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
Merge central moment 4: Fourth-moment translation omits third-moment coupling. · case 01
The reduction disagrees with its explicit aggregation oracle.
Merge central moment 4: Fourth-moment translation omits third-moment coupling. · case 02
The reduction disagrees with its explicit aggregation oracle.
Merge central moment 4: Fourth-moment translation omits third-moment coupling. · case 03
The reduction disagrees with its explicit aggregation oracle.
Merge central moment 4: Fourth-moment translation omits third-moment coupling. · case 04
The reduction disagrees with its explicit aggregation oracle.
Merge central moment 4: Fourth-moment translation omits third-moment coupling. · case 05
The reduction disagrees with its explicit aggregation oracle.
Merge central moment 4: The count polynomial uses the square of the count difference. · case 01
The reduction disagrees with its explicit aggregation oracle.
Merge central moment 4: The count polynomial uses the square of the count difference. · case 02
The reduction disagrees with its explicit aggregation oracle.
Merge central moment 4: The count polynomial uses the square of the count difference. · case 03
The reduction disagrees with its explicit aggregation oracle.
Merge central moment 4: The count polynomial uses the square of the count difference. · case 04
The reduction disagrees with its explicit aggregation oracle.
Merge central moment 4: The count polynomial uses the square of the count difference. · case 05
The reduction disagrees with its explicit aggregation oracle.
Merge central moment 4: The fourth-moment merger drops accumulated within-block fourth moment. · case 01
The reduction disagrees with its explicit aggregation oracle.
Merge central moment 4: The fourth-moment merger drops accumulated within-block fourth moment. · case 02
The reduction disagrees with its explicit aggregation oracle.
Merge central moment 4: The fourth-moment merger drops accumulated within-block fourth moment. · case 03
The reduction disagrees with its explicit aggregation oracle.
Merge central moment 4: The fourth-moment merger drops accumulated within-block fourth moment. · case 04
The reduction disagrees with its explicit aggregation oracle.
Merge central moment 4: The fourth-moment merger drops accumulated within-block fourth moment. · case 05
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: An intersecting bin contributes all of its mass. · case 01
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: An intersecting bin contributes all of its mass. · case 02
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: An intersecting bin contributes all of its mass. · case 03
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: An intersecting bin contributes all of its mass. · case 04
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: An intersecting bin contributes all of its mass. · case 05
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Overlap length is multiplied by mass without conversion to density. · case 01
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Overlap length is multiplied by mass without conversion to density. · case 02
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Overlap length is multiplied by mass without conversion to density. · case 03
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Overlap length is multiplied by mass without conversion to density. · case 04
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Overlap length is multiplied by mass without conversion to density. · case 05
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Disjoint bins contribute negative signed overlap. · case 01
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Disjoint bins contribute negative signed overlap. · case 02
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Disjoint bins contribute negative signed overlap. · case 03
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Disjoint bins contribute negative signed overlap. · case 04
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Disjoint bins contribute negative signed overlap. · case 05
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: The query left edge is ignored when truncating bins. · case 01
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: The query left edge is ignored when truncating bins. · case 02
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: The query left edge is ignored when truncating bins. · case 03
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: The query left edge is ignored when truncating bins. · case 04
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: The query left edge is ignored when truncating bins. · case 05
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: The query right edge is ignored when truncating bins. · case 01
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: The query right edge is ignored when truncating bins. · case 02
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: The query right edge is ignored when truncating bins. · case 03
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: The query right edge is ignored when truncating bins. · case 04
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: The query right edge is ignored when truncating bins. · case 05
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Density is truncated before integration. · case 01
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Density is truncated before integration. · case 02
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Density is truncated before integration. · case 03
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Density is truncated before integration. · case 04
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Density is truncated before integration. · case 05
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Bin contributions are averaged rather than accumulated. · case 01
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Bin contributions are averaged rather than accumulated. · case 02
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Bin contributions are averaged rather than accumulated. · case 03
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Bin contributions are averaged rather than accumulated. · case 04
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Bin contributions are averaged rather than accumulated. · case 05
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Reversed query bounds are silently sorted into a nonempty query. · case 01
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Reversed query bounds are silently sorted into a nonempty query. · case 02
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Reversed query bounds are silently sorted into a nonempty query. · case 03
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Reversed query bounds are silently sorted into a nonempty query. · case 04
The reduction disagrees with its explicit aggregation oracle.
Histogram interval mass: Reversed query bounds are silently sorted into a nonempty query. · case 05
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The between-block cross scatter is discarded. · case 01
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The between-block cross scatter is discarded. · case 02
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The between-block cross scatter is discarded. · case 03
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The between-block cross scatter is discarded. · case 04
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The between-block cross scatter is discarded. · case 05
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The covariance correction uses the square of the x displacement. · case 01
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The covariance correction uses the square of the x displacement. · case 02
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The covariance correction uses the square of the x displacement. · case 03
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The covariance correction uses the square of the x displacement. · case 04
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The covariance correction uses the square of the x displacement. · case 05
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The between-block covariance sign is discarded. · case 01
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The between-block covariance sign is discarded. · case 02
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The between-block covariance sign is discarded. · case 03
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The between-block covariance sign is discarded. · case 04
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The between-block covariance sign is discarded. · case 05
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The incoming block cross scatter is not added. · case 01
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The incoming block cross scatter is not added. · case 02
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The incoming block cross scatter is not added. · case 03
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The incoming block cross scatter is not added. · case 04
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The incoming block cross scatter is not added. · case 05
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The x centroid moves according to old rather than incoming population. · case 01
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The x centroid moves according to old rather than incoming population. · case 02
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The x centroid moves according to old rather than incoming population. · case 03
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The x centroid moves according to old rather than incoming population. · case 04
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The x centroid moves according to old rather than incoming population. · case 05
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The y centroid is updated using the x displacement. · case 01
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The y centroid is updated using the x displacement. · case 02
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The y centroid is updated using the x displacement. · case 03
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The y centroid is updated using the x displacement. · case 04
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The y centroid is updated using the x displacement. · case 05
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The cross correction uses a product rather than total count denominator. · case 01
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The cross correction uses a product rather than total count denominator. · case 02
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The cross correction uses a product rather than total count denominator. · case 03
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The cross correction uses a product rather than total count denominator. · case 04
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: The cross correction uses a product rather than total count denominator. · case 05
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: Each incoming cross scatter is normalized before unnormalised merging. · case 01
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: Each incoming cross scatter is normalized before unnormalised merging. · case 02
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: Each incoming cross scatter is normalized before unnormalised merging. · case 03
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: Each incoming cross scatter is normalized before unnormalised merging. · case 04
The reduction disagrees with its explicit aggregation oracle.
Merge cross scatter: Each incoming cross scatter is normalized before unnormalised merging. · case 05
The reduction disagrees with its explicit aggregation oracle.
Frequency left quantile: Weighted rank walks unsorted observations. · case 01
The reduction disagrees with its explicit aggregation oracle.
Frequency left quantile: Weighted rank walks unsorted observations. · case 02
The reduction disagrees with its explicit aggregation oracle.
Frequency left quantile: Weighted rank walks unsorted observations. · case 03
The reduction disagrees with its explicit aggregation oracle.
Frequency left quantile: Weighted rank walks unsorted observations. · case 04
The reduction disagrees with its explicit aggregation oracle.
Frequency left quantile: Weighted rank walks unsorted observations. · 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 ↗