Error-Analysis
ErrorAnalysis
AnchorSR Error Analysis
500道题，严格沿 failure_cases_500.json 的文件顺序排列，每题对照三个SFT模型。
推荐从第001题开始，点击“下一题”逐题阅读。
也可使用本页上方 Dataset Viewer，一行就是一题：图片、问题、标准答案、三个模型完整输出。
Q-Spatial 150题，SpatialRGPT 175题，VSI 175题（仅尺寸、距离，不含面积）。
全部500题：每个模型均提供原图和标注图，共3000张图；O编号和帧号来自模型声明。
原图与标注图使用相同源帧和拼图顺序。无效框/帧号或无声明会注明，不补造；此时标注页可能没有框。
原图指未添加模型框的网页展示副本，经过等比例缩放与JPEG编码，并非原始文件字节；SpatialRGPT原有区域标记保留。
视频只展示可绘制对象涉及帧，无有效框时展示第1帧，非完整视频。原图/标注图使用相同帧。
原生输出完整保留，包括循环、截断和格式错误；未修改答案或重新评分。
所有模型均为SFT，不是baseline。至少一个模型在该题失败，其他模型可能答对。… See the full description on the dataset page: https://huggingface.co/datasets/AnchorSR/ErrorAnalysis.camerabench_error_analysisvideo_error_analysisag_news_error_analysisThis is a dataset created for testing purposes in the context of this tutorial: https://rubrix.readthedocs.io/en/master/tutorials/08-error_analysis_using_loss.html
You can find more details on section 5. of the tutorial and the corresponding dataset with corrected labels at https://huggingface.co/datasets/Recognai/ag_news_corrected_labels
granite_4.0_h_small_FP8_test_detoxificability_annotation_error_analysisqwen-base-error-analysis
Qwen3.5-4B-Base Error Analysis Dataset
This dataset contains 10 diverse examples where the base language model Qwen3.5-4B-Base makes incorrect or unexpected predictions. It was created as part of an exploration of base model blind spots and failure modes.
Model Tested
Model: Qwen/Qwen3.5-4B-Base
Type: Pre-trained base model (not instruction-tuned)
Parameters: 4B
Architecture: Causal Language Model with hybrid Gated DeltaNet + Attention layers
Dataset Structure… See the full description on the dataset page: https://huggingface.co/datasets/ArslanMZahid/qwen-base-error-analysis.