From 60b7561247c0580fe0c29dccf920b27560b48495 Mon Sep 17 00:00:00 2001 From: Perry Zhu Date: Fri, 22 May 2026 19:30:12 -0700 Subject: [PATCH] build: v0.4.0 release --- CHANGELOG.md | 4 ++++ pyproject.toml | 2 +- uv.lock | 2 +- 3 files changed, 6 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 6dbd3586..1a2df2ec 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,6 +6,10 @@ All notable changes to this project will be documented in this file. The format is based on [Keep a Changelog](https://keepachangelog.com/) and this project adheres to [Semantic Versioning](https://semver.org/). +## [0.4.0] - 2026-05-22 +### Added +- Added scripts for rescoring and reproducing the benchmark results based on disclosed trajectories. + ## [0.3.3] - 2026-05-19 ### Changed - More data are stored in the `run-meta.json` for better post-hoc analysis and reproducibility, including the hash of the configs, runtime info, and flags used. diff --git a/pyproject.toml b/pyproject.toml index 4021dbd0..f471e259 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "hatchling.build" [project] name = "clawbench-eval" -version = "0.3.3" +version = "0.4.0" description = "Benchmarking framework for evaluating AI web agents on real-world online tasks" readme = "README.md" requires-python = ">=3.11" diff --git a/uv.lock b/uv.lock index eed388ef..f10b531e 100644 --- a/uv.lock +++ b/uv.lock @@ -58,7 +58,7 @@ wheels = [ [[package]] name = "clawbench-eval" -version = "0.3.3" +version = "0.4.0" source = { editable = "." } dependencies = [ { name = "fpdf2" },