DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to summarize graded trials by task and in total with Swe Sweep

Turn a folder of graded Harbor trials into per-task and JSON score summaries.

Who it is forA researcher or team lead comparing several agents' graded runs across SWE-sweep tasks.

The problemReading raw graded trial folders one by one makes it hard to compare runs or report the benchmark score.

The outcomeA per-task breakdown or a JSON summary of bugs resolved across the graded trials.

What you need first

  • Python with uv (or pip) installed
  • Harbor, as pinned by the repo
  • A unified diff file (model.patch) made against a task's base commit
  • Docker or the environment Harbor needs for the verifier, if Harbor requires it (inferred)

Steps

  1. git clone https://github.com/facebookresearch/swe-sweep.git
  2. cd swe-sweep
  3. uv sync
  4. sweep info path/to/graded-solutions --per-task
  5. sweep info path/to/graded-solutions --json

Prompt for your agent

In the facebookresearch/swe-sweep repo, run `sweep info <path-to-graded-trials> --json` and save the output. Verify that the reported total equals the number of bugs solved across tasks divided by the total number of bugs.

Caveat. The final score is a micro-average of bugs resolved, which is equivalent to a weighted average of individual task scores, so per-task averages will not match the headline number directly.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page