feat: add badcase recording, LLM judge fallback, dual metrics, and fi…

datasets/.gitattributes

@@ -0,0 +1,60 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.avro filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.lz4 filter=lfs diff=lfs merge=lfs -text
+*.mds filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Audio files - uncompressed
+*.pcm filter=lfs diff=lfs merge=lfs -text
+*.sam filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+# Audio files - compressed
+*.aac filter=lfs diff=lfs merge=lfs -text
+*.flac filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.ogg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+# Image files - uncompressed
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.tiff filter=lfs diff=lfs merge=lfs -text
+# Image files - compressed
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text
+# Video files - compressed
+*.mp4 filter=lfs diff=lfs merge=lfs -text
+*.webm filter=lfs diff=lfs merge=lfs -text

datasets/README.md

@@ -0,0 +1,10 @@
+---
+license: apache-2.0
+task_categories:
+- question-answering
+language:
+- en
+---
+**Theory of Mind（心智理论）**指的是：
+理解“别人有自己的想法、信念、情绪、意图”，而且这些可能和自己不同的能力。
+此数据库为 ToM 数据集集合

datasets/SocialIQA/dataset_dict.json

@@ -0,0 +1 @@
+{"splits": ["train", "dev", "test"]}

datasets/SocialIQA/dev/dataset_info.json

@@ -0,0 +1,114 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "State": {
+      "Human_State": {},
+      "Environment_State": {}
+    },
+    "Action": {},
+    "Story": {
+      "background": {
+        "feature": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "_type": "Sequence"
+      },
+      "full_story": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "summary": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "Question": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "Answer": {
+      "Correct_Answer": {
+        "feature": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "_type": "Sequence"
+      },
+      "Wrong_Answer": {
+        "feature": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "_type": "Sequence"
+      }
+    },
+    "Meta": {
+      "id": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "dataset_source": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "dimension": {
+        "feature": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "_type": "Sequence"
+      },
+      "order": {
+        "dtype": "int32",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "difficulty": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "ethics_category": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "charmap": {
+        "feature": {
+          "key": {
+            "dtype": "string",
+            "_type": "Value"
+          },
+          "value": {
+            "dtype": "string",
+            "_type": "Value"
+          }
+        },
+        "_type": "Sequence"
+      },
+      "answerSourcesOrigins": {
+        "feature": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "_type": "Sequence"
+      },
+      "answerSourcesWithCor": {
+        "feature": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "_type": "Sequence"
+      },
+      "promptQuestionFocusChar": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

datasets/SocialIQA/dev/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "522b767197a17e40",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

datasets/SocialIQA/test/dataset_info.json

@@ -0,0 +1,114 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "State": {
+      "Human_State": {},
+      "Environment_State": {}
+    },
+    "Action": {},
+    "Story": {
+      "background": {
+        "feature": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "_type": "Sequence"
+      },
+      "full_story": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "summary": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    },
+    "Question": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "Answer": {
+      "Correct_Answer": {
+        "feature": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "_type": "Sequence"
+      },
+      "Wrong_Answer": {
+        "feature": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "_type": "Sequence"
+      }
+    },
+    "Meta": {
+      "id": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "dataset_source": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "dimension": {
+        "feature": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "_type": "Sequence"
+      },
+      "order": {
+        "dtype": "int32",
+        "_type": "Value"
+      },
+      "task_type": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "difficulty": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "ethics_category": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "charmap": {
+        "feature": {
+          "key": {
+            "dtype": "string",
+            "_type": "Value"
+          },
+          "value": {
+            "dtype": "string",
+            "_type": "Value"
+          }
+        },
+        "_type": "Sequence"
+      },
+      "answerSourcesOrigins": {
+        "feature": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "_type": "Sequence"
+      },
+      "answerSourcesWithCor": {
+        "feature": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "_type": "Sequence"
+      },
+      "promptQuestionFocusChar": {
+        "dtype": "string",
+        "_type": "Value"
+      }
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

datasets/SocialIQA/test/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "9bdbd0b40bc40280",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}