dataset
cnn_dailymail_dm200
200 items · 5 arms. Headline: each arm's own primary metric, mean over its items; arms with different primary metrics are not ranked against each other.
Inspect the 5 arms on coverage, scored against gold/cnn_dailymail_dm200Open its sheet
goals: Short news summaries (CNN)
01arms
scored against silverscored by a judgescored against a label set, not a reference setunmarked rows are scored against gold
| arm | metric | mean | items | cost per item | speed per item | runs | scored against | |
|---|---|---|---|---|---|---|---|---|
| cnn_bart_l_dm200_v1 | coverage | 0.443 | 200 | $0.000000 · 934 tok | p50 10,251 · p95 16,948 ms | 1 | gold/cnn_dailymail_dm200 gold | inspect |
| cnn_bart_m_dm200_v1 | coverage | 0.443 | 200 | $0.000000 · 940 tok | p50 6,927 · p95 11,473 ms | 1 | gold/cnn_dailymail_dm200 gold | inspect |
| cnn_bart_s_dm200_v1 | coverage | 0.405 | 200 | $0.000000 · 914 tok | p50 4,207 · p95 5,571 ms | 1 | gold/cnn_dailymail_dm200 gold | inspect |
| cnn_lead3_dm200_v1 | coverage | 0.370 | 200 | $0.000000 | p50 0.1 · p95 0.27 ms | 1 | gold/cnn_dailymail_dm200 gold | inspect |
| cnn_bart_l_xsum_dm200_v1 | coverage | 0.152 | 200 | $0.000000 · 874 tok | p50 5,103 · p95 8,017 ms | 1 | gold/cnn_dailymail_dm200 gold | inspect |
02what's inside
200 items, text, 110–1844 words (median 605, middle half 422–859).
Source: abisee/cnn_dailymail (test split). The text stays there; each item below links to its row.
the gold
gold/cnn_dailymail_dm200: text, 22–130 words, median 54
| item | words | gold | open |
|---|---|---|---|
00bfcb9d07fa | 523 | 42 words | source ↗ · inspect |
01205b429804 | 330 | 41 words | source ↗ · inspect |
017738d8c5fc | 442 | 49 words | source ↗ · inspect |
051db32933d7 | 478 | 45 words | source ↗ · inspect |
0538c4e50be6 | 886 | 66 words | source ↗ · inspect |
070cff525ba5 | 679 | 101 words | source ↗ · inspect |
086d95421394 | 531 | 54 words | source ↗ · inspect |
096dda15ca27 | 670 | 78 words | source ↗ · inspect |
0a09b7008372 | 1108 | 80 words | source ↗ · inspect |
0fa083cb7da1 | 341 | 83 words | source ↗ · inspect |
128939500473 | 867 | 130 words | source ↗ · inspect |
14514f8448a1 | 227 | 52 words | source ↗ · inspect |
18a5d47e83e9 | 259 | 42 words | source ↗ · inspect |
19d910abd292 | 1411 | 84 words | source ↗ · inspect |
1a343914e243 | 420 | 39 words | source ↗ · inspect |
1bd44b6e16bf | 1665 | 81 words | source ↗ · inspect |
1c69b5c1b2fb | 883 | 70 words | source ↗ · inspect |
1d965b7ef3e3 | 281 | 61 words | source ↗ · inspect |
1ddc1d165b74 | 427 | 56 words | source ↗ · inspect |
1e717ed4d3b3 | 809 | 34 words | source ↗ · inspect |
21030573ff6b | 893 | 90 words | source ↗ · inspect |
22224ab649ac | 1101 | 52 words | source ↗ · inspect |
225f2330a647 | 228 | 59 words | source ↗ · inspect |
226e8811bb8b | 852 | 64 words | source ↗ · inspect |
24f53c358c67 | 556 | 38 words | source ↗ · inspect |
289e33599f43 | 866 | 54 words | source ↗ · inspect |
2aa60a7b1f02 | 330 | 64 words | source ↗ · inspect |
2dfa0295b482 | 564 | 38 words | source ↗ · inspect |
2e2e6c661375 | 613 | 51 words | source ↗ · inspect |
2e40e0934dde | 852 | 50 words | source ↗ · inspect |
2f13a3fa89fa | 417 | 35 words | source ↗ · inspect |
304dfe02b1bd | 762 | 51 words | source ↗ · inspect |
32076aaf7374 | 275 | 51 words | source ↗ · inspect |
324799aced1d | 290 | 59 words | source ↗ · inspect |
32b1f281483c | 422 | 53 words | source ↗ · inspect |
349d234d54b5 | 556 | 59 words | source ↗ · inspect |
36c34f4ffa88 | 168 | 40 words | source ↗ · inspect |
36d0dfb24f45 | 425 | 36 words | source ↗ · inspect |
37a8f67bffe7 | 1148 | 62 words | source ↗ · inspect |
37b736205317 | 739 | 66 words | source ↗ · inspect |
388e3456094f | 330 | 65 words | source ↗ · inspect |
3b8dc47341aa | 754 | 53 words | source ↗ · inspect |
3c92b3c36e05 | 1813 | 127 words | source ↗ · inspect |
3d06967875a8 | 747 | 45 words | source ↗ · inspect |
3da318564d11 | 428 | 34 words | source ↗ · inspect |
3da4c2801fcc | 343 | 64 words | source ↗ · inspect |
3dd47c7a4db1 | 266 | 74 words | source ↗ · inspect |
4006ed714a50 | 625 | 48 words | source ↗ · inspect |
409d09b6f4fd | 742 | 52 words | source ↗ · inspect |
41ea154a71ba | 1306 | 56 words | source ↗ · inspect |
43a900fa3160 | 705 | 106 words | source ↗ · inspect |
45ca61ee5a26 | 1250 | 37 words | source ↗ · inspect |
46931c4bd3a6 | 1128 | 37 words | source ↗ · inspect |
47b1af381aac | 645 | 78 words | source ↗ · inspect |
48ba76cd72d1 | 341 | 53 words | source ↗ · inspect |
48f52d03996f | 634 | 50 words | source ↗ · inspect |
4ee59a5bf1ef | 354 | 75 words | source ↗ · inspect |
518a7c882001 | 203 | 36 words | source ↗ · inspect |
53473bfa17eb | 825 | 41 words | source ↗ · inspect |
53e798bb1a4f | 287 | 22 words | source ↗ · inspect |
5584b67ffb2a | 1700 | 56 words | source ↗ · inspect |
55b8192b89cc | 277 | 42 words | source ↗ · inspect |
58ca33afaedb | 957 | 55 words | source ↗ · inspect |
5acf7aba8351 | 378 | 86 words | source ↗ · inspect |
5b286830ff35 | 794 | 56 words | source ↗ · inspect |
5c0a90c2e1a5 | 852 | 100 words | source ↗ · inspect |
5fdd0e36b6c9 | 414 | 73 words | source ↗ · inspect |
60f4f74a0e77 | 493 | 54 words | source ↗ · inspect |
62271db1dd48 | 598 | 50 words | source ↗ · inspect |
625c26dea34c | 893 | 65 words | source ↗ · inspect |
63b17fa94a31 | 456 | 69 words | source ↗ · inspect |
685573e9aaed | 1020 | 65 words | source ↗ · inspect |
6a54725e5444 | 852 | 110 words | source ↗ · inspect |
6bcdaaa4ce3f | 1044 | 47 words | source ↗ · inspect |
6c1341bedf92 | 234 | 36 words | source ↗ · inspect |
6c6f1dbdfc24 | 508 | 76 words | source ↗ · inspect |
6caae1d09765 | 837 | 50 words | source ↗ · inspect |
6d1328c719e6 | 494 | 50 words | source ↗ · inspect |
6d580f4aef62 | 1058 | 106 words | source ↗ · inspect |
6d65c417c889 | 314 | 54 words | source ↗ · inspect |
6e201472a236 | 859 | 87 words | source ↗ · inspect |
6e4055886499 | 470 | 70 words | source ↗ · inspect |
700b448e4556 | 1407 | 57 words | source ↗ · inspect |
7428b0892cc1 | 493 | 66 words | source ↗ · inspect |
74468085fc39 | 690 | 70 words | source ↗ · inspect |
7691a520145a | 782 | 107 words | source ↗ · inspect |
78492369ef4f | 272 | 31 words | source ↗ · inspect |
7afdcaba2fd0 | 471 | 37 words | source ↗ · inspect |
7b27f7ffb9c9 | 464 | 49 words | source ↗ · inspect |
7d15a0b9f8c4 | 701 | 52 words | source ↗ · inspect |
7d8389d498d7 | 1307 | 29 words | source ↗ · inspect |
7df38beb49dd | 689 | 67 words | source ↗ · inspect |
822fd6ef8463 | 547 | 38 words | source ↗ · inspect |
831ad546d0ac | 397 | 49 words | source ↗ · inspect |
84c8f7cbb37c | 785 | 54 words | source ↗ · inspect |
854e84296958 | 710 | 43 words | source ↗ · inspect |
862bbd27abe6 | 750 | 75 words | source ↗ · inspect |
87626b6f72f2 | 836 | 32 words | source ↗ · inspect |
894695f31517 | 596 | 67 words | source ↗ · inspect |
89baf55b264e | 490 | 60 words | source ↗ · inspect |
8a5d61134503 | 673 | 32 words | source ↗ · inspect |
8a9a4d935893 | 623 | 60 words | source ↗ · inspect |
8c65ea56cda0 | 451 | 31 words | source ↗ · inspect |
8f8c6175fd14 | 290 | 55 words | source ↗ · inspect |
9107fbb67605 | 555 | 46 words | source ↗ · inspect |
9130155af3f9 | 1844 | 43 words | source ↗ · inspect |
91b7d2311527 | 110 | 35 words | source ↗ · inspect |
92ce51c6b1b2 | 1160 | 61 words | source ↗ · inspect |
9307675298b5 | 675 | 72 words | source ↗ · inspect |
94e9c63bb761 | 742 | 50 words | source ↗ · inspect |
98274af48dff | 408 | 55 words | source ↗ · inspect |
992a8f57a533 | 605 | 60 words | source ↗ · inspect |
9a31ceff27ac | 955 | 33 words | source ↗ · inspect |
9aba5324e32e | 466 | 33 words | source ↗ · inspect |
9d5a64da66af | 1274 | 43 words | source ↗ · inspect |
9dd43f7237d0 | 617 | 105 words | source ↗ · inspect |
9ef9bcf7b102 | 592 | 48 words | source ↗ · inspect |
a290765c547b | 347 | 83 words | source ↗ · inspect |
a3238a368672 | 1074 | 64 words | source ↗ · inspect |
a36ff64c7a7f | 1542 | 44 words | source ↗ · inspect |
a3b6201aca77 | 425 | 63 words | source ↗ · inspect |
a726904222fc | 1700 | 77 words | source ↗ · inspect |
a7486968048b | 536 | 72 words | source ↗ · inspect |
a80add45ec40 | 422 | 35 words | source ↗ · inspect |
a864b02f2f80 | 786 | 46 words | source ↗ · inspect |
a9d468537ca8 | 435 | 77 words | source ↗ · inspect |
a9fdb9e984bb | 930 | 75 words | source ↗ · inspect |
ae49ea8ca263 | 442 | 53 words | source ↗ · inspect |
b0348c9c7e26 | 253 | 49 words | source ↗ · inspect |
b1585b611a90 | 434 | 37 words | source ↗ · inspect |
b18caeefd6e3 | 391 | 89 words | source ↗ · inspect |
b23343f2af2a | 542 | 52 words | source ↗ · inspect |
b45ab07ab745 | 1085 | 38 words | source ↗ · inspect |
b52cb9c37221 | 544 | 50 words | source ↗ · inspect |
b5596ad0d22c | 603 | 53 words | source ↗ · inspect |
b57ea4a4c707 | 1133 | 38 words | source ↗ · inspect |
b5a377afaf93 | 120 | 38 words | source ↗ · inspect |
b773c7f158ae | 763 | 42 words | source ↗ · inspect |
b77e01dfab76 | 479 | 50 words | source ↗ · inspect |
b8139bbbf3d7 | 398 | 72 words | source ↗ · inspect |
b8f746629678 | 1094 | 47 words | source ↗ · inspect |
b96ef482f5e6 | 1029 | 58 words | source ↗ · inspect |
bcbdb86d4eba | 943 | 52 words | source ↗ · inspect |
bcefd57fbf8c | 418 | 61 words | source ↗ · inspect |
be575882b45f | 619 | 50 words | source ↗ · inspect |
bf45bdab5ec8 | 908 | 53 words | source ↗ · inspect |
bffca412fd17 | 755 | 80 words | source ↗ · inspect |
c0daee326074 | 1027 | 67 words | source ↗ · inspect |
c3396652f6e7 | 1125 | 61 words | source ↗ · inspect |
c3608b0a9543 | 640 | 49 words | source ↗ · inspect |
c37431a19d84 | 491 | 70 words | source ↗ · inspect |
c4b1d91028a2 | 551 | 69 words | source ↗ · inspect |
c4f93b339ca5 | 251 | 36 words | source ↗ · inspect |
c57e46857d5a | 1028 | 58 words | source ↗ · inspect |
c58477f5ac31 | 1137 | 88 words | source ↗ · inspect |
c5dcaf5c23ff | 1595 | 54 words | source ↗ · inspect |
c715c8dcc0fc | 617 | 44 words | source ↗ · inspect |
cb7a72d78d5f | 291 | 81 words | source ↗ · inspect |
cbf34d5ddfac | 489 | 53 words | source ↗ · inspect |
cd064649d106 | 392 | 36 words | source ↗ · inspect |
d0767fea9058 | 578 | 63 words | source ↗ · inspect |
d0b4d71e6d02 | 328 | 33 words | source ↗ · inspect |
d18f4335544e | 745 | 95 words | source ↗ · inspect |
d243e0bdc63d | 1096 | 76 words | source ↗ · inspect |
d297355a0186 | 304 | 45 words | source ↗ · inspect |
d453bd848a14 | 584 | 53 words | source ↗ · inspect |
d4bcbba8a280 | 640 | 77 words | source ↗ · inspect |
d4f5e19dfa49 | 1528 | 59 words | source ↗ · inspect |
d5e3add9f887 | 967 | 42 words | source ↗ · inspect |
d6e1dbb11293 | 1357 | 109 words | source ↗ · inspect |
d7972cbb7f52 | 1186 | 46 words | source ↗ · inspect |
d987f48e7413 | 403 | 39 words | source ↗ · inspect |
da653ae66413 | 165 | 38 words | source ↗ · inspect |
dc4c106fba9c | 415 | 76 words | source ↗ · inspect |
dc6af0351303 | 358 | 43 words | source ↗ · inspect |
e0f1759fd452 | 496 | 52 words | source ↗ · inspect |
e12a6d81e715 | 780 | 58 words | source ↗ · inspect |
e33105857efc | 1064 | 63 words | source ↗ · inspect |
e8fd26eb7eef | 183 | 48 words | source ↗ · inspect |
eaa26b0b349b | 274 | 55 words | source ↗ · inspect |
eb98777b9704 | 541 | 50 words | source ↗ · inspect |
ec8df2c3e900 | 621 | 48 words | source ↗ · inspect |
ef581231850a | 520 | 54 words | source ↗ · inspect |
f069049a0374 | 507 | 53 words | source ↗ · inspect |
f0976e50cbdd | 1069 | 55 words | source ↗ · inspect |
f1a5b86c3699 | 273 | 36 words | source ↗ · inspect |
f2c5101a0773 | 668 | 54 words | source ↗ · inspect |
f30645fc7f73 | 1740 | 66 words | source ↗ · inspect |
f3716b374462 | 450 | 111 words | source ↗ · inspect |
f48a1745c08f | 776 | 98 words | source ↗ · inspect |
f5aa0a5183f7 | 365 | 50 words | source ↗ · inspect |
f5ab37eb415d | 435 | 52 words | source ↗ · inspect |
f60256b9f993 | 430 | 39 words | source ↗ · inspect |
f91a6e3839c7 | 813 | 64 words | source ↗ · inspect |
f99f7c90a4ef | 681 | 50 words | source ↗ · inspect |
f9a1388b5b53 | 898 | 52 words | source ↗ · inspect |
fa6a8b996f1a | 260 | 37 words | source ↗ · inspect |
fc2d95d4b9e1 | 526 | 41 words | source ↗ · inspect |
fd48dbfe1172 | 607 | 69 words | source ↗ · inspect |
fe4531d4b8d7 | 419 | 57 words | source ↗ · inspect |
Each row is the profile evh dataset-items --dataset-id cnn_dailymail_dm200 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
- gold/cnn_dailymail_dm200 gold · promoted from person the dataset's authors
04labels
No labels yet. A sheet to fill: evh label-sheet --dataset-id cnn_dailymail_dm200 --out sheet.csv; a run's outputs as a model set: evh label-from-run --run R --set S.