Propose a part

Datasheet · A tool

Run its own code

run

Helps on Coding, Haiku 5.5 with thinking off (+4.0 points).

Coding, Haiku 5.5 with thinking off

Pooled across 1 notebook: +4.0 points, 95% interval +2.0 to +6.1; measured once.

  1. EXCITESNotebook #083+4.0 points (+1.5 to +6.8), 432 pairs, cost ×2.39signed verdict 510

Where it acts

Its effect sits in AMM swap output (+29.5) and Parsing durations (+14.1); no other family moved clearly.

  1. AMM swap output+29.5+6.4 to +53.939 tasks
  2. Parsing durations+14.1+3.9 to +26.939 tasks
The other 9 families, none moved clearly
  1. Moving averages+2.6−5.1 to +12.839 tasks
  2. Business days+0.0+0.0 to +0.040 tasks
  3. Fees in whole cents+0.0+0.0 to +0.039 tasks
  4. Merging intervals+0.0+0.0 to +0.039 tasks
  5. Run-length encoding+0.0+0.0 to +0.039 tasks
  6. Comparing versions+0.0+0.0 to +0.040 tasks
  7. URL slugs+0.0+0.0 to +0.039 tasks
  8. Top k by score+0.0+0.0 to +0.040 tasks
  9. Trade profit−1.3−14.1 to +9.039 tasks

Read from 432 paired tasks in 1 notebook, each task against its own notebook’s two controls, with every interval widened for the 11 families read. No notebook preregisters a family: this says where to look, and a notebook says whether it holds. The runs behind it are on each notebook’s page.

Put this datasheet in a README

The badge shows what the signed record says about this part, in the setting measured most, and links here. It follows the record as new notebooks publish. Add ?suite= and a suite’s id to show another setting.

OPSIN: helps +4.0 on Coding
[![OPSIN](https://opsinlab.io/badge/00e44145b830a036.svg)](https://opsinlab.io/parts/00e44145b830a036)

Measure it in a setting it has not been measured in: propose it. As JSON for an agent: /v1/parts/00e44145b830a036. Every part: the atlas.