scrubdata / eval /results /money_table.json
OpenAI Codex
deploy: add sponsor:openai tag (Best Use of Codex) + Codex-hardened build
16dc556
Raw
History Blame Contribute Delete
1.4 kB
[
{
"system": "grounded (ours)",
"north": 0.22450647183198283,
"north_ci": 0.0041127657308937466,
"real_f1": 0.2248342298406393,
"real_f1_per_seed": [
0.22483422984063933,
0.22483422984063933,
0.22483422984063933
],
"inj_f1": 0.22437180007268678,
"damage": 0.09228345663981756,
"abstain": 1.0,
"n_datasets": 65,
"seeds": [
7,
17,
27
]
},
{
"system": "OpenRefine fingerprint",
"north": 0.21052532670820204,
"north_ci": 0.00010526877274414428,
"real_f1": 0.03919215053000111,
"real_f1_per_seed": [
0.03919215053000111,
0.03919215053000111,
0.03919215053000111
],
"inj_f1": 0.2817577151327488,
"damage": 0.0009339582253623949,
"abstain": 1.0,
"n_datasets": 65,
"seeds": [
7,
17,
27
]
},
{
"system": "OpenRefine kNN",
"north": 0.12214138232309169,
"north_ci": 0.002346570532929038,
"real_f1": 0.058356518613316845,
"real_f1_per_seed": [
0.058356518613316845,
0.058356518613316845,
0.058356518613316845
],
"inj_f1": 0.1485689316939941,
"damage": 0.09577749923124519,
"abstain": 1.0,
"n_datasets": 65,
"seeds": [
7,
17,
27
]
},
{
"system": "no-op",
"north": 0.0,
"north_ci": 0.0,
"real_f1": 0.0,
"real_f1_per_seed": [
0.0,
0.0,
0.0
],
"inj_f1": 0.0,
"damage": 0.0,
"abstain": 1.0,
"n_datasets": 65,
"seeds": [
7,
17,
27
]
}
]