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
Median imputation uses held-out rows while fitting · case 01
Median imputation uses held-out rows while fitting.
Median imputation uses held-out rows while fitting · case 02
Median imputation uses held-out rows while fitting.
Median imputation uses held-out rows while fitting · case 03
Median imputation uses held-out rows while fitting.
Median imputation uses held-out rows while fitting · case 04
Median imputation uses held-out rows while fitting.
Median imputation uses held-out rows while fitting · case 05
Median imputation uses held-out rows while fitting.
Median imputation applies fitted state incorrectly · case 01
Median imputation applies fitted state incorrectly.
Median imputation applies fitted state incorrectly · case 02
Median imputation applies fitted state incorrectly.
Median imputation applies fitted state incorrectly · case 03
Median imputation applies fitted state incorrectly.
Median imputation applies fitted state incorrectly · case 04
Median imputation applies fitted state incorrectly.
Median imputation applies fitted state incorrectly · case 05
Median imputation applies fitted state incorrectly.
Median and interquartile scaling uses held-out rows while fitting · case 01
Median and interquartile scaling uses held-out rows while fitting.
Median and interquartile scaling uses held-out rows while fitting · case 02
Median and interquartile scaling uses held-out rows while fitting.
Median and interquartile scaling uses held-out rows while fitting · case 03
Median and interquartile scaling uses held-out rows while fitting.
Median and interquartile scaling uses held-out rows while fitting · case 04
Median and interquartile scaling uses held-out rows while fitting.
Median and interquartile scaling uses held-out rows while fitting · case 05
Median and interquartile scaling uses held-out rows while fitting.
Median and interquartile scaling applies fitted state incorrectly · case 01
Median and interquartile scaling applies fitted state incorrectly.
Median and interquartile scaling applies fitted state incorrectly · case 02
Median and interquartile scaling applies fitted state incorrectly.
Median and interquartile scaling applies fitted state incorrectly · case 03
Median and interquartile scaling applies fitted state incorrectly.
Median and interquartile scaling applies fitted state incorrectly · case 04
Median and interquartile scaling applies fitted state incorrectly.
Median and interquartile scaling applies fitted state incorrectly · case 05
Median and interquartile scaling applies fitted state incorrectly.
Quantile bin assignment uses held-out rows while fitting · case 01
Quantile bin assignment uses held-out rows while fitting.
Quantile bin assignment uses held-out rows while fitting · case 02
Quantile bin assignment uses held-out rows while fitting.
Quantile bin assignment uses held-out rows while fitting · case 03
Quantile bin assignment uses held-out rows while fitting.
Quantile bin assignment uses held-out rows while fitting · case 04
Quantile bin assignment uses held-out rows while fitting.
Quantile bin assignment uses held-out rows while fitting · case 05
Quantile bin assignment uses held-out rows while fitting.
Quantile bin assignment applies fitted state incorrectly · case 01
Quantile bin assignment applies fitted state incorrectly.
Quantile bin assignment applies fitted state incorrectly · case 02
Quantile bin assignment applies fitted state incorrectly.
Quantile bin assignment applies fitted state incorrectly · case 03
Quantile bin assignment applies fitted state incorrectly.
Quantile bin assignment applies fitted state incorrectly · case 04
Quantile bin assignment applies fitted state incorrectly.
Quantile bin assignment applies fitted state incorrectly · case 05
Quantile bin assignment applies fitted state incorrectly.
Learned missingness indicators uses held-out rows while fitting · case 01
Learned missingness indicators uses held-out rows while fitting.
Learned missingness indicators uses held-out rows while fitting · case 02
Learned missingness indicators uses held-out rows while fitting.
Learned missingness indicators uses held-out rows while fitting · case 03
Learned missingness indicators uses held-out rows while fitting.
Learned missingness indicators uses held-out rows while fitting · case 04
Learned missingness indicators uses held-out rows while fitting.
Learned missingness indicators uses held-out rows while fitting · case 05
Learned missingness indicators uses held-out rows while fitting.
Learned missingness indicators applies fitted state incorrectly · case 01
Learned missingness indicators applies fitted state incorrectly.
Learned missingness indicators applies fitted state incorrectly · case 02
Learned missingness indicators applies fitted state incorrectly.
Learned missingness indicators applies fitted state incorrectly · case 03
Learned missingness indicators applies fitted state incorrectly.
Learned missingness indicators applies fitted state incorrectly · case 04
Learned missingness indicators applies fitted state incorrectly.
Learned missingness indicators applies fitted state incorrectly · case 05
Learned missingness indicators applies fitted state incorrectly.
Sparse tensor: duplicate coordinates are overwritten instead of summed · case 01
duplicate coordinates are overwritten instead of summed.
Sparse tensor: duplicate coordinates are overwritten instead of summed · case 02
duplicate coordinates are overwritten instead of summed.
Sparse tensor: duplicate coordinates are overwritten instead of summed · case 03
duplicate coordinates are overwritten instead of summed.
Sparse tensor: duplicate coordinates are overwritten instead of summed · case 04
duplicate coordinates are overwritten instead of summed.
Sparse tensor: duplicate coordinates are overwritten instead of summed · case 05
duplicate coordinates are overwritten instead of summed.
Sparse tensor: COO entries retain input order instead of row-major canonical order · case 01
COO entries retain input order instead of row-major canonical order.
Sparse tensor: COO entries retain input order instead of row-major canonical order · case 02
COO entries retain input order instead of row-major canonical order.
Sparse tensor: COO entries retain input order instead of row-major canonical order · case 03
COO entries retain input order instead of row-major canonical order.
Sparse tensor: COO entries retain input order instead of row-major canonical order · case 04
COO entries retain input order instead of row-major canonical order.
Sparse tensor: COO entries retain input order instead of row-major canonical order · case 05
COO entries retain input order instead of row-major canonical order.
Sparse tensor: coalesced zero values remain stored · case 01
coalesced zero values remain stored.
Sparse tensor: coalesced zero values remain stored · case 02
coalesced zero values remain stored.
Sparse tensor: coalesced zero values remain stored · case 03
coalesced zero values remain stored.
Sparse tensor: coalesced zero values remain stored · case 04
coalesced zero values remain stored.
Sparse tensor: coalesced zero values remain stored · case 05
coalesced zero values remain stored.
Sparse tensor: CSR row pointers omit empty rows · case 01
CSR row pointers omit empty rows.
Sparse tensor: CSR row pointers omit empty rows · case 02
CSR row pointers omit empty rows.
Sparse tensor: CSR row pointers omit empty rows · case 03
CSR row pointers omit empty rows.
Sparse tensor: CSR row pointers omit empty rows · case 04
CSR row pointers omit empty rows.
Sparse tensor: CSR row pointers omit empty rows · case 05
CSR row pointers omit empty rows.
Sparse tensor: CSR expansion loses rows with repeated row pointers · case 01
CSR expansion loses rows with repeated row pointers.
Sparse tensor: CSR expansion loses rows with repeated row pointers · case 02
CSR expansion loses rows with repeated row pointers.
Sparse tensor: CSR expansion loses rows with repeated row pointers · case 03
CSR expansion loses rows with repeated row pointers.
Sparse tensor: CSR expansion loses rows with repeated row pointers · case 04
CSR expansion loses rows with repeated row pointers.
Sparse tensor: CSR expansion loses rows with repeated row pointers · case 05
CSR expansion loses rows with repeated row pointers.
Sparse tensor: columns inside each CSR row are not canonicalized · case 01
columns inside each CSR row are not canonicalized.
Sparse tensor: columns inside each CSR row are not canonicalized · case 02
columns inside each CSR row are not canonicalized.
Sparse tensor: columns inside each CSR row are not canonicalized · case 03
columns inside each CSR row are not canonicalized.
Sparse tensor: columns inside each CSR row are not canonicalized · case 04
columns inside each CSR row are not canonicalized.
Sparse tensor: columns inside each CSR row are not canonicalized · case 05
columns inside each CSR row are not canonicalized.
Sparse tensor: duplicate CSR columns are retained as separate coordinates · case 01
duplicate CSR columns are retained as separate coordinates.
Sparse tensor: duplicate CSR columns are retained as separate coordinates · case 02
duplicate CSR columns are retained as separate coordinates.
Sparse tensor: duplicate CSR columns are retained as separate coordinates · case 03
duplicate CSR columns are retained as separate coordinates.
Sparse tensor: duplicate CSR columns are retained as separate coordinates · case 04
duplicate CSR columns are retained as separate coordinates.
Sparse tensor: duplicate CSR columns are retained as separate coordinates · case 05
duplicate CSR columns are retained as separate coordinates.
Sparse tensor: row reduction uses the global value array · case 01
row reduction uses the global value array.
Sparse tensor: row reduction uses the global value array · case 02
row reduction uses the global value array.
Sparse tensor: row reduction uses the global value array · case 03
row reduction uses the global value array.
Sparse tensor: row reduction uses the global value array · case 04
row reduction uses the global value array.
Sparse tensor: row reduction uses the global value array · case 05
row reduction uses the global value array.
Sparse tensor: column reduction confuses row positions with column indices · case 01
column reduction confuses row positions with column indices.
Sparse tensor: column reduction confuses row positions with column indices · case 02
column reduction confuses row positions with column indices.
Sparse tensor: column reduction confuses row positions with column indices · case 03
column reduction confuses row positions with column indices.
Sparse tensor: column reduction confuses row positions with column indices · case 04
column reduction confuses row positions with column indices.
Sparse tensor: column reduction confuses row positions with column indices · case 05
column reduction confuses row positions with column indices.
Sparse tensor: COO matrix-vector product ignores row coordinates · case 01
COO matrix-vector product ignores row coordinates.
Sparse tensor: COO matrix-vector product ignores row coordinates · case 02
COO matrix-vector product ignores row coordinates.
Sparse tensor: COO matrix-vector product ignores row coordinates · case 03
COO matrix-vector product ignores row coordinates.
Sparse tensor: COO matrix-vector product ignores row coordinates · case 04
COO matrix-vector product ignores row coordinates.
Sparse tensor: COO matrix-vector product ignores row coordinates · case 05
COO matrix-vector product ignores row coordinates.
Sparse tensor: transpose swaps shape but leaves coordinates unchanged · case 01
transpose swaps shape but leaves coordinates unchanged.
Sparse tensor: transpose swaps shape but leaves coordinates unchanged · case 02
transpose swaps shape but leaves coordinates unchanged.
Sparse tensor: transpose swaps shape but leaves coordinates unchanged · case 03
transpose swaps shape but leaves coordinates unchanged.
Sparse tensor: transpose swaps shape but leaves coordinates unchanged · case 04
transpose swaps shape but leaves coordinates unchanged.
Sparse tensor: transpose swaps shape but leaves coordinates unchanged · case 05
transpose swaps shape but leaves coordinates unchanged.
Sparse tensor: diagonal extraction includes off-diagonal values · case 01
diagonal extraction includes off-diagonal values.
Sparse tensor: diagonal extraction includes off-diagonal values · case 02
diagonal extraction includes off-diagonal values.
Sparse tensor: diagonal extraction includes off-diagonal values · case 03
diagonal extraction includes off-diagonal values.
Sparse tensor: diagonal extraction includes off-diagonal values · case 04
diagonal extraction includes off-diagonal values.
Sparse tensor: diagonal extraction includes off-diagonal values · case 05
diagonal extraction includes off-diagonal values.
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 ↗