Tags

Tags give the ability to mark specific points in history as being important

0.0.21

691814e6 · Remove a leftover from a merge · Jul 02, 2021
0.0.20

88e413c6 · Bump version number · May 03, 2021
0.0.19

873856e2 · Fix the scripts.evaluate CLI · Aug 29, 2020
0.0.18

c3aab4ef · Make get_ndcg produce confidence intervals · Aug 27, 2020
0.0.17

f777489d · evaluate_run @ evaluate.py: support for ranks starting at zero (cont.) · Aug 25, 2020
0.0.16

394a85c8 · Support specifying subset from the CLO · Aug 24, 2020
0.0.15

2d2d8d87 · Add common.get_judgement · Jul 21, 2020
0.0.14

0b94ae2e · Remove topics B.58 and B.65 from qrel_task2*.tsv · Jul 17, 2020
0.0.13

de8752c0 · Support computing NDCG' score of an ARQMath submission from the CLI · Jul 11, 2020
0.0.12

b844217e · Add task2-topics-formula_ids.V.1.1 task (cont.) · Jun 03, 2020
0.0.11

a1439cf8 · Rename Mr. Random to xrando42 · Jun 02, 2020
0.0.10

63708218 · Create per-task leaderboards · Jun 01, 2020
0.0.9

b01fbaf7 · Merge branch 'master' of gitlab.fi.muni.cz:xstefan3/arqmath-eval · Jun 01, 2020
0.0.8

5b796f63 · Parallelize scripts.evaluate and support LEGEND.md · May 11, 2020
0.0.7

15faa1af · Add random system performance to the leaderboards · May 07, 2020
0.0.6

13217011 · Fix scripts.common.get_random_ndcg · May 06, 2020
0.0.5

db16de5f · Fix scripts.common.get_topics and get_judged_documents · May 06, 2020
0.0.4

cfd526ae · Add small-validation subset for the task1-votes task (cont.) · Apr 25, 2020
0.0.3

8a145e95 · Use only top 1000 results in the runs (cont.) · Apr 25, 2020
0.0.2

bcf29452 · Fix SIGSEGV · Apr 24, 2020

Prev
1
2
Next