{"id":"18d4a969-e96b-4f9b-8d91-6a9c42eecf2d","org_id":"4de8c2bc-e09e-46ad-a95e-2504ee965da3","slug":"cua-verified-slack-clone-codex-build","name":"CUA-verified / slack-clone (long-horizon PR #65) — codex build (81 steps) + opus-4-7 CUA verifier (54 steps)","visibility":"unlisted","can_edit":false,"agent_name":"prebuilt-artifact","model_name":null,"environment_type":"docker","n_trials":1,"n_errors":0,"n_pass":0,"mean_reward":0.333333333333333,"org_name":"Refresh","org_slug":"refresh","projects":[],"uploaded_by_id":"5c566e7a-cc42-4420-b873-fd947a6b5cea","uploaded_by_name":"Christopher Settles","uploaded_by_email":"chris@refresh.dev","uploaded_by_avatar":"https://lh3.googleusercontent.com/a/ACg8ocJ8c5SoEvnBaFY4RUo3TW91noIfxy0lhU6vuloXRC2W7M4Gwm8-=s96-c","config":{"debug":true,"quiet":false,"retry":{"max_retries":0,"max_wait_sec":60.0,"min_wait_sec":1.0,"wait_multiplier":1.0,"exclude_exceptions":["VerifierTimeoutError","RewardFileEmptyError","AgentTimeoutError","VerifierOutputParseError","RewardFileNotFoundError"],"include_exceptions":null},"tasks":[],"agents":[{"env":{},"name":"prebuilt-artifact","kwargs":{},"model_name":null,"import_path":null,"max_timeout_sec":null,"override_timeout_sec":null,"override_setup_timeout_sec":null}],"metrics":[],"datasets":[{"ref":null,"name":null,"path":"examples/tasks/cua-verified","n_tasks":null,"version":null,"overwrite":false,"task_names":["slack-clone-prebuilt"],"download_dir":null,"registry_url":null,"registry_path":null,"exclude_task_names":null}],"job_name":"cua-verified-slack-004","jobs_dir":"jobs","verifier":{"env":{},"disable":false,"max_timeout_sec":null,"override_timeout_sec":null},"artifacts":[],"n_attempts":1,"environment":{"env":{},"type":"docker","delete":true,"kwargs":{},"force_build":false,"import_path":null,"mounts_json":null,"override_cpus":null,"override_gpus":null,"override_memory_mb":null,"override_storage_mb":null,"suppress_override_warnings":false},"timeout_multiplier":1.0,"n_concurrent_trials":1,"agent_timeout_multiplier":null,"verifier_timeout_multiplier":null,"agent_setup_timeout_multiplier":null,"environment_build_timeout_multiplier":null},"stats":{"evals":{"prebuilt-artifact__synthetic__cua-verified":{"metrics":[{"mean":0.3333333333333333}],"n_errors":0,"n_trials":1,"pass_at_k":{},"reward_stats":{"reward":{"0.3333333333333333":["slack-clone-prebuilt__FZtCJDV"]}},"exception_stats":{}}},"cost_usd":null,"n_trials":1,"n_retries":0,"n_cache_tokens":null,"n_input_tokens":null,"n_output_tokens":null,"n_errored_trials":0,"n_pending_trials":0,"n_running_trials":0,"n_cancelled_trials":0,"n_completed_trials":1},"created_at":"2026-05-04T01:31:25.580753+00:00","trials":[{"id":"ad4cd4fa-d301-4f29-bb52-d9fa112a2d32","trial_name":"slack-clone-prebuilt__FZtCJDV","task_external_id":"cua-verified/slack-clone-prebuilt","task_id":null,"task_checksum":"b09e71a72256e4f5f9e8cae976ab678d47f15eb32723912b5b66a5e7112795e6","agent_name":"prebuilt-artifact","model_name":"synthetic","reward":0.333333333333333,"n_input_tokens":null,"n_output_tokens":null,"cost_usd":null,"n_episodes":null,"n_steps":81,"duration_sec":789.144291,"exception_type":null,"created_at":"2026-05-04T01:32:19.83952+00:00"}],"task_prompt":null,"preview_fingerprint":"560fcc612aff216d41ebb093f208beadfc397e2fdf17fa5ec7c402322298920d","preview_score":null,"preview_version":null,"preview_score_version":null,"preview_current_version":"activity-v12","preview_latest_version":null,"preview_available":false}