Skip to main content

runopsy-bench

Labelled traces with known ground truth, and the metrics that score a diagnosis against them.

This package is the difference between claiming the engine localizes failures and knowing it does. Every case declares where the run actually broke, so onset accuracy, top-3 recall and step distance are measured rather than asserted.

Two design choices keep the number honest.

Negative controls are part of the suite. A healthy run that produces no finding is scored alongside the failures. An engine that flags everything would otherwise post a perfect onset accuracy while being useless, and false positives are what actually get a diagnosis tool switched off.

Known blind spots are labelled, not hidden. Some cases — a tool that succeeds while writing the wrong value, an agent that picks a plausible but wrong tool — cannot be found by structural analysis at all, because nothing in the recorded trace is anomalous. They are marked deterministically_detectable = False, excluded from the accuracy figure, and reported separately as the coverage gap that semantic analysis exists to close. Quietly dropping them would inflate the headline number and hide exactly the work that remains.

Metadata

Release files for runopsy-bench 0.1.9

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for runopsy-bench 0.1.9
File Size Uploaded
runopsy_bench-0.1.9.tar.gz 26.9 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for runopsy-bench 0.1.9
File Interpreter ABI Platform
runopsy_bench-0.1.9-py3-none-any.whl Python 3 none any Details

Total release size: 60.9 kB

Release files / runopsy_bench-0.1.9.tar.gz

Download URL runopsy_bench-0.1.9.tar.gz
Size 26.9 kB
Tags Source
SHA-256 checksum
How to use checksums
07ffb4bb0b7afdc1ae25a29f5acb343cb2ad8570a7b05e8c52a82915fd2c1fd1
BLAKE2b-256 checksum
How to use checksums
891e84dceb86ee2b0a06d7903d7588fe755d343da33e7a026626185f28ab4ff8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.0 {"installer":{"name":"uv","version":"0.12.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / runopsy_bench-0.1.9-py3-none-any.whl

Download URL runopsy_bench-0.1.9-py3-none-any.whl
Size 34.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
fc84a38ce9b6458cebccba2ab6f1680c53d8a8ae6c79954e4b27d6afafef5c3e
BLAKE2b-256 checksum
How to use checksums
9e86a5d525afa1deede5f232503fa3dc44d44df7520bc3bec88e1ad0e8ffe881
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.0 {"installer":{"name":"uv","version":"0.12.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release history Release notifications | RSS feed

This release

0.1.9 This release

2 release files

0.1.8

2 release files

0.1.7

2 release files

0.1.6

2 release files

0.1.5

2 release files

0.1.4

2 release files

0.1.3

2 release files

0.1.2

2 release files

0.1.1

2 release files

0.1.0

1 release file

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page