arm
se_length_n100_v1
One config on summeval_100, scored one way; its repeats averaged per item.
- dataset
- summeval_100
- scored against
- gold/summeval_100 gold
- goal
- A scorer that agrees with experts on summaries (SummEval)
- runs
- 1
- headline
- tau 0.039
- last run
- 2026-10-15 13:05
Inspect itAgainst the baselineWith the 35 arms scored the same way
01metrics
| metric | mean | items | better |
|---|---|---|---|
| tau | 0.039 | 100 | higher |
| cost_usd | $0.000000 | 100 | lower |
| latency_ms | 0.192 | 100 | lower |
| parsed | 1.000 | 100 | neutral |
| rho | 0.048 | 100 | higher |
| rho_coherence | -0.020 | 100 | higher |
| rho_consistency | 0.085 | 100 | higher |
| rho_fluency | 0.001 | 100 | higher |
| rho_relevance | 0.124 | 100 | higher |
| tau_coherence | -0.014 | 100 | higher |
| tau_consistency | 0.071 | 100 | higher |
| tau_fluency | -0.002 | 100 | higher |
| tau_relevance | 0.100 | 100 | higher |
| tie_rate | 0.026 | 100 | neutral |
02cost and speed
- cost per item
- $0.000000
- speed per item
- p50 0.18 · p95 0.3 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 |
|---|---|---|---|---|
se_length_n100_v1_20261015T130520Z | 2026-10-15 13:05 | 100 | $0.000000 | measured |
04config
config se_length_n100_v1 · adapter examples/summeval-judging/adapter.py · credentials are never shown
- family
baseline- price_tier
free- provider
length
05conditions
- data.items_sha256
b59999b281b2cbe87c57e4af34cc475c01ba1d531c7b77cb93a136665119c613- deployment.model
length- deployment.source
params- fingerprint.version
5- library.numpy
1.26.4- library.openai
3.31.0- library.rouge-score
0.1.2- library.torch
2.14.1- 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-v114- reference.sha256
7b5e618e23b7f2b222665d83e99006eb0e9a51066e63e2e5ff8c51ae3c696c21- scorer.id
examples/summeval-judging/adapter.py- scorer.sha256
b7d5e2e5ce84ea0fe683e3488ba09fbcc416464d2b8f5abc47956930bf0262eb
06rounds
- Round r1 of A scorer that agrees with experts on summaries (SummEval), closed: one of its arms.