eval-harness

dataset

cnn_dailymail_200

200 items · 153 arms. Headline: each arm's own primary metric, mean over its items; arms with different primary metrics are not ranked against each other.

baseline, promoted 2026-10-25

cnn_bart_l_n200_v1

bart_l (BART-large-CNN, MIT, $0 on a CPU) leads on coverage at 0.3461, not significantly different from deepseek_m (0.3460, p = 0.99), for CNN-style text; rent deepseek_m if you need speed. REPORT_SUMMARIZATION, executive summary.

Inspect the 35 arms on coverage, scored against gold/cnn_dailymail_200Inspect the 29 arms on coverage, scored against silver/cnn_dailymail_200Inspect the 29 arms on judge_score, judged by judge-summ-v1Inspect the 29 arms on judge_score, judged by judge-summ-v2Inspect the 29 arms on judge_won, judged by judge-summ-pick-v1Inspect the 2 arms on judge_score_unvalidated, judged by judge-summ-pointwise-v1Open its sheet

goals: Short news summaries (CNN)

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

153 shown
armmetricmeanitemscost per itemspeed per itemrunsscored against
cnn_bart_l_n200_v1 baseline
run on mac-dev · Darwin/x86_64, 12 CPUs
coverage0.346200$0.000000 · 763 tokp50 10,724 · p95 14,371 ms1gold/cnn_dailymail_200 goldinspect
cnn_bart_l_n200_v1 · linux
run on Linux/x86_64, 4 CPUs
coverage0.346200$0.000000 · 763 tokp50 6,257 · p95 9,188 ms1gold/cnn_dailymail_200 goldinspect
cnn_deepseek_m_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.346200$0.000191 · 812 tokp50 1,497 · p95 2,924 ms1gold/cnn_dailymail_200 goldinspect
cnn_llama_l_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.339200$0.000195 · 805 tokp50 3,646 · p95 5,531 ms1gold/cnn_dailymail_200 goldinspect
cnn_llama_m_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.338200$0.000165 · 809 tokp50 2,682 · p95 11,240 ms1gold/cnn_dailymail_200 goldinspect
cnn_bart_m_n200_v1
run on Linux/x86_64, 4 CPUs
coverage0.337200$0.000000 · 766 tokp50 4,649 · p95 7,223 ms1gold/cnn_dailymail_200 goldinspect
cnn_bart_m_n200_v1 · linux
run on Linux/x86_64, 4 CPUs
coverage0.337200$0.000000 · 766 tokp50 4,108 · p95 6,463 ms1gold/cnn_dailymail_200 goldinspect
cnn_llama_s_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.333200$0.000111 · 814 tokp50 2,204 · p95 4,041 ms1gold/cnn_dailymail_200 goldinspect
cnn_deepseek_l_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.332200$0.000694 · 802 tokp50 2,354 · p95 4,380 ms1gold/cnn_dailymail_200 goldinspect
cnn_glm_m_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.332200$0.000497 · 803 tokp50 1,848 · p95 7,145 ms1gold/cnn_dailymail_200 goldinspect
cnn_deepseek_s_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.328200$0.000069 · 800 tokp50 2,237 · p95 5,644 ms1gold/cnn_dailymail_200 goldinspect
cnn_bart_s_n200_v1
run on Linux/x86_64, 4 CPUs
coverage0.328200$0.000000 · 761 tokp50 3,683 · p95 5,055 ms1gold/cnn_dailymail_200 goldinspect
cnn_bart_s_n200_v1 · linux
run on Linux/x86_64, 4 CPUs
coverage0.328200$0.000000 · 761 tokp50 3,387 · p95 4,550 ms1gold/cnn_dailymail_200 goldinspect
cnn_bart_s_n200_v1 · repeats
run on Linux/x86_64, 4 CPUs
coverage0.328200$0.000000 · 761 tokp50 3,708 · p95 4,822 ms1gold/cnn_dailymail_200 goldinspect
cnn_openai_m_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.327200$0.005358 · 786 tokp50 1,719 · p95 2,126 ms1gold/cnn_dailymail_200 goldinspect
cnn_openai_l_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.327200$0.002181 · 786 tokp50 1,735 · p95 2,381 ms1gold/cnn_dailymail_200 goldinspect
cnn_mistral_s_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.326200$0.000089 · 833 tokp50 2,573 · p95 5,142 ms1gold/cnn_dailymail_200 goldinspect
cnn_anthropic_s_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.324200$0.001305 · 897 tokp50 1,982 · p95 2,834 ms1gold/cnn_dailymail_200 goldinspect
cnn_anthropic_m_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.324200$0.003739 · 1,282 tokp50 2,992 · p95 3,675 ms1gold/cnn_dailymail_200 goldinspect
cnn_gemma_l_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.320200$0.000119 · 810 tokp50 1,817 · p95 6,172 ms1gold/cnn_dailymail_200 goldinspect
cnn_openai_s_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.317200$0.000836 · 793 tokp50 1,238 · p95 1,573 ms1gold/cnn_dailymail_200 goldinspect
cnn_anthropic_l_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.315200$0.009826 · 1,301 tokp50 3,259 · p95 4,718 ms1gold/cnn_dailymail_200 goldinspect
cnn_glm_s_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.314200$0.000152 · 786 tokp50 1,580 · p95 2,341 ms1gold/cnn_dailymail_200 goldinspect
cnn_gemma_m_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.314200$0.000077 · 812 tokp50 1,388 · p95 4,483 ms1gold/cnn_dailymail_200 goldinspect
cnn_glm_l_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.312200$0.000766 · 818 tokp50 2,351 · p95 12,758 ms1gold/cnn_dailymail_200 goldinspect
cnn_gemma_s_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.312200$0.000100 · 820 tokp50 5,933 · p95 12,255 ms1gold/cnn_dailymail_200 goldinspect
cnn_qwen_l_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.311200$0.000844 · 828 tokp50 2,732 · p95 4,428 ms1gold/cnn_dailymail_200 goldinspect
cnn_mistral_l_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.308200$0.000486 · 828 tokp50 2,272 · p95 51,619 ms1gold/cnn_dailymail_200 goldinspect
cnn_qwen_s_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.307200$0.000135 · 825 tokp50 7,855 · p95 108,807 ms1gold/cnn_dailymail_200 goldinspect
cnn_mistral_m_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.304200$0.000435 · 832 tokp50 2,495 · p95 4,801 ms1gold/cnn_dailymail_200 goldinspect
cnn_qwen_m_n200_v1
run on Darwin/x86_64, 12 CPUs
coverage0.303200$0.000331 · 826 tokp50 1,531 · p95 1,911 ms1gold/cnn_dailymail_200 goldinspect
cnn_lead3_n200_v1
run on mac-dev · Darwin/x86_64, 12 CPUs
coverage0.272200$0.000000p50 0.057 · p95 0.13 ms1gold/cnn_dailymail_200 goldinspect
cnn_lead3_n200_v1 · linux
run on Linux/x86_64, 4 CPUs
coverage0.272200$0.000000p50 0.063 · p95 0.15 ms1gold/cnn_dailymail_200 goldinspect
cnn_bart_l_xsum_n200_v1
run on Linux/x86_64, 4 CPUs
coverage0.207200$0.000000 · 725 tokp50 4,433 · p95 7,325 ms1gold/cnn_dailymail_200 goldinspect
cnn_bart_l_xsum_n200_v1 · linux
run on Linux/x86_64, 4 CPUs
coverage0.207200$0.000000 · 725 tokp50 3,934 · p95 7,054 ms1gold/cnn_dailymail_200 goldinspect
cnn_anthropic_l_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage1.000200$0.009826 · 1,301 tokp50 3,259 · p95 4,718 ms1silver/cnn_dailymail_200 silverinspect
cnn_anthropic_m_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.491200$0.003739 · 1,282 tokp50 2,992 · p95 3,675 ms1silver/cnn_dailymail_200 silverinspect
cnn_deepseek_m_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.471200$0.000191 · 812 tokp50 1,497 · p95 2,924 ms1silver/cnn_dailymail_200 silverinspect
cnn_anthropic_s_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.469200$0.001305 · 897 tokp50 1,982 · p95 2,834 ms1silver/cnn_dailymail_200 silverinspect
cnn_deepseek_l_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.399200$0.000694 · 802 tokp50 2,354 · p95 4,380 ms1silver/cnn_dailymail_200 silverinspect
cnn_qwen_l_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.398200$0.000844 · 828 tokp50 2,732 · p95 4,428 ms1silver/cnn_dailymail_200 silverinspect
cnn_glm_m_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.389200$0.000497 · 803 tokp50 1,848 · p95 7,145 ms1silver/cnn_dailymail_200 silverinspect
cnn_llama_s_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.388200$0.000111 · 814 tokp50 2,204 · p95 4,041 ms1silver/cnn_dailymail_200 silverinspect
cnn_deepseek_s_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.388200$0.000069 · 800 tokp50 2,237 · p95 5,644 ms1silver/cnn_dailymail_200 silverinspect
cnn_openai_s_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.384200$0.000836 · 793 tokp50 1,238 · p95 1,573 ms1silver/cnn_dailymail_200 silverinspect
cnn_mistral_s_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.382200$0.000089 · 833 tokp50 2,573 · p95 5,142 ms1silver/cnn_dailymail_200 silverinspect
cnn_qwen_m_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.381200$0.000331 · 826 tokp50 1,531 · p95 1,911 ms1silver/cnn_dailymail_200 silverinspect
cnn_glm_l_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.375200$0.000766 · 818 tokp50 2,351 · p95 12,758 ms1silver/cnn_dailymail_200 silverinspect
cnn_openai_l_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.371200$0.002181 · 786 tokp50 1,735 · p95 2,381 ms1silver/cnn_dailymail_200 silverinspect
cnn_llama_l_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.370200$0.000195 · 805 tokp50 3,646 · p95 5,531 ms1silver/cnn_dailymail_200 silverinspect
cnn_openai_m_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.359200$0.005358 · 786 tokp50 1,719 · p95 2,126 ms1silver/cnn_dailymail_200 silverinspect
cnn_llama_m_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.358200$0.000165 · 809 tokp50 2,682 · p95 11,240 ms1silver/cnn_dailymail_200 silverinspect
cnn_gemma_s_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.350200$0.000100 · 820 tokp50 5,933 · p95 12,255 ms1silver/cnn_dailymail_200 silverinspect
cnn_gemma_m_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.342200$0.000077 · 812 tokp50 1,388 · p95 4,483 ms1silver/cnn_dailymail_200 silverinspect
cnn_gemma_l_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.342200$0.000119 · 810 tokp50 1,817 · p95 6,172 ms1silver/cnn_dailymail_200 silverinspect
cnn_mistral_l_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.337200$0.000486 · 828 tokp50 2,272 · p95 51,619 ms1silver/cnn_dailymail_200 silverinspect
cnn_qwen_s_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.334200$0.000135 · 825 tokp50 7,855 · p95 108,807 ms1silver/cnn_dailymail_200 silverinspect
cnn_mistral_m_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.320200$0.000435 · 832 tokp50 2,495 · p95 4,801 ms1silver/cnn_dailymail_200 silverinspect
cnn_bart_m_n200_v1 · silver
run on Linux/x86_64, 4 CPUs
coverage0.320200$0.000000 · 766 tokp50 4,649 · p95 7,223 ms1silver/cnn_dailymail_200 silverinspect
cnn_bart_l_n200_v1 · silver
run on mac-dev · Darwin/x86_64, 12 CPUs
coverage0.317200$0.000000 · 763 tokp50 10,724 · p95 14,371 ms1silver/cnn_dailymail_200 silverinspect
cnn_bart_s_n200_v1 · silver
run on Linux/x86_64, 4 CPUs
coverage0.306200$0.000000 · 761 tokp50 3,683 · p95 5,055 ms1silver/cnn_dailymail_200 silverinspect
cnn_glm_s_n200_v1 · silver
run on Darwin/x86_64, 12 CPUs
coverage0.303200$0.000152 · 786 tokp50 1,580 · p95 2,341 ms1silver/cnn_dailymail_200 silverinspect
cnn_lead3_n200_v1 · silver
run on mac-dev · Darwin/x86_64, 12 CPUs
coverage0.300200$0.000000p50 0.057 · p95 0.13 ms1silver/cnn_dailymail_200 silverinspect
cnn_bart_l_xsum_n200_v1 · silver
run on Linux/x86_64, 4 CPUs
coverage0.137200$0.000000 · 725 tokp50 4,433 · p95 7,325 ms1silver/cnn_dailymail_200 silverinspect
cnn_anthropic_l_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.976197$0.009811 · 1,298 tokp50 3,258 · p95 4,724 ms1judge judge-summ-v1inspect
cnn_anthropic_m_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.963197$0.003730 · 1,278 tokp50 2,992 · p95 3,678 ms1judge judge-summ-v1inspect
cnn_anthropic_s_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.952197$0.001301 · 894 tokp50 1,981 · p95 2,838 ms1judge judge-summ-v1inspect
cnn_deepseek_m_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.923197$0.000191 · 809 tokp50 1,489 · p95 2,889 ms1judge judge-summ-v1inspect
cnn_anthropic_l_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.888200$0.009826 · 1,301 tokp50 3,259 · p95 4,718 ms1judge judge-summ-v2inspect
cnn_deepseek_l_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.877197$0.000685 · 799 tokp50 2,350 · p95 4,386 ms1judge judge-summ-v1inspect
cnn_qwen_m_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.876197$0.000330 · 824 tokp50 1,529 · p95 1,913 ms1judge judge-summ-v1inspect
cnn_glm_m_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.861197$0.000497 · 801 tokp50 1,853 · p95 7,153 ms1judge judge-summ-v1inspect
cnn_deepseek_m_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.854200$0.000191 · 812 tokp50 1,497 · p95 2,924 ms1judge judge-summ-v2inspect
cnn_openai_l_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.847200$0.002181 · 786 tokp50 1,735 · p95 2,381 ms1judge judge-summ-v2inspect
cnn_openai_s_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.825197$0.000834 · 791 tokp50 1,238 · p95 1,588 ms1judge judge-summ-v1inspect
cnn_deepseek_s_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.818197$0.000069 · 797 tokp50 2,247 · p95 5,697 ms1judge judge-summ-v1inspect
cnn_qwen_l_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.812197$0.000842 · 826 tokp50 2,725 · p95 4,438 ms1judge judge-summ-v1inspect
cnn_openai_m_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.811200$0.005358 · 786 tokp50 1,719 · p95 2,126 ms1judge judge-summ-v2inspect
cnn_anthropic_m_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.809200$0.003739 · 1,282 tokp50 2,992 · p95 3,675 ms1judge judge-summ-v2inspect
cnn_gemma_s_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.801197$0.000100 · 818 tokp50 5,952 · p95 12,351 ms1judge judge-summ-v1inspect
cnn_mistral_s_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.798197$0.000089 · 831 tokp50 2,575 · p95 5,148 ms1judge judge-summ-v1inspect
cnn_openai_m_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.795197$0.005346 · 784 tokp50 1,720 · p95 2,132 ms1judge judge-summ-v1inspect
cnn_openai_l_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.773197$0.002175 · 783 tokp50 1,733 · p95 2,376 ms1judge judge-summ-v1inspect
cnn_deepseek_l_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.763200$0.000694 · 802 tokp50 2,354 · p95 4,380 ms1judge judge-summ-v2inspect
cnn_openai_s_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.747200$0.000836 · 793 tokp50 1,238 · p95 1,573 ms1judge judge-summ-v2inspect
cnn_anthropic_s_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.728200$0.001305 · 897 tokp50 1,982 · p95 2,834 ms1judge judge-summ-v2inspect
cnn_glm_m_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.718200$0.000497 · 803 tokp50 1,848 · p95 7,145 ms1judge judge-summ-v2inspect
cnn_gemma_l_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.715197$0.000119 · 808 tokp50 1,826 · p95 6,351 ms1judge judge-summ-v1inspect
cnn_mistral_m_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.708197$0.000434 · 830 tokp50 2,496 · p95 4,810 ms1judge judge-summ-v1inspect
cnn_gemma_m_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.707197$0.000077 · 810 tokp50 1,386 · p95 4,487 ms1judge judge-summ-v1inspect
cnn_llama_s_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.704197$0.000111 · 812 tokp50 2,195 · p95 4,062 ms1judge judge-summ-v1inspect
cnn_llama_l_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.700197$0.000193 · 803 tokp50 3,657 · p95 5,541 ms1judge judge-summ-v1inspect
cnn_mistral_l_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.698197$0.000485 · 826 tokp50 2,240 · p95 51,633 ms1judge judge-summ-v1inspect
cnn_llama_m_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.674197$0.000165 · 807 tokp50 2,692 · p95 11,257 ms1judge judge-summ-v1inspect
cnn_deepseek_s_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.644200$0.000069 · 800 tokp50 2,237 · p95 5,644 ms1judge judge-summ-v2inspect
cnn_qwen_s_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.609197$0.000135 · 823 tokp50 7,347 · p95 110,048 ms1judge judge-summ-v1inspect
cnn_glm_l_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.607197$0.000763 · 816 tokp50 2,351 · p95 12,769 ms1judge judge-summ-v1inspect
cnn_gemma_l_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.603200$0.000119 · 810 tokp50 1,817 · p95 6,172 ms1judge judge-summ-v2inspect
cnn_qwen_m_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.600200$0.000331 · 826 tokp50 1,531 · p95 1,911 ms1judge judge-summ-v2inspect
cnn_gemma_m_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.585200$0.000077 · 812 tokp50 1,388 · p95 4,483 ms1judge judge-summ-v2inspect
cnn_qwen_l_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.573200$0.000844 · 828 tokp50 2,732 · p95 4,428 ms1judge judge-summ-v2inspect
cnn_glm_s_n200_v1 · judged/judge-summ-v1
run on Darwin/x86_64, 12 CPUs
judge_score4.530197$0.000152 · 783 tokp50 1,587 · p95 2,343 ms1judge judge-summ-v1inspect
cnn_llama_l_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.529200$0.000195 · 805 tokp50 3,646 · p95 5,531 ms1judge judge-summ-v2inspect
cnn_llama_m_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.488200$0.000165 · 809 tokp50 2,682 · p95 11,240 ms1judge judge-summ-v2inspect
cnn_llama_s_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.469200$0.000111 · 814 tokp50 2,204 · p95 4,041 ms1judge judge-summ-v2inspect
cnn_qwen_s_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.461200$0.000135 · 825 tokp50 7,855 · p95 108,807 ms1judge judge-summ-v2inspect
cnn_gemma_s_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.429200$0.000100 · 820 tokp50 5,933 · p95 12,255 ms1judge judge-summ-v2inspect
cnn_glm_s_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.420200$0.000152 · 786 tokp50 1,580 · p95 2,341 ms1judge judge-summ-v2inspect
cnn_mistral_s_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.408200$0.000089 · 833 tokp50 2,573 · p95 5,142 ms1judge judge-summ-v2inspect
cnn_glm_l_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.384200$0.000766 · 818 tokp50 2,351 · p95 12,758 ms1judge judge-summ-v2inspect
cnn_mistral_m_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.309200$0.000435 · 832 tokp50 2,495 · p95 4,801 ms1judge judge-summ-v2inspect
cnn_mistral_l_n200_v1 · judged/judge-summ-v2
run on Darwin/x86_64, 12 CPUs
judge_score4.037200$0.000486 · 828 tokp50 2,272 · p95 51,619 ms1judge judge-summ-v2inspect
cnn_bart_l_n200_v1 · judged/judge-summ-v1
run on mac-dev · Darwin/x86_64, 12 CPUs
judge_score3.868197$0.000000 · 761 tokp50 10,700 · p95 14,266 ms1judge judge-summ-v1inspect
cnn_bart_l_n200_v1 · judged/judge-summ-v2
run on mac-dev · Darwin/x86_64, 12 CPUs
judge_score3.821200$0.000000 · 763 tokp50 10,724 · p95 14,371 ms1judge judge-summ-v2inspect
cnn_bart_m_n200_v1 · judged/judge-summ-v1
run on Linux/x86_64, 4 CPUs
judge_score3.564197$0.000000 · 764 tokp50 4,621 · p95 7,239 ms1judge judge-summ-v1inspect
cnn_bart_l_xsum_n200_v1 · judged/judge-summ-v1
run on Linux/x86_64, 4 CPUs
judge_score3.516197$0.000000 · 723 tokp50 4,368 · p95 7,328 ms1judge judge-summ-v1inspect
cnn_lead3_n200_v1 · judged/judge-summ-v1
run on mac-dev · Darwin/x86_64, 12 CPUs
judge_score3.421197$0.000000p50 0.057 · p95 0.13 ms1judge judge-summ-v1inspect
cnn_bart_l_xsum_n200_v1 · judged/judge-summ-v2
run on Linux/x86_64, 4 CPUs
judge_score3.366200$0.000000 · 725 tokp50 4,433 · p95 7,325 ms1judge judge-summ-v2inspect
cnn_lead3_n200_v1 · judged/judge-summ-v2
run on mac-dev · Darwin/x86_64, 12 CPUs
judge_score3.339200$0.000000p50 0.057 · p95 0.13 ms1judge judge-summ-v2inspect
cnn_bart_m_n200_v1 · judged/judge-summ-v2
run on Linux/x86_64, 4 CPUs
judge_score3.235200$0.000000 · 766 tokp50 4,649 · p95 7,223 ms1judge judge-summ-v2inspect
cnn_bart_s_n200_v1 · judged/judge-summ-v1
run on Linux/x86_64, 4 CPUs
judge_score3.185197$0.000000 · 759 tokp50 3,672 · p95 5,058 ms1judge judge-summ-v1inspect
cnn_bart_s_n200_v1 · judged/judge-summ-v2
run on Linux/x86_64, 4 CPUs
judge_score2.946200$0.000000 · 761 tokp50 3,683 · p95 5,055 ms1judge judge-summ-v2inspect
cnn_deepseek_m_n200_v1 · judged/judge-summ-pointwise-v1
run on Darwin/x86_64, 12 CPUs
judge_score_unvalidated4.940200$0.000191 · 812 tokp50 1,497 · p95 2,924 ms1judge judge-summ-pointwise-v1inspect
cnn_bart_l_n200_v1 · judged/judge-summ-pointwise-v1
run on mac-dev · Darwin/x86_64, 12 CPUs
judge_score_unvalidated4.181200$0.000000 · 763 tokp50 10,724 · p95 14,371 ms1judge judge-summ-pointwise-v1inspect
cnn_anthropic_l_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.402198$0.009783 · 1,293 tokp50 3,259 · p95 4,722 ms1judge judge-summ-pick-v1inspect
cnn_anthropic_s_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.226198$0.001299 · 892 tokp50 1,980 · p95 2,836 ms1judge judge-summ-pick-v1inspect
cnn_anthropic_m_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.144198$0.003724 · 1,275 tokp50 2,992 · p95 3,677 ms1judge judge-summ-pick-v1inspect
cnn_deepseek_m_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.083198$0.000189 · 807 tokp50 1,497 · p95 2,927 ms1judge judge-summ-pick-v1inspect
cnn_qwen_l_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.059198$0.000840 · 823 tokp50 2,732 · p95 4,435 ms1judge judge-summ-pick-v1inspect
cnn_qwen_m_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.020198$0.000329 · 821 tokp50 1,528 · p95 1,912 ms1judge judge-summ-pick-v1inspect
cnn_deepseek_l_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.014198$0.000699 · 797 tokp50 2,348 · p95 4,384 ms1judge judge-summ-pick-v1inspect
cnn_openai_s_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.008198$0.000833 · 788 tokp50 1,238 · p95 1,583 ms1judge judge-summ-pick-v1inspect
cnn_glm_l_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.006198$0.000765 · 813 tokp50 2,351 · p95 12,765 ms1judge judge-summ-pick-v1inspect
cnn_gemma_m_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.005198$0.000076 · 807 tokp50 1,388 · p95 4,485 ms1judge judge-summ-pick-v1inspect
cnn_glm_m_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.005198$0.000496 · 798 tokp50 1,848 · p95 7,151 ms1judge judge-summ-pick-v1inspect
cnn_openai_l_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.004198$0.002169 · 781 tokp50 1,731 · p95 2,385 ms1judge judge-summ-pick-v1inspect
cnn_mistral_s_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.004198$0.000089 · 828 tokp50 2,573 · p95 5,085 ms1judge judge-summ-pick-v1inspect
cnn_deepseek_s_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.004198$0.000068 · 795 tokp50 2,227 · p95 5,599 ms1judge judge-summ-pick-v1inspect
cnn_openai_m_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.004198$0.005335 · 781 tokp50 1,719 · p95 2,130 ms1judge judge-summ-pick-v1inspect
cnn_llama_l_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.003198$0.000194 · 800 tokp50 3,646 · p95 5,538 ms1judge judge-summ-pick-v1inspect
cnn_mistral_l_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.003198$0.000484 · 823 tokp50 2,236 · p95 51,435 ms1judge judge-summ-pick-v1inspect
cnn_gemma_s_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.002198$0.000099 · 816 tokp50 5,887 · p95 12,319 ms1judge judge-summ-pick-v1inspect
cnn_llama_s_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.001198$0.000111 · 809 tokp50 2,191 · p95 4,013 ms1judge judge-summ-pick-v1inspect
cnn_qwen_s_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.001198$0.000134 · 820 tokp50 7,855 · p95 109,634 ms1judge judge-summ-pick-v1inspect
cnn_glm_s_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.001198$0.000151 · 781 tokp50 1,580 · p95 2,342 ms1judge judge-summ-pick-v1inspect
cnn_gemma_l_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.001198$0.000118 · 805 tokp50 1,817 · p95 6,291 ms1judge judge-summ-pick-v1inspect
cnn_llama_m_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.001198$0.000163 · 804 tokp50 2,682 · p95 11,251 ms1judge judge-summ-pick-v1inspect
cnn_bart_l_n200_v1 · judged/judge-summ-pick-v1
run on mac-dev · Darwin/x86_64, 12 CPUs
judge_won0.000198$0.000000 · 759 tokp50 10,690 · p95 14,372 ms1judge judge-summ-pick-v1inspect
cnn_bart_l_xsum_n200_v1 · judged/judge-summ-pick-v1
run on Linux/x86_64, 4 CPUs
judge_won0.000198$0.000000 · 721 tokp50 4,392 · p95 7,327 ms1judge judge-summ-pick-v1inspect
cnn_bart_m_n200_v1 · judged/judge-summ-pick-v1
run on Linux/x86_64, 4 CPUs
judge_won0.000198$0.000000 · 761 tokp50 4,623 · p95 7,234 ms1judge judge-summ-pick-v1inspect
cnn_bart_s_n200_v1 · judged/judge-summ-pick-v1
run on Linux/x86_64, 4 CPUs
judge_won0.000198$0.000000 · 757 tokp50 3,675 · p95 5,057 ms1judge judge-summ-pick-v1inspect
cnn_lead3_n200_v1 · judged/judge-summ-pick-v1
run on mac-dev · Darwin/x86_64, 12 CPUs
judge_won0.000198$0.000000p50 0.057 · p95 0.13 ms1judge judge-summ-pick-v1inspect
cnn_mistral_m_n200_v1 · judged/judge-summ-pick-v1
run on Darwin/x86_64, 12 CPUs
judge_won0.000198$0.000433 · 827 tokp50 2,482 · p95 4,807 ms1judge judge-summ-pick-v1inspect

02what's inside

200 items, text, 102–1497 words (median 465, middle half 283–774).

Source: abisee/cnn_dailymail (test split). The text stays there; each item below links to its row.

02550102–241 words: 32242–381 words: 45382–521 words: 34522–661 words: 21662–801 words: 21802–941 words: 16942–1081 words: 161082–1221 words: 71222–1361 words: 51362–1501 words: 3102–241242–381382–521522–661662–801802–941942–10811082–12211222–13611362–1501

the gold

gold/cnn_dailymail_200: text, 14–67 words, median 34

200 shown
itemwordsgoldopen
012819ffa25487133 wordssource ↗ · inspect
04c28c2d6c52149741 wordssource ↗ · inspect
054ccc28076726150 wordssource ↗ · inspect
07f60889bcd192618 wordssource ↗ · inspect
0a6b027b338445527 wordssource ↗ · inspect
0b66cb7ebcfd23541 wordssource ↗ · inspect
0d3c8c276d0736144 wordssource ↗ · inspect
0f39feebc34f64845 wordssource ↗ · inspect
12a3eec84bff28323 wordssource ↗ · inspect
12d18fce815517138 wordssource ↗ · inspect
130663882dcf45515 wordssource ↗ · inspect
17412737648b34436 wordssource ↗ · inspect
18e1af12d67923822 wordssource ↗ · inspect
192bf513d8ad19652 wordssource ↗ · inspect
1b2cc634e2bf44024 wordssource ↗ · inspect
1c26bc66402236226 wordssource ↗ · inspect
1dd00c89d71a95445 wordssource ↗ · inspect
1ecb11d97cc361647 wordssource ↗ · inspect
202a51397a4d28227 wordssource ↗ · inspect
203886369fee46532 wordssource ↗ · inspect
20a6b5894c4c26628 wordssource ↗ · inspect
230c5228549941144 wordssource ↗ · inspect
23b01320d93b72849 wordssource ↗ · inspect
2549d3c10d5b78726 wordssource ↗ · inspect
25a52d1de3a386740 wordssource ↗ · inspect
2af3d550555928924 wordssource ↗ · inspect
2b1b6a434b17112337 wordssource ↗ · inspect
2b4eb5a283f510328 wordssource ↗ · inspect
2bd8ada1de6a11321 wordssource ↗ · inspect
2c05ddcc2bf528744 wordssource ↗ · inspect
2dac7b4a9ed996667 wordssource ↗ · inspect
2f6106809de440521 wordssource ↗ · inspect
2ffe3bdf91bd66140 wordssource ↗ · inspect
32655a04c9e444443 wordssource ↗ · inspect
32a7125a655a69023 wordssource ↗ · inspect
32f8af7757d570727 wordssource ↗ · inspect
33cab1f129c337135 wordssource ↗ · inspect
346c39e1a89232833 wordssource ↗ · inspect
357a3c6ad7f571825 wordssource ↗ · inspect
36ac591f1b7a98625 wordssource ↗ · inspect
37477ed1fc0631938 wordssource ↗ · inspect
3783ef06d42f51530 wordssource ↗ · inspect
384175be1c8d49827 wordssource ↗ · inspect
386b182672cd10230 wordssource ↗ · inspect
38a207accfb320928 wordssource ↗ · inspect
3bfe27dc86f020025 wordssource ↗ · inspect
3cf7f404fef833644 wordssource ↗ · inspect
3fbdee096ce983642 wordssource ↗ · inspect
41592d02ca32105529 wordssource ↗ · inspect
41c6edecee1236447 wordssource ↗ · inspect
42c49513463e71933 wordssource ↗ · inspect
43f18fc9b20f14324 wordssource ↗ · inspect
4495ba8f3a3470438 wordssource ↗ · inspect
44d681105bca56838 wordssource ↗ · inspect
454434c7bf7752241 wordssource ↗ · inspect
469c6ac05092113352 wordssource ↗ · inspect
4bd20bce906663733 wordssource ↗ · inspect
4cc5744a14d864740 wordssource ↗ · inspect
4fbf675fb79074646 wordssource ↗ · inspect
5139ccfabee528135 wordssource ↗ · inspect
5231a93ff48e54740 wordssource ↗ · inspect
5362f24162b383926 wordssource ↗ · inspect
5493b9481b0017937 wordssource ↗ · inspect
574767c29dfe107927 wordssource ↗ · inspect
578677b3280b27030 wordssource ↗ · inspect
58b9fcb9a353121539 wordssource ↗ · inspect
599bf6f13bc825249 wordssource ↗ · inspect
5a4f7f0a9cc775062 wordssource ↗ · inspect
5a650587a76e50029 wordssource ↗ · inspect
61a61056428016820 wordssource ↗ · inspect
6222f33c2c7928928 wordssource ↗ · inspect
6302a6cf856418323 wordssource ↗ · inspect
6344c9689865132643 wordssource ↗ · inspect
63e19d47746938859 wordssource ↗ · inspect
63ee59d6998234544 wordssource ↗ · inspect
646cba2e8b3083331 wordssource ↗ · inspect
68382576e699122950 wordssource ↗ · inspect
695fecd970ab15124 wordssource ↗ · inspect
69af3b9fc4ba63542 wordssource ↗ · inspect
69e1f777e41b18336 wordssource ↗ · inspect
6c4ed9b048e0108933 wordssource ↗ · inspect
6ce9f3ddbed989042 wordssource ↗ · inspect
6da088a4a4c542726 wordssource ↗ · inspect
72610cfcc7b859526 wordssource ↗ · inspect
72df456684b6126947 wordssource ↗ · inspect
74b24c60df8b27857 wordssource ↗ · inspect
74e99c26d8bb19530 wordssource ↗ · inspect
76a518ad3aa525233 wordssource ↗ · inspect
78a670384c9027524 wordssource ↗ · inspect
7b8bb308a48e77437 wordssource ↗ · inspect
7d5b44afe30b26130 wordssource ↗ · inspect
7e4d197d5fe829021 wordssource ↗ · inspect
7fb513044e3751940 wordssource ↗ · inspect
8012ab9261e193732 wordssource ↗ · inspect
82461522ee9043528 wordssource ↗ · inspect
837970f6b54454523 wordssource ↗ · inspect
84c9dd43080e29933 wordssource ↗ · inspect
84dabfdd73c2109550 wordssource ↗ · inspect
8610ead0a43075223 wordssource ↗ · inspect
88e7dac40f3e80529 wordssource ↗ · inspect
8911c07945c315244 wordssource ↗ · inspect
89daa80db49b35426 wordssource ↗ · inspect
8ba20bec435848837 wordssource ↗ · inspect
8be49747e36422244 wordssource ↗ · inspect
8ec9aabea31a13432 wordssource ↗ · inspect
934a2d92350249019 wordssource ↗ · inspect
9378a8d4b9a647236 wordssource ↗ · inspect
947b339a524a38226 wordssource ↗ · inspect
947eeb8bbfec23342 wordssource ↗ · inspect
970f75d6e5b239529 wordssource ↗ · inspect
978a6fc6a91028537 wordssource ↗ · inspect
97c0670cd61440844 wordssource ↗ · inspect
996940764a0626328 wordssource ↗ · inspect
9a2ffa6ad64362124 wordssource ↗ · inspect
9b54bd1709bd25234 wordssource ↗ · inspect
9bea5cbe9a0127427 wordssource ↗ · inspect
9dc3325d901826127 wordssource ↗ · inspect
9eb7dd37e50b69946 wordssource ↗ · inspect
9f051fe922a899249 wordssource ↗ · inspect
9fbd984bd3a434320 wordssource ↗ · inspect
a168d913945078346 wordssource ↗ · inspect
a2363d02185b85852 wordssource ↗ · inspect
a2a2ac30f46521346 wordssource ↗ · inspect
a2b66e43762540725 wordssource ↗ · inspect
a2ee2faeb2dc104632 wordssource ↗ · inspect
a37f0005819d106656 wordssource ↗ · inspect
a38e72fed88620245 wordssource ↗ · inspect
a43893ac7046134927 wordssource ↗ · inspect
a8c1b6fc673831924 wordssource ↗ · inspect
afd04a7bf64540824 wordssource ↗ · inspect
b10db3ae83ab67452 wordssource ↗ · inspect
b21cd549314991945 wordssource ↗ · inspect
b3619076f8eb25824 wordssource ↗ · inspect
b540aeae06b069423 wordssource ↗ · inspect
b7c282a0373918732 wordssource ↗ · inspect
b882ed05925f54329 wordssource ↗ · inspect
b8e56b3cb5fa98245 wordssource ↗ · inspect
bbdc0e58a20353428 wordssource ↗ · inspect
bbe26fc3817579935 wordssource ↗ · inspect
be5d8524bf2134936 wordssource ↗ · inspect
c0340e53445e33546 wordssource ↗ · inspect
c222979bd1cf73837 wordssource ↗ · inspect
c27cf1b136cc36443 wordssource ↗ · inspect
c34d84d38ccf95137 wordssource ↗ · inspect
c5390093fa60108834 wordssource ↗ · inspect
c67a5be9af7145128 wordssource ↗ · inspect
c71b08cede3b27324 wordssource ↗ · inspect
c7a2fff8169413130 wordssource ↗ · inspect
c7caf9181c2e81344 wordssource ↗ · inspect
c811d9ae87c9105449 wordssource ↗ · inspect
ca1c3b587b72103647 wordssource ↗ · inspect
cb56840e21bb13726 wordssource ↗ · inspect
cc86a588b4e425629 wordssource ↗ · inspect
cd745b3c66da41928 wordssource ↗ · inspect
cf3f7388c3b533224 wordssource ↗ · inspect
cf7094270cbb146646 wordssource ↗ · inspect
d71e9a0213b113126 wordssource ↗ · inspect
d8aee1ae4b1189442 wordssource ↗ · inspect
d96576c5c5e659437 wordssource ↗ · inspect
da9588f556b150248 wordssource ↗ · inspect
dc833f8b55e3102847 wordssource ↗ · inspect
dc8bb8429f6292139 wordssource ↗ · inspect
dd4f7262003521331 wordssource ↗ · inspect
e21f3aefeb4187841 wordssource ↗ · inspect
e2706dce6cf277356 wordssource ↗ · inspect
e2bccd4dec9346037 wordssource ↗ · inspect
e30518a464ea13232 wordssource ↗ · inspect
e3f8ceb7a62794925 wordssource ↗ · inspect
e4fcad9e8cf820332 wordssource ↗ · inspect
e65440d2469c129824 wordssource ↗ · inspect
e67604ecb75a28626 wordssource ↗ · inspect
e6c7c16699d254925 wordssource ↗ · inspect
e709f9942da035944 wordssource ↗ · inspect
e8c90d557031148153 wordssource ↗ · inspect
eaf4a786420853625 wordssource ↗ · inspect
eb39e1395ad142435 wordssource ↗ · inspect
ec4b5fef725b38935 wordssource ↗ · inspect
ecb2616fc4fb67514 wordssource ↗ · inspect
ee17dfb574fe11133 wordssource ↗ · inspect
eeafdc8b2d8126218 wordssource ↗ · inspect
ef92201afc2d48532 wordssource ↗ · inspect
f001ec5c470456736 wordssource ↗ · inspect
f1c555fe64f957336 wordssource ↗ · inspect
f309d4d0aabf70231 wordssource ↗ · inspect
f555b81fb88849326 wordssource ↗ · inspect
f66c8ff2cad236935 wordssource ↗ · inspect
f78024d271fd58523 wordssource ↗ · inspect
f78fb08d7ccc99928 wordssource ↗ · inspect
f7c2eb46547923023 wordssource ↗ · inspect
f8e429a6906f39345 wordssource ↗ · inspect
f97442bee2ac39034 wordssource ↗ · inspect
f97b9b19e5a966745 wordssource ↗ · inspect
f9f5d81bc74d33138 wordssource ↗ · inspect
fcd69b35b0bd19619 wordssource ↗ · inspect
fd0e8622b9ee38334 wordssource ↗ · inspect
ff42fad959e843820 wordssource ↗ · inspect
ff4cf78e837b107436 wordssource ↗ · inspect
ff866754ef03120439 wordssource ↗ · inspect
ff9c1536bfa661846 wordssource ↗ · inspect
ffff11a2f44d92638 wordssource ↗ · inspect

Each row is the profile evh dataset-items --dataset-id cnn_dailymail_200 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 cnn_dailymail_200 --out sheet.csv; a run's outputs as a model set: evh label-from-run --run R --set S.