{"schema_version":"onlylabs.public_analysis_evidence.v1","title":"StreamLake (Kuaishou) analysis evidence pack","description":"Public onlylabs evidence pack for cited agent analysis: captured pages, ranked public signals, and stored web-search provenance used by the background analysis workflow.","url":"https://onlylabs.fyi/labs/streamlake","json_url":"https://onlylabs.fyi/analysis/streamlake/evidence.json","generated_at":"2026-06-11T18:06:15.463Z","org":{"slug":"streamlake","name":"StreamLake (Kuaishou)","category":"neocloud","category_label":"Neocloud","dossier_url":"https://onlylabs.fyi/labs/streamlake"},"analysis":null,"workflow":{"version":"onlylabs-deepagents-analysis-v3","provider":null,"model":null,"agent":null,"public_pack_mode":"local-pages-and-events","live_web_fetches":false,"note":"Public evidence exports do not trigger live Exa calls; stored Exa provenance is included when analysis metadata contains it."},"stats":{"pages":4,"events":4,"web":0,"evidence":8,"signal_desks":{"hiring":0,"forks":1,"releases":0,"talking":0,"repos":3},"data_radar_lanes":null,"data_radar_matches":null,"stored_analysis_evidence":null,"stored_analysis_web":null,"stored_analysis_signal_desks":null,"stored_analysis_data_radar_lanes":null,"stored_analysis_data_radar_matches":null},"stored_web_provenance":null,"evidence":[{"ref":"P1","kind":"page","title":"kwaipilot/SWE-Compass repository metadata","date":"2026-06-11T04:08:23.63462+00:00","date_source":null,"source_url":"https://github.com/kwaipilot/SWE-Compass","signal_url":null,"signal_json_url":null,"text":"# kwaipilot/SWE-Compass\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 18\n\nForks: 2\n\nOpen issues: 3\n\nCreated: 2025-12-03T07:47:56Z\n\nPushed: 2026-03-28T10:37:57Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n<img src=\"https://cdn-uploads.huggingface.co/production/uploads/61ee40a269351366e29972ad/KIYEa1c_WJEWPpeS0L_k1.png\" width=\"100%\" alt=\"Kwaipilot\" />\n<hr>\n<div align=\"center\" style=\"line-height: 1;\">\n<a href=\"https://huggingface.co/datasets/Kwaipilot/SWE-Compass\"><img alt=\"Hugging Face\"\nsrc=\"https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-swecompass-ffc107?color=ffc107&logoColor=white\"/></a>\n<a href=\"https://github.com/shunxing12345/swecompass/blob/main/LICENSE\"><img alt=\"License\"\nsrc=\"https://img.shields.io/badge/License-Apache%202.0-f5de53?&color=f5de53\"/></a>\n<a href=\"https://arxiv.org/abs/2511.05459\"><img alt=\"arXiv\" src=\"https://img.shields.io/badge/arXiv-2511.05459-B31B1B?logo=arxiv&logoColor=white\"/></a>\n<br>\n<a href=\"https://github.com/kwaipilot/SWE-Compass/stargazers\"><img alt=\"GitHub stars\"\nsrc=\"https://img.shields.io/github/stars/kwaipilot/SWE-Compass\"/></a>\n<a href=\"https://github.com/kwaipilot/SWE-Compass/network\"><img alt=\"GitHub forks\"\nsrc=\"https://img.shields.io/github/forks/kwaipilot/SWE-Compass\"/></a>\n</div>\n</div>\n\n[🇺🇸 English ](README.md) [🇨🇳 简体中文](README_CN.md)\n\n---\n\n## 🧠 SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models\n\nCurrent evaluations of LLMs for software engineering are limited by a narrow range of task categories, a Python-centric bias, and insufficient alignment with real-world development workflows. \nTo bridge these gaps, SWECompass establishes a **high-coverage, multi-dimensional, and production-aligned evaluation framework**:\n\n* ✨ Covers **8 software engineering task types, 8 programming scenarios, and 10 programming languages**\n* ✨ Contains **2000 high-quality instances sourced from real GitHub pull requests**\n* ✨ Supports multi-dimensional performance comparison across task types, languages, and scenarios\n\nBy integrating heterogeneous code tasks with real engineering practices, SWECompass provides a **reproducible, rigorous, and producti"},{"ref":"P2","kind":"page","title":"kwaipilot/KAT-Coder-Agent repository metadata","date":"2026-06-11T04:08:23.627081+00:00","date_source":null,"source_url":"https://github.com/kwaipilot/KAT-Coder-Agent","signal_url":null,"signal_json_url":null,"text":"# kwaipilot/KAT-Coder-Agent\n\nStars: 1\n\nForks: 0\n\nOpen issues: 0\n\nCreated: 2025-09-16T09:01:43Z\n\nPushed: 2025-09-16T11:07:55Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# KAT-Coder-Agent"},{"ref":"P3","kind":"page","title":"kwaipilot/KAT-Coder repository metadata","date":"2026-06-11T04:08:23.570153+00:00","date_source":null,"source_url":"https://github.com/kwaipilot/KAT-Coder","signal_url":null,"signal_json_url":null,"text":"# kwaipilot/KAT-Coder\n\nLanguage: HTML\n\nStars: 1\n\nForks: 0\n\nOpen issues: 1\n\nCreated: 2025-09-16T04:10:32Z\n\nPushed: 2025-09-26T04:34:07Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME: none published or not readable through the GitHub API."},{"ref":"P4","kind":"page","title":"kwaipilot/experiments repository metadata","date":"2026-06-11T02:53:56.249051+00:00","date_source":null,"source_url":"https://github.com/kwaipilot/experiments","signal_url":null,"signal_json_url":null,"text":"# kwaipilot/experiments\n\nDescription: Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.\n\nStars: 0\n\nForks: 0\n\nOpen issues: 0\n\nCreated: 2025-09-10T07:18:03Z\n\nPushed: 2025-08-28T17:46:13Z\n\nDefault branch: main\n\nFork: yes\n\nParent repository: SWE-bench/experiments\n\nArchived: no\n\nREADME:\n# SWE-bench Experiments\n\nThis repository contains records of submissions to the [SWE-bench](https://swe-bench.github.io/) leaderboard.\n\n<details>\n<summary>How is this repository organized?</summary>\n\n```\nexperiments/\n├── evaluation/\n│ ├── lite/\n│ ├── verified/\n│ ├── multimodal/\n│ ├── multilingual/\n│ └── test/\n| ├── <date>_<model>\n│ │ ├── all_preds.jsonl\n│ │ ├── metadata.yaml\n│ │ ├── README.md\n│ │ ├── logs/<instance_id>/<exec. artifacts> (Execution Logs)\n│ │ └── trajs/*.traj (Reasoning Traces)\n│ └── ...\n└── validation/\n├── dev\n└── test\n```\n\nTop level directories in `evaluation/` are different splits of SWE-bench (lite, test, verified) and SWE-bench Multimodal.\n* Each subfolder is a submission to that benchmark.\n* A subfolder contains the predictions, results, execution logs, and trajectories (if applicable) for the submission.\n\nThe `validation/` folder contains the validation logs for the dev and test splits of SWE-bench.\nEach of these top level folders consist of repo-level subfolders\n(e.g. `pallets/flask` is a test split repository, so there is a `flask/` folder under `validation/test/`).\nThe `validation/test_202404` is a re-run of validation performed April 2024 to ensure reproducibility of task instances' behavior since SWE-bench was created in September 2023\n(You can read more about the re-run [here](https://github.com/SWE-bench/SWE-bench/tree/main/docs/20240415_eval_bug)).\n\nThese logs are publicly accessible and meant to enable greater reproducibility and transparency of the experiments conducted on the SWE-bench task.\n</details>\n\n## 🔎 Viewing Logs, Trajectories\nYou can download the logs and trajectories for each submission by running the following command to download the data:\n```bash\npython -m analysis.download_logs evaluation/<split>/<date + model>\npython -m analysis.download_logs evaluation/lite/"},{"ref":"E1","kind":"event","title":"kwaipilot/SWE-Compass","date":"2025-12-03T07:47:56+00:00","date_source":"source","source_url":"https://github.com/kwaipilot/SWE-Compass","signal_url":"https://onlylabs.fyi/signals/ee974edf-d22e-4f4a-b4a7-cf7b658fe164","signal_json_url":"https://onlylabs.fyi/signals/ee974edf-d22e-4f4a-b4a7-cf7b658fe164/signal.json","text":"repo_new · kwaipilot/SWE-Compass · signal_desk=repos · occurred_at=2025-12-03T07:47:56+00:00 · url=https://github.com/kwaipilot/SWE-Compass · stars=18 · raw={\"repo\":\"kwaipilot/SWE-Compass\",\"language\":\"Python\"}"},{"ref":"E2","kind":"event","title":"kwaipilot/KAT-Coder-Agent","date":"2025-09-16T09:01:43+00:00","date_source":"source","source_url":"https://github.com/kwaipilot/KAT-Coder-Agent","signal_url":"https://onlylabs.fyi/signals/09dd7b46-b7e6-494c-b49c-86dae5d63931","signal_json_url":"https://onlylabs.fyi/signals/09dd7b46-b7e6-494c-b49c-86dae5d63931/signal.json","text":"repo_new · kwaipilot/KAT-Coder-Agent · signal_desk=repos · occurred_at=2025-09-16T09:01:43+00:00 · url=https://github.com/kwaipilot/KAT-Coder-Agent · stars=1 · raw={\"repo\":\"kwaipilot/KAT-Coder-Agent\"}"},{"ref":"E3","kind":"event","title":"kwaipilot/KAT-Coder","date":"2025-09-16T04:10:32+00:00","date_source":"source","source_url":"https://github.com/kwaipilot/KAT-Coder","signal_url":"https://onlylabs.fyi/signals/f926a4df-2ae9-48d0-8d9b-b18d451888d7","signal_json_url":"https://onlylabs.fyi/signals/f926a4df-2ae9-48d0-8d9b-b18d451888d7/signal.json","text":"repo_new · kwaipilot/KAT-Coder · signal_desk=repos · occurred_at=2025-09-16T04:10:32+00:00 · url=https://github.com/kwaipilot/KAT-Coder · stars=1 · raw={\"repo\":\"kwaipilot/KAT-Coder\",\"language\":\"HTML\"}"},{"ref":"E4","kind":"event","title":"kwaipilot/experiments","date":"2025-09-10T07:18:03+00:00","date_source":"source","source_url":"https://github.com/kwaipilot/experiments","signal_url":"https://onlylabs.fyi/signals/1293dfc1-4102-40d5-bbe8-8eaf68857cd9","signal_json_url":"https://onlylabs.fyi/signals/1293dfc1-4102-40d5-bbe8-8eaf68857cd9/signal.json","text":"repo_forked · kwaipilot/experiments · signal_desk=forks · occurred_at=2025-09-10T07:18:03+00:00 · url=https://github.com/kwaipilot/experiments · raw={\"repo\":\"kwaipilot/experiments\",\"parent\":\"SWE-bench/experiments\"}"}]}