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
Dataset deduplication: single insertion makes two fingerprints unrelated · case 01
single insertion makes two fingerprints unrelated.
Dataset deduplication: single insertion makes two fingerprints unrelated · case 02
single insertion makes two fingerprints unrelated.
Dataset deduplication: single insertion makes two fingerprints unrelated · case 03
single insertion makes two fingerprints unrelated.
Dataset deduplication: single insertion makes two fingerprints unrelated · case 04
single insertion makes two fingerprints unrelated.
Dataset deduplication: single insertion makes two fingerprints unrelated · case 05
single insertion makes two fingerprints unrelated.
Dataset deduplication: short duplicate fragment fails containment test · case 01
short duplicate fragment fails containment test.
Dataset deduplication: short duplicate fragment fails containment test · case 02
short duplicate fragment fails containment test.
Dataset deduplication: short duplicate fragment fails containment test · case 03
short duplicate fragment fails containment test.
Dataset deduplication: short duplicate fragment fails containment test · case 04
short duplicate fragment fails containment test.
Dataset deduplication: short duplicate fragment fails containment test · case 05
short duplicate fragment fails containment test.
Dataset deduplication: final token shingle is omitted · case 01
final token shingle is omitted.
Dataset deduplication: final token shingle is omitted · case 02
final token shingle is omitted.
Dataset deduplication: final token shingle is omitted · case 03
final token shingle is omitted.
Dataset deduplication: final token shingle is omitted · case 04
final token shingle is omitted.
Dataset deduplication: final token shingle is omitted · case 05
final token shingle is omitted.
Dataset deduplication: signature selects maximum hash per band · case 01
signature selects maximum hash per band.
Dataset deduplication: signature selects maximum hash per band · case 02
signature selects maximum hash per band.
Dataset deduplication: signature selects maximum hash per band · case 03
signature selects maximum hash per band.
Dataset deduplication: signature selects maximum hash per band · case 04
signature selects maximum hash per band.
Dataset deduplication: signature selects maximum hash per band · case 05
signature selects maximum hash per band.
Dataset deduplication: hash collision merges distinct records · case 01
hash collision merges distinct records.
Dataset deduplication: hash collision merges distinct records · case 02
hash collision merges distinct records.
Dataset deduplication: hash collision merges distinct records · case 03
hash collision merges distinct records.
Dataset deduplication: hash collision merges distinct records · case 04
hash collision merges distinct records.
Dataset deduplication: hash collision merges distinct records · case 05
hash collision merges distinct records.
Dataset deduplication: equivalence group IDs depend on input order · case 01
equivalence group IDs depend on input order.
Dataset deduplication: equivalence group IDs depend on input order · case 02
equivalence group IDs depend on input order.
Dataset deduplication: equivalence group IDs depend on input order · case 03
equivalence group IDs depend on input order.
Dataset deduplication: equivalence group IDs depend on input order · case 04
equivalence group IDs depend on input order.
Dataset deduplication: equivalence group IDs depend on input order · case 05
equivalence group IDs depend on input order.
Dataset deduplication: duplicate rows consume the result cap · case 01
duplicate rows consume the result cap.
Dataset deduplication: duplicate rows consume the result cap · case 02
duplicate rows consume the result cap.
Dataset deduplication: duplicate rows consume the result cap · case 03
duplicate rows consume the result cap.
Dataset deduplication: duplicate rows consume the result cap · case 04
duplicate rows consume the result cap.
Dataset deduplication: duplicate rows consume the result cap · case 05
duplicate rows consume the result cap.
Dataset deduplication: pair exactly at distance budget is missed · case 01
pair exactly at distance budget is missed.
Dataset deduplication: pair exactly at distance budget is missed · case 02
pair exactly at distance budget is missed.
Dataset deduplication: pair exactly at distance budget is missed · case 03
pair exactly at distance budget is missed.
Dataset deduplication: pair exactly at distance budget is missed · case 04
pair exactly at distance budget is missed.
Dataset deduplication: pair exactly at distance budget is missed · case 05
pair exactly at distance budget is missed.
Mean imputation uses held-out rows while fitting · case 01
Mean imputation uses held-out rows while fitting.
Mean imputation uses held-out rows while fitting · case 02
Mean imputation uses held-out rows while fitting.
Mean imputation uses held-out rows while fitting · case 03
Mean imputation uses held-out rows while fitting.
Mean imputation uses held-out rows while fitting · case 04
Mean imputation uses held-out rows while fitting.
Mean imputation uses held-out rows while fitting · case 05
Mean imputation uses held-out rows while fitting.
Mean imputation applies fitted state incorrectly · case 01
Mean imputation applies fitted state incorrectly.
Mean imputation applies fitted state incorrectly · case 02
Mean imputation applies fitted state incorrectly.
Mean imputation applies fitted state incorrectly · case 03
Mean imputation applies fitted state incorrectly.
Mean imputation applies fitted state incorrectly · case 04
Mean imputation applies fitted state incorrectly.
Mean imputation applies fitted state incorrectly · case 05
Mean imputation applies fitted state incorrectly.
Min-max scaling uses held-out rows while fitting · case 01
Min-max scaling uses held-out rows while fitting.
Min-max scaling uses held-out rows while fitting · case 02
Min-max scaling uses held-out rows while fitting.
Min-max scaling uses held-out rows while fitting · case 03
Min-max scaling uses held-out rows while fitting.
Min-max scaling uses held-out rows while fitting · case 04
Min-max scaling uses held-out rows while fitting.
Min-max scaling uses held-out rows while fitting · case 05
Min-max scaling uses held-out rows while fitting.
Min-max scaling applies fitted state incorrectly · case 01
Min-max scaling applies fitted state incorrectly.
Min-max scaling applies fitted state incorrectly · case 02
Min-max scaling applies fitted state incorrectly.
Min-max scaling applies fitted state incorrectly · case 03
Min-max scaling applies fitted state incorrectly.
Min-max scaling applies fitted state incorrectly · case 04
Min-max scaling applies fitted state incorrectly.
Min-max scaling applies fitted state incorrectly · case 05
Min-max scaling applies fitted state incorrectly.
Population standardization uses held-out rows while fitting · case 01
Population standardization uses held-out rows while fitting.
Population standardization uses held-out rows while fitting · case 02
Population standardization uses held-out rows while fitting.
Population standardization uses held-out rows while fitting · case 03
Population standardization uses held-out rows while fitting.
Population standardization uses held-out rows while fitting · case 04
Population standardization uses held-out rows while fitting.
Population standardization uses held-out rows while fitting · case 05
Population standardization uses held-out rows while fitting.
Population standardization applies fitted state incorrectly · case 01
Population standardization applies fitted state incorrectly.
Population standardization applies fitted state incorrectly · case 02
Population standardization applies fitted state incorrectly.
Population standardization applies fitted state incorrectly · case 03
Population standardization applies fitted state incorrectly.
Population standardization applies fitted state incorrectly · case 04
Population standardization applies fitted state incorrectly.
Population standardization applies fitted state incorrectly · case 05
Population standardization applies fitted state incorrectly.
Category vocabulary encoding uses held-out rows while fitting · case 01
Category vocabulary encoding uses held-out rows while fitting.
Category vocabulary encoding uses held-out rows while fitting · case 02
Category vocabulary encoding uses held-out rows while fitting.
Category vocabulary encoding uses held-out rows while fitting · case 03
Category vocabulary encoding uses held-out rows while fitting.
Category vocabulary encoding uses held-out rows while fitting · case 04
Category vocabulary encoding uses held-out rows while fitting.
Category vocabulary encoding uses held-out rows while fitting · case 05
Category vocabulary encoding uses held-out rows while fitting.
Category vocabulary encoding applies fitted state incorrectly · case 01
Category vocabulary encoding applies fitted state incorrectly.
Category vocabulary encoding applies fitted state incorrectly · case 02
Category vocabulary encoding applies fitted state incorrectly.
Category vocabulary encoding applies fitted state incorrectly · case 03
Category vocabulary encoding applies fitted state incorrectly.
Category vocabulary encoding applies fitted state incorrectly · case 04
Category vocabulary encoding applies fitted state incorrectly.
Category vocabulary encoding applies fitted state incorrectly · case 05
Category vocabulary encoding applies fitted state incorrectly.
Variance selector learns feature support from held-out rows · case 01
The fitted feature projection changes the dimensionality of transformed numeric rows.
Variance selector learns feature support from held-out rows · case 02
The fitted feature projection changes the dimensionality of transformed numeric rows.
Variance selector learns feature support from held-out rows · case 03
The fitted feature projection changes the dimensionality of transformed numeric rows.
Variance selector learns feature support from held-out rows · case 04
The fitted feature projection changes the dimensionality of transformed numeric rows.
Variance selector learns feature support from held-out rows · case 05
The fitted feature projection changes the dimensionality of transformed numeric rows.
Variance selector includes a feature at the strict cutoff · case 01
The fitted feature projection changes the dimensionality of transformed numeric rows.
Variance selector includes a feature at the strict cutoff · case 02
The fitted feature projection changes the dimensionality of transformed numeric rows.
Variance selector includes a feature at the strict cutoff · case 03
The fitted feature projection changes the dimensionality of transformed numeric rows.
Variance selector includes a feature at the strict cutoff · case 04
The fitted feature projection changes the dimensionality of transformed numeric rows.
Variance selector includes a feature at the strict cutoff · case 05
The fitted feature projection changes the dimensionality of transformed numeric rows.
Training frequency encoding uses held-out rows while fitting · case 01
Training frequency encoding uses held-out rows while fitting.
Training frequency encoding uses held-out rows while fitting · case 02
Training frequency encoding uses held-out rows while fitting.
Training frequency encoding uses held-out rows while fitting · case 03
Training frequency encoding uses held-out rows while fitting.
Training frequency encoding uses held-out rows while fitting · case 04
Training frequency encoding uses held-out rows while fitting.
Training frequency encoding uses held-out rows while fitting · case 05
Training frequency encoding uses held-out rows while fitting.
Training frequency encoding applies fitted state incorrectly · case 01
Training frequency encoding applies fitted state incorrectly.
Training frequency encoding applies fitted state incorrectly · case 02
Training frequency encoding applies fitted state incorrectly.
Training frequency encoding applies fitted state incorrectly · case 03
Training frequency encoding applies fitted state incorrectly.
Training frequency encoding applies fitted state incorrectly · case 04
Training frequency encoding applies fitted state incorrectly.
Training frequency encoding applies fitted state incorrectly · case 05
Training frequency encoding applies fitted state incorrectly.
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 ↗