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
Timestamp half decayed mass: Negative correction contributions are discarded. · case 01
The reduction disagrees with its explicit aggregation oracle.
Timestamp half decayed mass: Negative correction contributions are discarded. · case 02
The reduction disagrees with its explicit aggregation oracle.
Timestamp half decayed mass: Negative correction contributions are discarded. · case 03
The reduction disagrees with its explicit aggregation oracle.
Timestamp half decayed mass: Negative correction contributions are discarded. · case 04
The reduction disagrees with its explicit aggregation oracle.
Timestamp half decayed mass: Negative correction contributions are discarded. · case 05
The reduction disagrees with its explicit aggregation oracle.
Timestamp half decayed mass: Decayed total is divided by eligible event count. · case 01
The reduction disagrees with its explicit aggregation oracle.
Timestamp half decayed mass: Decayed total is divided by eligible event count. · case 02
The reduction disagrees with its explicit aggregation oracle.
Timestamp half decayed mass: Decayed total is divided by eligible event count. · case 03
The reduction disagrees with its explicit aggregation oracle.
Timestamp half decayed mass: Decayed total is divided by eligible event count. · case 04
The reduction disagrees with its explicit aggregation oracle.
Timestamp half decayed mass: Decayed total is divided by eligible event count. · case 05
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Segment levels are summed without duration weights. · case 01
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Segment levels are summed without duration weights. · case 02
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Segment levels are summed without duration weights. · case 03
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Segment levels are summed without duration weights. · case 04
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Segment levels are summed without duration weights. · case 05
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: A segment uses the level at its right endpoint. · case 01
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: A segment uses the level at its right endpoint. · case 02
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: A segment uses the level at its right endpoint. · case 03
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: A segment uses the level at its right endpoint. · case 04
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: A segment uses the level at its right endpoint. · case 05
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: A change is not active at its exact timestamp. · case 01
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: A change is not active at its exact timestamp. · case 02
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: A change is not active at its exact timestamp. · case 03
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: A change is not active at its exact timestamp. · case 04
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: A change is not active at its exact timestamp. · case 05
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Events before the averaging interval are discarded. · case 01
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Events before the averaging interval are discarded. · case 02
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Events before the averaging interval are discarded. · case 03
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Events before the averaging interval are discarded. · case 04
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Events before the averaging interval are discarded. · case 05
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Equal-time level updates are summed like deltas. · case 01
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Equal-time level updates are summed like deltas. · case 02
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Equal-time level updates are summed like deltas. · case 03
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Equal-time level updates are summed like deltas. · case 04
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Equal-time level updates are summed like deltas. · case 05
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: The first future level is backfilled before it begins. · case 01
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: The first future level is backfilled before it begins. · case 02
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: The first future level is backfilled before it begins. · case 03
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: The first future level is backfilled before it begins. · case 04
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: The first future level is backfilled before it begins. · case 05
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Total area is divided by change count rather than elapsed duration. · case 01
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Total area is divided by change count rather than elapsed duration. · case 02
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Total area is divided by change count rather than elapsed duration. · case 03
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Total area is divided by change count rather than elapsed duration. · case 04
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Total area is divided by change count rather than elapsed duration. · case 05
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: The final carried segment after the last change is omitted. · case 01
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: The final carried segment after the last change is omitted. · case 02
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: The final carried segment after the last change is omitted. · case 03
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: The final carried segment after the last change is omitted. · case 04
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: The final carried segment after the last change is omitted. · case 05
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Every segment uses the latest known event regardless of its time. · case 01
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Every segment uses the latest known event regardless of its time. · case 02
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Every segment uses the latest known event regardless of its time. · case 03
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Every segment uses the latest known event regardless of its time. · case 04
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: Every segment uses the latest known event regardless of its time. · case 05
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: An empty interval is reported as zero measured level. · case 01
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: An empty interval is reported as zero measured level. · case 02
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: An empty interval is reported as zero measured level. · case 03
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: An empty interval is reported as zero measured level. · case 04
The reduction disagrees with its explicit aggregation oracle.
Time weighted step level: An empty interval is reported as zero measured level. · case 05
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Expected cell counts assume uniformly sized rows and columns. · case 01
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Expected cell counts assume uniformly sized rows and columns. · case 02
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Expected cell counts assume uniformly sized rows and columns. · case 03
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Expected cell counts assume uniformly sized rows and columns. · case 04
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Expected cell counts assume uniformly sized rows and columns. · case 05
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: The product of marginals is not divided by the grand total. · case 01
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: The product of marginals is not divided by the grand total. · case 02
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: The product of marginals is not divided by the grand total. · case 03
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: The product of marginals is not divided by the grand total. · case 04
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: The product of marginals is not divided by the grand total. · case 05
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Cells with zero observed count are excluded despite positive expectation. · case 01
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Cells with zero observed count are excluded despite positive expectation. · case 02
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Cells with zero observed count are excluded despite positive expectation. · case 03
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Cells with zero observed count are excluded despite positive expectation. · case 04
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Cells with zero observed count are excluded despite positive expectation. · case 05
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Absolute cell discrepancy replaces the squared discrepancy. · case 01
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Absolute cell discrepancy replaces the squared discrepancy. · case 02
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Absolute cell discrepancy replaces the squared discrepancy. · case 03
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Absolute cell discrepancy replaces the squared discrepancy. · case 04
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Absolute cell discrepancy replaces the squared discrepancy. · case 05
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Residuals are normalized by observed counts. · case 01
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Residuals are normalized by observed counts. · case 02
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Residuals are normalized by observed counts. · case 03
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Residuals are normalized by observed counts. · case 04
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Residuals are normalized by observed counts. · case 05
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: A column marginal is taken from the row marginal array. · case 01
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: A column marginal is taken from the row marginal array. · case 02
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: A column marginal is taken from the row marginal array. · case 03
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: A column marginal is taken from the row marginal array. · case 04
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: A column marginal is taken from the row marginal array. · case 05
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Cell contributions are averaged rather than summed. · case 01
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Cell contributions are averaged rather than summed. · case 02
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Cell contributions are averaged rather than summed. · case 03
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Cell contributions are averaged rather than summed. · case 04
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: Cell contributions are averaged rather than summed. · case 05
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: The expected count uses the square of one marginal. · case 01
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: The expected count uses the square of one marginal. · case 02
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: The expected count uses the square of one marginal. · case 03
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: The expected count uses the square of one marginal. · case 04
The reduction disagrees with its explicit aggregation oracle.
Contingency pearson reduction: The expected count uses the square of one marginal. · 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 ↗