diff --git a/eval/dovodka/blind-read/KEY-2-do-not-show-judges.json b/eval/dovodka/blind-read/KEY-2-do-not-show-judges.json new file mode 100644 index 00000000..aff572b8 --- /dev/null +++ b/eval/dovodka/blind-read/KEY-2-do-not-show-judges.json @@ -0,0 +1,362 @@ +[ + { + "alias": "ed01", + "kind": "null", + "prompt": "p9", + "chapter": 7, + "chunk": 0, + "arm_A": "p9-low", + "arm_B": "low2" + }, + { + "alias": "ed02", + "kind": "null", + "prompt": "p9", + "chapter": 13, + "chunk": 0, + "arm_A": "low2", + "arm_B": "p9-low" + }, + { + "alias": "ed03", + "kind": "real", + "prompt": "p9", + "chapter": 10, + "chunk": 0, + "arm_A": "p9-low", + "arm_B": "p9-off" + }, + { + "alias": "ed04", + "kind": "real", + "prompt": "p9", + "chapter": 12, + "chunk": 1, + "arm_A": "p9-off", + "arm_B": "p9-low" + }, + { + "alias": "ed05", + "kind": "null", + "prompt": "p9", + "chapter": 12, + "chunk": 0, + "arm_A": "low2", + "arm_B": "p9-low" + }, + { + "alias": "ed06", + "kind": "real", + "prompt": "p7", + "chapter": 3, + "chunk": 1, + "arm_A": "p7-low", + "arm_B": "p7-off" + }, + { + "alias": "ed07", + "kind": "real", + "prompt": "p9", + "chapter": 3, + "chunk": 0, + "arm_A": "p9-low", + "arm_B": "p9-off" + }, + { + "alias": "ed08", + "kind": "real", + "prompt": "p7", + "chapter": 10, + "chunk": 0, + "arm_A": "p7-off", + "arm_B": "p7-low" + }, + { + "alias": "ed09", + "kind": "real", + "prompt": "p9", + "chapter": 9, + "chunk": 0, + "arm_A": "p9-off", + "arm_B": "p9-low" + }, + { + "alias": "ed10", + "kind": "null", + "prompt": "p9", + "chapter": 8, + "chunk": 0, + "arm_A": "p9-low", + "arm_B": "low2" + }, + { + "alias": "ed11", + "kind": "real", + "prompt": "p7", + "chapter": 8, + "chunk": 0, + "arm_A": "p7-low", + "arm_B": "p7-off" + }, + { + "alias": "ed12", + "kind": "real", + "prompt": "p7", + "chapter": 5, + "chunk": 0, + "arm_A": "p7-off", + "arm_B": "p7-low" + }, + { + "alias": "ed13", + "kind": "null", + "prompt": "p9", + "chapter": 16, + "chunk": 0, + "arm_A": "low2", + "arm_B": "p9-low" + }, + { + "alias": "ed14", + "kind": "real", + "prompt": "p7", + "chapter": 16, + "chunk": 0, + "arm_A": "p7-low", + "arm_B": "p7-off" + }, + { + "alias": "ed15", + "kind": "real", + "prompt": "p9", + "chapter": 8, + "chunk": 0, + "arm_A": "p9-off", + "arm_B": "p9-low" + }, + { + "alias": "ed16", + "kind": "null", + "prompt": "p9", + "chapter": 3, + "chunk": 1, + "arm_A": "p9-low", + "arm_B": "low2" + }, + { + "alias": "ed17", + "kind": "real", + "prompt": "p9", + "chapter": 6, + "chunk": 0, + "arm_A": "p9-off", + "arm_B": "p9-low" + }, + { + "alias": "ed18", + "kind": "real", + "prompt": "p7", + "chapter": 9, + "chunk": 0, + "arm_A": "p7-off", + "arm_B": "p7-low" + }, + { + "alias": "ed19", + "kind": "real", + "prompt": "p9", + "chapter": 1, + "chunk": 0, + "arm_A": "p9-off", + "arm_B": "p9-low" + }, + { + "alias": "ed20", + "kind": "real", + "prompt": "p9", + "chapter": 7, + "chunk": 0, + "arm_A": "p9-off", + "arm_B": "p9-low" + }, + { + "alias": "ed21", + "kind": "real", + "prompt": "p9", + "chapter": 2, + "chunk": 0, + "arm_A": "p9-low", + "arm_B": "p9-off" + }, + { + "alias": "ed22", + "kind": "real", + "prompt": "p9", + "chapter": 3, + "chunk": 1, + "arm_A": "p9-low", + "arm_B": "p9-off" + }, + { + "alias": "ed23", + "kind": "real", + "prompt": "p7", + "chapter": 3, + "chunk": 0, + "arm_A": "p7-low", + "arm_B": "p7-off" + }, + { + "alias": "ed24", + "kind": "null", + "prompt": "p9", + "chapter": 3, + "chunk": 0, + "arm_A": "p9-low", + "arm_B": "low2" + }, + { + "alias": "ed25", + "kind": "null", + "prompt": "p9", + "chapter": 10, + "chunk": 0, + "arm_A": "p9-low", + "arm_B": "low2" + }, + { + "alias": "ed26", + "kind": "real", + "prompt": "p7", + "chapter": 6, + "chunk": 0, + "arm_A": "p7-low", + "arm_B": "p7-off" + }, + { + "alias": "ed27", + "kind": "real", + "prompt": "p9", + "chapter": 16, + "chunk": 0, + "arm_A": "p9-low", + "arm_B": "p9-off" + }, + { + "alias": "ed28", + "kind": "real", + "prompt": "p7", + "chapter": 7, + "chunk": 0, + "arm_A": "p7-low", + "arm_B": "p7-off" + }, + { + "alias": "ed29", + "kind": "real", + "prompt": "p7", + "chapter": 13, + "chunk": 0, + "arm_A": "p7-low", + "arm_B": "p7-off" + }, + { + "alias": "ed30", + "kind": "real", + "prompt": "p7", + "chapter": 2, + "chunk": 0, + "arm_A": "p7-off", + "arm_B": "p7-low" + }, + { + "alias": "ed31", + "kind": "real", + "prompt": "p9", + "chapter": 15, + "chunk": 0, + "arm_A": "p9-off", + "arm_B": "p9-low" + }, + { + "alias": "ed32", + "kind": "real", + "prompt": "p7", + "chapter": 12, + "chunk": 1, + "arm_A": "p7-low", + "arm_B": "p7-off" + }, + { + "alias": "ed33", + "kind": "null", + "prompt": "p9", + "chapter": 15, + "chunk": 0, + "arm_A": "low2", + "arm_B": "p9-low" + }, + { + "alias": "ed34", + "kind": "real", + "prompt": "p7", + "chapter": 1, + "chunk": 0, + "arm_A": "p7-off", + "arm_B": "p7-low" + }, + { + "alias": "ed35", + "kind": "real", + "prompt": "p9", + "chapter": 5, + "chunk": 0, + "arm_A": "p9-low", + "arm_B": "p9-off" + }, + { + "alias": "ed36", + "kind": "real", + "prompt": "p9", + "chapter": 12, + "chunk": 0, + "arm_A": "p9-low", + "arm_B": "p9-off" + }, + { + "alias": "ed37", + "kind": "real", + "prompt": "p7", + "chapter": 15, + "chunk": 0, + "arm_A": "p7-off", + "arm_B": "p7-low" + }, + { + "alias": "ed38", + "kind": "real", + "prompt": "p7", + "chapter": 12, + "chunk": 0, + "arm_A": "p7-off", + "arm_B": "p7-low" + }, + { + "alias": "ed39", + "kind": "null", + "prompt": "p9", + "chapter": 6, + "chunk": 0, + "arm_A": "low2", + "arm_B": "p9-low" + }, + { + "alias": "ed40", + "kind": "real", + "prompt": "p9", + "chapter": 13, + "chunk": 0, + "arm_A": "p9-low", + "arm_B": "p9-off" + } +] \ No newline at end of file