05
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: All ties at a trim boundary are removed rather than the requested count. · case 01
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: All ties at a trim boundary are removed rather than the requested count. · case 02
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: All ties at a trim boundary are removed rather than the requested count. · case 03
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: All ties at a trim boundary are removed rather than the requested count. · case 04
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: All ties at a trim boundary are removed rather than the requested count. · case 05
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: Compressed frequencies expand through an inclusive upper bound. · case 01
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: Compressed frequencies expand through an inclusive upper bound. · case 02
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: Compressed frequencies expand through an inclusive upper bound. · case 03
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: Compressed frequencies expand through an inclusive upper bound. · case 04
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: Compressed frequencies expand through an inclusive upper bound. · case 05
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: An exhausted trim is reported as a measured zero mean. · case 01
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: An exhausted trim is reported as a measured zero mean. · case 02
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: An exhausted trim is reported as a measured zero mean. · case 03
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: An exhausted trim is reported as a measured zero mean. · case 04
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: An exhausted trim is reported as a measured zero mean. · case 05
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: The retained mean uses integer division. · case 01
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: The retained mean uses integer division. · case 02
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: The retained mean uses integer division. · case 03
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: The retained mean uses integer division. · case 04
The reduction disagrees with its explicit aggregation oracle.
Frequency symmetric trim mean: The retained mean uses integer division. · case 05
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: The collision numerator includes drawing an observation with itself. · case 01
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: The collision numerator includes drawing an observation with itself. · case 02
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: The collision numerator includes drawing an observation with itself. · case 03
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: The collision numerator includes drawing an observation with itself. · case 04
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: The collision numerator includes drawing an observation with itself. · case 05
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: The denominator counts draws with replacement. · case 01
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: The denominator counts draws with replacement. · case 02
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: The denominator counts draws with replacement. · case 03
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: The denominator counts draws with replacement. · case 04
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: The denominator counts draws with replacement. · case 05
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Label categories receive equal mass regardless of frequency. · case 01
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Label categories receive equal mass regardless of frequency. · case 02
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Label categories receive equal mass regardless of frequency. · case 03
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Label categories receive equal mass regardless of frequency. · case 04
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Label categories receive equal mass regardless of frequency. · case 05
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Only the numerator is converted to unordered pairs. · case 01
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Only the numerator is converted to unordered pairs. · case 02
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Only the numerator is converted to unordered pairs. · case 03
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Only the numerator is converted to unordered pairs. · case 04
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Only the numerator is converted to unordered pairs. · case 05
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Label values replace category counts in the collision total. · case 01
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Label values replace category counts in the collision total. · case 02
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Label values replace category counts in the collision total. · case 03
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Label values replace category counts in the collision total. · case 04
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Label values replace category counts in the collision total. · case 05
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: A singleton is assigned zero rather than an undefined distinct-draw probability. · case 01
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: A singleton is assigned zero rather than an undefined distinct-draw probability. · case 02
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: A singleton is assigned zero rather than an undefined distinct-draw probability. · case 03
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: A singleton is assigned zero rather than an undefined distinct-draw probability. · case 04
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: A singleton is assigned zero rather than an undefined distinct-draw probability. · case 05
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: All label frequencies are summed before squaring. · case 01
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: All label frequencies are summed before squaring. · case 02
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: All label frequencies are summed before squaring. · case 03
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: All label frequencies are summed before squaring. · case 04
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: All label frequencies are summed before squaring. · case 05
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Only the largest category contributes collision pairs. · case 01
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Only the largest category contributes collision pairs. · case 02
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Only the largest category contributes collision pairs. · case 03
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Only the largest category contributes collision pairs. · case 04
The reduction disagrees with its explicit aggregation oracle.
Empirical distinct draw collision: Only the largest category contributes collision pairs. · case 05
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: The maximum point-mass difference is used without cumulative accumulation. · case 01
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: The maximum point-mass difference is used without cumulative accumulation. · case 02
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: The maximum point-mass difference is used without cumulative accumulation. · case 03
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: The maximum point-mass difference is used without cumulative accumulation. · case 04
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: The maximum point-mass difference is used without cumulative accumulation. · case 05
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: Only positive CDF differences contribute. · case 01
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: Only positive CDF differences contribute. · case 02
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: Only positive CDF differences contribute. · case 03
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: Only positive CDF differences contribute. · case 04
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: Only positive CDF differences contribute. · case 05
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: Both CDFs use the first sample size. · case 01
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: Both CDFs use the first sample size. · case 02
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: Both CDFs use the first sample size. · case 03
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: Both CDFs use the first sample size. · case 04
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: Both CDFs use the first sample size. · case 05
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: The scan omits positions appearing in only one sample. · case 01
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: The scan omits positions appearing in only one sample. · case 02
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: The scan omits positions appearing in only one sample. · case 03
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: The scan omits positions appearing in only one sample. · case 04
The reduction disagrees with its explicit aggregation oracle.
Empirical cdf supremum: The scan omits positions appearing in only one sample. · case 05
The reduction disagrees with its explicit aggregation oracle.
INSPECTABLE BY DESIGN
Every result has a runnable source.
Runnable implementations with recorded outputs, source hashes, and explicit contracts. Related variants share a failure mechanism and belong together in evaluation splits.
Read the methodology ↗