Regenerate: python3 harness/summarize.py > docs/results-summary.md
(see that script’s docstring for metric semantics; do not hand-edit)
| problem | arm | correct | abstain | vote | median | mean | worst |
|---|---|---|---|---|---|---|---|
| p0977 | collaborative | 5/5 | 0 | correct | 4.3m | 5.6m | 11.3m |
| p0977 | solo | 4/5 | 1 | correct | 10.1m | 17.1m | 39.8m |
| p0978 | collaborative | 5/5 | 0 | correct | 1.3m | 1.2m | 1.3m |
| p0978 | solo | 5/5 | 0 | correct | 0.9m | 1.0m | 1.2m |
| p0979 | collaborative | 5/5 | 0 | correct | 2.0m | 2.3m | 3.8m |
| p0979 | solo | 5/5 | 0 | correct | 4.6m | 13.0m | 29.9m |
| p0980 | collaborative | 5/5 | 0 | correct | 1.5m | 1.5m | 2.0m |
| p0980 | solo | 5/5 | 0 | correct | 1.4m | 1.4m | 1.6m |
| p0981 | collaborative | 5/5 | 0 | correct | 1.6m | 1.6m | 1.9m |
| p0981 | solo | 4/5 | 0 | correct | 2.5m | 7.7m | 30.1m |
| p0982 | collaborative | 4/5 | 0 | correct | 3.4m | 4.9m | 11.8m |
| p0982 | solo | 5/5 | 0 | correct | 6.7m | 9.7m | 27.4m |
| p0984 | collaborative | 5/5 | 0 | correct | 5.1m | 5.2m | 5.9m |
| p0984 | solo | 1/5 | 3 | TIE | 39.8m | 29.2m | 39.8m |
| p0985 | collaborative | 5/5 | 0 | correct | 2.3m | 3.6m | 7.6m |
| p0985 | solo | 5/5 | 0 | correct | 2.7m | 9.0m | 31.5m |
| p0986 | collaborative | 0/5 | 4 | WRONG | 40.0m | 38.8m | 40.1m |
| p0986 | solo | 0/5 | 4 | WRONG | 40.0m | 40.0m | 40.0m |
| p0987 | collaborative | 5/5 | 0 | correct | 1.4m | 1.9m | 3.1m |
| p0987 | solo | 5/5 | 0 | correct | 4.0m | 9.9m | 30.2m |
| p0988 | collaborative | 5/5 | 0 | correct | 0.9m | 0.9m | 1.0m |
| p0988 | solo | 5/5 | 0 | correct | 0.8m | 1.0m | 1.4m |
| p0989 | collaborative | 5/5 | 0 | correct | 29.6m | 24.2m | 29.7m |
| p0989 | solo | 0/5 | 3 | TIE | 40.0m | 37.5m | 40.0m |
| p0990 | collaborative | 5/5 | 0 | correct | 3.9m | 5.6m | 9.9m |
| p0990 | solo | 4/5 | 1 | correct | 16.1m | 16.7m | 39.9m |
| p0991 | collaborative | 5/5 | 0 | correct | 3.1m | 4.2m | 10.9m |
| p0991 | solo | 5/5 | 0 | correct | 5.7m | 9.7m | 29.8m |
| p0992 | collaborative | 5/5 | 0 | correct | 1.8m | 1.7m | 2.1m |
| p0992 | solo | 5/5 | 0 | correct | 1.2m | 1.3m | 1.9m |
| p0993 | collaborative | 5/5 | 0 | correct | 3.5m | 5.5m | 13.7m |
| p0993 | solo | 3/5 | 1 | correct | 30.9m | 23.6m | 39.4m |
| p0994 | collaborative | 5/5 | 0 | correct | 19.5m | 21.6m | 29.9m |
| p0994 | solo | 3/5 | 0 | correct | 15.4m | 15.6m | 21.8m |
| p0995 | collaborative | 1/5 | 4 | correct | 40.0m | 37.0m | 40.0m |
| p0995 | solo | 0/5 | 5 | - | 39.9m | 39.9m | 39.9m |
| p0996 | collaborative | 5/5 | 0 | correct | 3.5m | 10.2m | 29.9m |
| p0996 | solo | 2/5 | 0 | correct | 4.7m | 9.6m | 31.4m |
| p0997 | collaborative | 5/5 | 0 | correct | 1.5m | 7.2m | 30.1m |
| p0997 | solo | 5/5 | 0 | correct | 1.6m | 7.3m | 29.9m |
| p0998 | collaborative | 0/5 | 4 | WRONG | 39.9m | 39.9m | 40.0m |
| p0998 | solo | 0/5 | 5 | - | 39.5m | 39.5m | 39.5m |
| p0999 | collaborative | 5/5 | 0 | correct | 4.0m | 8.9m | 31.1m |
| p0999 | solo | 5/5 | 0 | correct | 4.4m | 9.9m | 34.0m |
| p1000 | collaborative | 5/5 | 0 | correct | 1.7m | 2.3m | 4.5m |
| p1000 | solo | 5/5 | 0 | correct | 1.7m | 7.3m | 29.4m |
| p1001 | collaborative | 5/5 | 0 | correct | 2.7m | 3.0m | 4.1m |
| p1001 | solo | 4/5 | 0 | correct | 4.5m | 6.2m | 12.2m |
| p1002 | collaborative | 5/5 | 0 | correct | 0.9m | 0.9m | 1.0m |
| p1002 | solo | 5/5 | 0 | correct | 0.9m | 1.0m | 1.2m |
| p1003 | collaborative | 5/5 | 0 | correct | 3.8m | 16.7m | 40.0m |
| p1003 | solo | 5/5 | 0 | correct | 3.7m | 10.2m | 31.4m |
| p1004 | collaborative | 5/5 | 0 | correct | 3.4m | 3.6m | 5.3m |
| p1004 | solo | 4/5 | 1 | correct | 1.5m | 9.3m | 39.9m |
| p1005 | collaborative | 5/5 | 0 | correct | 0.7m | 0.6m | 0.7m |
| p1005 | solo | 5/5 | 0 | correct | 0.7m | 0.7m | 0.8m |
| p1006 | collaborative | 0/5 | 0 | WRONG | 30.3m | 26.8m | 32.0m |
| p1006 | solo | 0/5 | 0 | TIE | 30.1m | 30.4m | 31.1m |
| p1007 | collaborative | 5/5 | 0 | correct | 30.0m | 23.1m | 32.8m |
| p1007 | solo | 4/5 | 1 | correct | 9.6m | 17.7m | 39.9m |