eval-harness

dataset

few_nerd_56

56 items · 0 arms. Headline: each arm's own primary metric, mean over its items; arms with different primary metrics are not ranked against each other.

Open its sheet

goals: Named-entity extraction (Few-NERD)

01arms

scored against silverscored by a judgewrote the reference it is scored againstscored against a label set, not a reference setunmarked rows are scored against gold

0 shown
armmetricmeanitemscost per itemspeed per itemrunsscored against

02what's inside

56 items, text, 5–61 words (median 24, middle half 16–33).

Source: DFKI-SLT/few-nerd (test split). The text stays there; each item below links to its row.

010205–10 words: 611–16 words: 1117–22 words: 623–28 words: 1329–34 words: 935–40 words: 241–46 words: 447–52 words: 153–58 words: 359–64 words: 15–1011–1617–2223–2829–3435–4041–4647–5253–5859–64

the gold

gold/few_nerd_56: a list per item, 0–13 entries, median 2

56 shown
itemwordsgoldopen
009e011601e7322 entriessource ↗
0d9666f7f385230 entriessource ↗
0e88aabc5a04170 entriessource ↗
0fd56d48992d50 entriessource ↗
114599c4db48272 entriessource ↗
154350ae6e7f334 entriessource ↗
184098570107112 entriessource ↗
1985ab09043b162 entriessource ↗
1996f8ce65e3365 entriessource ↗
1e39a6ccdcf8314 entriessource ↗
1f007e7e7bc7362 entriessource ↗
225a2c68e43e81 entriessource ↗
259eccd9c019285 entriessource ↗
2708ce3cf54a162 entriessource ↗
2a41dc156fa9111 entriessource ↗
3508a3a3b41d263 entriessource ↗
353f0f464182111 entriessource ↗
3abb3b9915ef242 entriessource ↗
45a806c770c26113 entriessource ↗
4a6a00d4b489232 entriessource ↗
4b6ab1b30460174 entriessource ↗
5418a048089c324 entriessource ↗
59ff807150be503 entriessource ↗
5a648df06391220 entriessource ↗
61d02cfeea14183 entriessource ↗
63a55a54089c426 entriessource ↗
675c0e87cbd9331 entriessource ↗
68495a46e487164 entriessource ↗
7134935983e3260 entriessource ↗
756f937ac1ca243 entriessource ↗
7779c6667d6d252 entriessource ↗
815027679a00342 entriessource ↗
9e6f8f7c28a6152 entriessource ↗
ac3383156b9f264 entriessource ↗
b0d96c600ed9436 entriessource ↗
b1bd7568935c102 entriessource ↗
b1dfb240c31f333 entriessource ↗
b2283442b299313 entriessource ↗
b8bc97b4949d263 entriessource ↗
be34c5ea1240101 entriessource ↗
c12a0d572623536 entriessource ↗
c463913bc497430 entriessource ↗
c51442586d8e154 entriessource ↗
c652a25da2f9545 entriessource ↗
c7d2d8aa9755233 entriessource ↗
d27225312792142 entriessource ↗
d2bb81825498418 entriessource ↗
d837cd062513211 entriessource ↗
d9d3911536f2110 entriessource ↗
dcc5b5ca25ad241 entriessource ↗
ee24c587d35871 entriessource ↗
ee90f2323bf7122 entriessource ↗
efd76ea1d6ce101 entriessource ↗
f56f1708001a536 entriessource ↗
f5708db0e156303 entriessource ↗
fac5fa7ae1d1172 entriessource ↗

Each row is the profile evh dataset-items --dataset-id few_nerd_56 prints; inspect opens the item in the inspector with the dataset's largest group of comparable arms, and its text where the inspector runs on a machine that has it.

03reference sets

04labels

No labels yet. A sheet to fill: evh label-sheet --dataset-id few_nerd_56 --out sheet.csv; a run's outputs as a model set: evh label-from-run --run R --set S.