arm
cnn_lead3_n200_v1 · linux
One config on cnn_dailymail_200, scored one way; its repeats averaged per item.
- dataset
- cnn_dailymail_200
- scored against
- gold/cnn_dailymail_200 gold
- goal
- Short news summaries (CNN)
- runs
- 1
- headline
- coverage 0.272
- last run
- 2026-09-30 14:41
Inspect itAgainst the baselineWith the 35 arms scored the same way
01metrics
| metric | mean | items | better |
|---|---|---|---|
| coverage | 0.272 | 200 | higher |
| compression | 0.159 | 200 | neutral |
| concision | 0.215 | 200 | higher |
| cost_usd | $0.000000 | 200 | lower |
| fmt_bullets | 0.000 | 200 | neutral |
| fmt_label | 0.000 | 200 | neutral |
| fmt_markdown | 0.000 | 200 | neutral |
| fmt_narration | 0.010 | 200 | neutral |
| fmt_overlong | 0.085 | 200 | neutral |
| fmt_paragraphs | 0.000 | 200 | neutral |
| grounding | 1.000 | 200 | higher |
| latency_ms | 0.070 | 200 | lower |
| length_vs_reference | 1.905 | 200 | neutral |
| reference_words | 34.7 | 200 | neutral |
| rouge1 | 0.302 | 200 | higher |
| rougeLsum | 0.270 | 200 | higher |
| summary_words | 62.0 | 200 | neutral |
02cost and speed
- cost per item
- $0.000000
- speed per item
- p50 0.063 · p95 0.15 ms
Per item, over its items: cost as dollars and tokens (a local model is free but still uses tokens), speed as the median and the slow tail (p95). A goal that names this arm weighs them in its decision.
03runs
| run | made | items | cost | how |
|---|---|---|---|---|
cnn_lead3_n200_v1_20260930T144131Z | 2026-09-30 14:41 | 200 | $0.000000 | measured |
04config
config cnn_lead3_n200_v1 · adapter examples/summarization-cnn-dailymail/adapter.py · credentials are never shown
- family
lead- price_tier
free- provider
lead_k- sentences
3
05conditions
- data.items_sha256
257feda902391b934b8cde940c15e91201096dbe96ec5a81337e9da007ce3ec7- deployment.model
lead_3- deployment.source
params- fingerprint.version
5- library.numpy
2.4.6- library.openai
3.19.2- library.rouge-score
0.1.2- library.torch
2.14.0- library.transformers
4.55.4- machine.cpu_count
4- machine.platform
Linux/x86_64- machine.processor
x86_64- machine.python
3.11.15- machine.release
6.18.44-fc-v50- reference.sha256
5d0b02c3798017535572d24dd3ce0592332938a0c91e93684d163963a60a7cd9- scorer.id
examples/summarization-cnn-dailymail/adapter.py- scorer.sha256
34afcfd48fa46f013ccf160f8f55175607831f419fff14536a0daa1061a5ed88
06the same config, scored other ways
scored against silverscored by a judgescored against a label set, not a reference setunmarked rows are scored against gold
| arm | scored against | headline | mean |
|---|---|---|---|
| cnn_lead3_n200_v1 | gold/cnn_dailymail_200 gold | coverage | 0.272 |
| cnn_lead3_n200_v1 · silver | silver/cnn_dailymail_200 silver | coverage | 0.300 |
| cnn_lead3_n200_v1 · judged/judge-summ-pick-v1 | judge judge-summ-pick-v1 | judge_won | 0.000 |
| cnn_lead3_n200_v1 · judged/judge-summ-v1 | judge judge-summ-v1 | judge_score | 3.421 |
| cnn_lead3_n200_v1 · judged/judge-summ-v2 | judge judge-summ-v2 | judge_score | 3.339 |
07rounds
- Round r2 of Short news summaries (CNN), closed: retired in it.