Upload folder using huggingface_hub
Browse files- baseline/score_report.json +1719 -0
- baseline/temporal_wordings.jsonl +0 -0
- baseline/validation_scores.jsonl +0 -0
- report.json +0 -0
- retriever.pt +3 -0
- retriever_epoch_01.pt +3 -0
- retriever_epoch_02.pt +3 -0
- temporal_wordings.jsonl +0 -0
- validation_scores_epoch_01.jsonl +0 -0
- validation_scores_epoch_02.jsonl +0 -0
baseline/score_report.json
ADDED
|
@@ -0,0 +1,1719 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"checkpoint": "/home/zhangchao/work/minye_training/mixed_retrieval_normal/retriever.pt",
|
| 3 |
+
"use_retrieval_rope": false,
|
| 4 |
+
"time_embedding_size": 128,
|
| 5 |
+
"memory_temporal_positions_shuffled": false,
|
| 6 |
+
"temporal_wording_counts": {
|
| 7 |
+
"train:after": 1,
|
| 8 |
+
"train:before": 98,
|
| 9 |
+
"train:comparison": 903,
|
| 10 |
+
"train:earliest": 783,
|
| 11 |
+
"train:latest": 748,
|
| 12 |
+
"train:session": 1431,
|
| 13 |
+
"train:unmatched": 390,
|
| 14 |
+
"validation:before": 70,
|
| 15 |
+
"validation:comparison": 414,
|
| 16 |
+
"validation:earliest": 354,
|
| 17 |
+
"validation:latest": 358,
|
| 18 |
+
"validation:session": 789,
|
| 19 |
+
"validation:unmatched": 161
|
| 20 |
+
},
|
| 21 |
+
"task_distribution": {
|
| 22 |
+
"all_complete_samples": {
|
| 23 |
+
"sample_count": 6168,
|
| 24 |
+
"rag_query_count": 10985,
|
| 25 |
+
"control_query_count": 111,
|
| 26 |
+
"by_task": {
|
| 27 |
+
"change_comparison": {
|
| 28 |
+
"rag_query_count": 1480,
|
| 29 |
+
"control_query_count": 0
|
| 30 |
+
},
|
| 31 |
+
"current_only_control": {
|
| 32 |
+
"rag_query_count": 0,
|
| 33 |
+
"control_query_count": 110
|
| 34 |
+
},
|
| 35 |
+
"direct_recall": {
|
| 36 |
+
"rag_query_count": 2814,
|
| 37 |
+
"control_query_count": 0
|
| 38 |
+
},
|
| 39 |
+
"historical_state": {
|
| 40 |
+
"rag_query_count": 1508,
|
| 41 |
+
"control_query_count": 0
|
| 42 |
+
},
|
| 43 |
+
"latest_state": {
|
| 44 |
+
"rag_query_count": 1470,
|
| 45 |
+
"control_query_count": 0
|
| 46 |
+
},
|
| 47 |
+
"multi_hop_composition": {
|
| 48 |
+
"rag_query_count": 1671,
|
| 49 |
+
"control_query_count": 0
|
| 50 |
+
},
|
| 51 |
+
"recent_context_control": {
|
| 52 |
+
"rag_query_count": 0,
|
| 53 |
+
"control_query_count": 1
|
| 54 |
+
},
|
| 55 |
+
"temporal_localization": {
|
| 56 |
+
"rag_query_count": 2042,
|
| 57 |
+
"control_query_count": 0
|
| 58 |
+
}
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"train_split": {
|
| 62 |
+
"sample_count": 5014,
|
| 63 |
+
"rag_query_count": 7000,
|
| 64 |
+
"control_query_count": 0,
|
| 65 |
+
"by_task": {
|
| 66 |
+
"change_comparison": {
|
| 67 |
+
"rag_query_count": 1010,
|
| 68 |
+
"control_query_count": 0
|
| 69 |
+
},
|
| 70 |
+
"direct_recall": {
|
| 71 |
+
"rag_query_count": 1323,
|
| 72 |
+
"control_query_count": 0
|
| 73 |
+
},
|
| 74 |
+
"historical_state": {
|
| 75 |
+
"rag_query_count": 1008,
|
| 76 |
+
"control_query_count": 0
|
| 77 |
+
},
|
| 78 |
+
"latest_state": {
|
| 79 |
+
"rag_query_count": 1013,
|
| 80 |
+
"control_query_count": 0
|
| 81 |
+
},
|
| 82 |
+
"multi_hop_composition": {
|
| 83 |
+
"rag_query_count": 1323,
|
| 84 |
+
"control_query_count": 0
|
| 85 |
+
},
|
| 86 |
+
"temporal_localization": {
|
| 87 |
+
"rag_query_count": 1323,
|
| 88 |
+
"control_query_count": 0
|
| 89 |
+
}
|
| 90 |
+
}
|
| 91 |
+
},
|
| 92 |
+
"validation_split": {
|
| 93 |
+
"sample_count": 1154,
|
| 94 |
+
"rag_query_count": 3985,
|
| 95 |
+
"control_query_count": 111,
|
| 96 |
+
"by_task": {
|
| 97 |
+
"change_comparison": {
|
| 98 |
+
"rag_query_count": 470,
|
| 99 |
+
"control_query_count": 0
|
| 100 |
+
},
|
| 101 |
+
"current_only_control": {
|
| 102 |
+
"rag_query_count": 0,
|
| 103 |
+
"control_query_count": 110
|
| 104 |
+
},
|
| 105 |
+
"direct_recall": {
|
| 106 |
+
"rag_query_count": 1491,
|
| 107 |
+
"control_query_count": 0
|
| 108 |
+
},
|
| 109 |
+
"historical_state": {
|
| 110 |
+
"rag_query_count": 500,
|
| 111 |
+
"control_query_count": 0
|
| 112 |
+
},
|
| 113 |
+
"latest_state": {
|
| 114 |
+
"rag_query_count": 457,
|
| 115 |
+
"control_query_count": 0
|
| 116 |
+
},
|
| 117 |
+
"multi_hop_composition": {
|
| 118 |
+
"rag_query_count": 348,
|
| 119 |
+
"control_query_count": 0
|
| 120 |
+
},
|
| 121 |
+
"recent_context_control": {
|
| 122 |
+
"rag_query_count": 0,
|
| 123 |
+
"control_query_count": 1
|
| 124 |
+
},
|
| 125 |
+
"temporal_localization": {
|
| 126 |
+
"rag_query_count": 719,
|
| 127 |
+
"control_query_count": 0
|
| 128 |
+
}
|
| 129 |
+
}
|
| 130 |
+
}
|
| 131 |
+
},
|
| 132 |
+
"validation": {
|
| 133 |
+
"query_count": 3985,
|
| 134 |
+
"recall_at_k": {
|
| 135 |
+
"1": 0.6943565607070923,
|
| 136 |
+
"3": 0.9150701761245728,
|
| 137 |
+
"5": 0.9561480283737183
|
| 138 |
+
},
|
| 139 |
+
"all_support_em_at_k": {
|
| 140 |
+
"3": 0.8687578439712524,
|
| 141 |
+
"5": 0.9327477812767029
|
| 142 |
+
},
|
| 143 |
+
"by_speaker_query_type": {
|
| 144 |
+
"fact_to_person": {
|
| 145 |
+
"query_count": 786,
|
| 146 |
+
"recall_at_k": {
|
| 147 |
+
"1": 0.825658917427063,
|
| 148 |
+
"3": 0.9750257730484009,
|
| 149 |
+
"5": 0.9804449677467346
|
| 150 |
+
},
|
| 151 |
+
"all_support_em_at_k": {
|
| 152 |
+
"3": 0.9631043076515198,
|
| 153 |
+
"5": 0.9681933522224426
|
| 154 |
+
}
|
| 155 |
+
},
|
| 156 |
+
"person_to_fact": {
|
| 157 |
+
"query_count": 969,
|
| 158 |
+
"recall_at_k": {
|
| 159 |
+
"1": 0.7372819781303406,
|
| 160 |
+
"3": 0.9379526972770691,
|
| 161 |
+
"5": 0.9745736718177795
|
| 162 |
+
},
|
| 163 |
+
"all_support_em_at_k": {
|
| 164 |
+
"3": 0.9050567746162415,
|
| 165 |
+
"5": 0.9659442901611328
|
| 166 |
+
}
|
| 167 |
+
},
|
| 168 |
+
"self_to_fact": {
|
| 169 |
+
"query_count": 509,
|
| 170 |
+
"recall_at_k": {
|
| 171 |
+
"1": 0.2673543095588684,
|
| 172 |
+
"3": 0.6982645392417908,
|
| 173 |
+
"5": 0.898657500743866
|
| 174 |
+
},
|
| 175 |
+
"all_support_em_at_k": {
|
| 176 |
+
"3": 0.48919451236724854,
|
| 177 |
+
"5": 0.8251473307609558
|
| 178 |
+
}
|
| 179 |
+
},
|
| 180 |
+
"speaker_independent": {
|
| 181 |
+
"query_count": 1721,
|
| 182 |
+
"recall_at_k": {
|
| 183 |
+
"1": 0.7365096807479858,
|
| 184 |
+
"3": 0.9389259815216064,
|
| 185 |
+
"5": 0.9516802430152893
|
| 186 |
+
},
|
| 187 |
+
"all_support_em_at_k": {
|
| 188 |
+
"3": 0.9174898266792297,
|
| 189 |
+
"5": 0.9296920299530029
|
| 190 |
+
}
|
| 191 |
+
}
|
| 192 |
+
},
|
| 193 |
+
"by_task_and_speaker_query_type": {
|
| 194 |
+
"change_comparison": {
|
| 195 |
+
"fact_to_person": {
|
| 196 |
+
"query_count": 74,
|
| 197 |
+
"recall_at_k": {
|
| 198 |
+
"1": 0.5,
|
| 199 |
+
"3": 1.0,
|
| 200 |
+
"5": 1.0
|
| 201 |
+
},
|
| 202 |
+
"all_support_em_at_k": {
|
| 203 |
+
"3": 1.0,
|
| 204 |
+
"5": 1.0
|
| 205 |
+
}
|
| 206 |
+
},
|
| 207 |
+
"person_to_fact": {
|
| 208 |
+
"query_count": 88,
|
| 209 |
+
"recall_at_k": {
|
| 210 |
+
"1": 0.5,
|
| 211 |
+
"3": 0.9545454382896423,
|
| 212 |
+
"5": 1.0
|
| 213 |
+
},
|
| 214 |
+
"all_support_em_at_k": {
|
| 215 |
+
"3": 0.9090908765792847,
|
| 216 |
+
"5": 1.0
|
| 217 |
+
}
|
| 218 |
+
},
|
| 219 |
+
"self_to_fact": {
|
| 220 |
+
"query_count": 99,
|
| 221 |
+
"recall_at_k": {
|
| 222 |
+
"1": 0.1111111119389534,
|
| 223 |
+
"3": 0.49494948983192444,
|
| 224 |
+
"5": 0.8282828330993652
|
| 225 |
+
},
|
| 226 |
+
"all_support_em_at_k": {
|
| 227 |
+
"3": 0.09090909361839294,
|
| 228 |
+
"5": 0.6565656661987305
|
| 229 |
+
}
|
| 230 |
+
},
|
| 231 |
+
"speaker_independent": {
|
| 232 |
+
"query_count": 209,
|
| 233 |
+
"recall_at_k": {
|
| 234 |
+
"1": 0.49441784620285034,
|
| 235 |
+
"3": 0.9896332025527954,
|
| 236 |
+
"5": 0.9932217597961426
|
| 237 |
+
},
|
| 238 |
+
"all_support_em_at_k": {
|
| 239 |
+
"3": 0.9856459498405457,
|
| 240 |
+
"5": 0.9904305934906006
|
| 241 |
+
}
|
| 242 |
+
}
|
| 243 |
+
},
|
| 244 |
+
"direct_recall": {
|
| 245 |
+
"fact_to_person": {
|
| 246 |
+
"query_count": 524,
|
| 247 |
+
"recall_at_k": {
|
| 248 |
+
"1": 0.9266858100891113,
|
| 249 |
+
"3": 0.9726463556289673,
|
| 250 |
+
"5": 0.980120837688446
|
| 251 |
+
},
|
| 252 |
+
"all_support_em_at_k": {
|
| 253 |
+
"3": 0.9599236249923706,
|
| 254 |
+
"5": 0.9675572514533997
|
| 255 |
+
}
|
| 256 |
+
},
|
| 257 |
+
"person_to_fact": {
|
| 258 |
+
"query_count": 306,
|
| 259 |
+
"recall_at_k": {
|
| 260 |
+
"1": 0.8153594732284546,
|
| 261 |
+
"3": 0.9229303598403931,
|
| 262 |
+
"5": 0.9507080912590027
|
| 263 |
+
},
|
| 264 |
+
"all_support_em_at_k": {
|
| 265 |
+
"3": 0.9117646813392639,
|
| 266 |
+
"5": 0.9346405267715454
|
| 267 |
+
}
|
| 268 |
+
},
|
| 269 |
+
"self_to_fact": {
|
| 270 |
+
"query_count": 57,
|
| 271 |
+
"recall_at_k": {
|
| 272 |
+
"1": 0.4312865138053894,
|
| 273 |
+
"3": 0.5979532599449158,
|
| 274 |
+
"5": 0.6769006252288818
|
| 275 |
+
},
|
| 276 |
+
"all_support_em_at_k": {
|
| 277 |
+
"3": 0.42105263471603394,
|
| 278 |
+
"5": 0.5438596606254578
|
| 279 |
+
}
|
| 280 |
+
},
|
| 281 |
+
"speaker_independent": {
|
| 282 |
+
"query_count": 604,
|
| 283 |
+
"recall_at_k": {
|
| 284 |
+
"1": 0.8199503421783447,
|
| 285 |
+
"3": 0.9064569473266602,
|
| 286 |
+
"5": 0.9199779629707336
|
| 287 |
+
},
|
| 288 |
+
"all_support_em_at_k": {
|
| 289 |
+
"3": 0.8824503421783447,
|
| 290 |
+
"5": 0.8923841118812561
|
| 291 |
+
}
|
| 292 |
+
}
|
| 293 |
+
},
|
| 294 |
+
"historical_state": {
|
| 295 |
+
"fact_to_person": {
|
| 296 |
+
"query_count": 91,
|
| 297 |
+
"recall_at_k": {
|
| 298 |
+
"1": 0.8681318759918213,
|
| 299 |
+
"3": 1.0,
|
| 300 |
+
"5": 1.0
|
| 301 |
+
},
|
| 302 |
+
"all_support_em_at_k": {
|
| 303 |
+
"3": 1.0,
|
| 304 |
+
"5": 1.0
|
| 305 |
+
}
|
| 306 |
+
},
|
| 307 |
+
"person_to_fact": {
|
| 308 |
+
"query_count": 125,
|
| 309 |
+
"recall_at_k": {
|
| 310 |
+
"1": 0.8320000171661377,
|
| 311 |
+
"3": 1.0,
|
| 312 |
+
"5": 1.0
|
| 313 |
+
},
|
| 314 |
+
"all_support_em_at_k": {
|
| 315 |
+
"3": 1.0,
|
| 316 |
+
"5": 1.0
|
| 317 |
+
}
|
| 318 |
+
},
|
| 319 |
+
"self_to_fact": {
|
| 320 |
+
"query_count": 82,
|
| 321 |
+
"recall_at_k": {
|
| 322 |
+
"1": 0.353658527135849,
|
| 323 |
+
"3": 0.9512194991111755,
|
| 324 |
+
"5": 1.0
|
| 325 |
+
},
|
| 326 |
+
"all_support_em_at_k": {
|
| 327 |
+
"3": 0.9512194991111755,
|
| 328 |
+
"5": 1.0
|
| 329 |
+
}
|
| 330 |
+
},
|
| 331 |
+
"speaker_independent": {
|
| 332 |
+
"query_count": 202,
|
| 333 |
+
"recall_at_k": {
|
| 334 |
+
"1": 0.896039605140686,
|
| 335 |
+
"3": 0.9975247383117676,
|
| 336 |
+
"5": 0.9975247383117676
|
| 337 |
+
},
|
| 338 |
+
"all_support_em_at_k": {
|
| 339 |
+
"3": 0.9950494766235352,
|
| 340 |
+
"5": 0.9950494766235352
|
| 341 |
+
}
|
| 342 |
+
}
|
| 343 |
+
},
|
| 344 |
+
"latest_state": {
|
| 345 |
+
"fact_to_person": {
|
| 346 |
+
"query_count": 31,
|
| 347 |
+
"recall_at_k": {
|
| 348 |
+
"1": 0.5483871102333069,
|
| 349 |
+
"3": 1.0,
|
| 350 |
+
"5": 1.0
|
| 351 |
+
},
|
| 352 |
+
"all_support_em_at_k": {
|
| 353 |
+
"3": 1.0,
|
| 354 |
+
"5": 1.0
|
| 355 |
+
}
|
| 356 |
+
},
|
| 357 |
+
"person_to_fact": {
|
| 358 |
+
"query_count": 92,
|
| 359 |
+
"recall_at_k": {
|
| 360 |
+
"1": 0.46195653080940247,
|
| 361 |
+
"3": 0.989130437374115,
|
| 362 |
+
"5": 1.0
|
| 363 |
+
},
|
| 364 |
+
"all_support_em_at_k": {
|
| 365 |
+
"3": 0.989130437374115,
|
| 366 |
+
"5": 1.0
|
| 367 |
+
}
|
| 368 |
+
},
|
| 369 |
+
"self_to_fact": {
|
| 370 |
+
"query_count": 82,
|
| 371 |
+
"recall_at_k": {
|
| 372 |
+
"1": 0.18292683362960815,
|
| 373 |
+
"3": 0.8536585569381714,
|
| 374 |
+
"5": 1.0
|
| 375 |
+
},
|
| 376 |
+
"all_support_em_at_k": {
|
| 377 |
+
"3": 0.8536585569381714,
|
| 378 |
+
"5": 1.0
|
| 379 |
+
}
|
| 380 |
+
},
|
| 381 |
+
"speaker_independent": {
|
| 382 |
+
"query_count": 252,
|
| 383 |
+
"recall_at_k": {
|
| 384 |
+
"1": 0.4523809552192688,
|
| 385 |
+
"3": 0.9821428656578064,
|
| 386 |
+
"5": 0.9980158805847168
|
| 387 |
+
},
|
| 388 |
+
"all_support_em_at_k": {
|
| 389 |
+
"3": 0.9801587462425232,
|
| 390 |
+
"5": 0.9960317611694336
|
| 391 |
+
}
|
| 392 |
+
}
|
| 393 |
+
},
|
| 394 |
+
"multi_hop_composition": {
|
| 395 |
+
"fact_to_person": {
|
| 396 |
+
"query_count": 66,
|
| 397 |
+
"recall_at_k": {
|
| 398 |
+
"1": 0.46037158370018005,
|
| 399 |
+
"3": 0.9197511076927185,
|
| 400 |
+
"5": 0.9249458909034729
|
| 401 |
+
},
|
| 402 |
+
"all_support_em_at_k": {
|
| 403 |
+
"3": 0.8787878751754761,
|
| 404 |
+
"5": 0.8787878751754761
|
| 405 |
+
}
|
| 406 |
+
},
|
| 407 |
+
"person_to_fact": {
|
| 408 |
+
"query_count": 84,
|
| 409 |
+
"recall_at_k": {
|
| 410 |
+
"1": 0.2699546217918396,
|
| 411 |
+
"3": 0.6632086038589478,
|
| 412 |
+
"5": 0.9249432682991028
|
| 413 |
+
},
|
| 414 |
+
"all_support_em_at_k": {
|
| 415 |
+
"3": 0.380952388048172,
|
| 416 |
+
"5": 0.8928571343421936
|
| 417 |
+
}
|
| 418 |
+
},
|
| 419 |
+
"self_to_fact": {
|
| 420 |
+
"query_count": 168,
|
| 421 |
+
"recall_at_k": {
|
| 422 |
+
"1": 0.2738095223903656,
|
| 423 |
+
"3": 0.6547619104385376,
|
| 424 |
+
"5": 0.9375
|
| 425 |
+
},
|
| 426 |
+
"all_support_em_at_k": {
|
| 427 |
+
"3": 0.3392857015132904,
|
| 428 |
+
"5": 0.8809523582458496
|
| 429 |
+
}
|
| 430 |
+
},
|
| 431 |
+
"speaker_independent": {
|
| 432 |
+
"query_count": 30,
|
| 433 |
+
"recall_at_k": {
|
| 434 |
+
"1": 0.2761111259460449,
|
| 435 |
+
"3": 0.5186111330986023,
|
| 436 |
+
"5": 0.5752777457237244
|
| 437 |
+
},
|
| 438 |
+
"all_support_em_at_k": {
|
| 439 |
+
"3": 0.20000000298023224,
|
| 440 |
+
"5": 0.2666666805744171
|
| 441 |
+
}
|
| 442 |
+
}
|
| 443 |
+
},
|
| 444 |
+
"temporal_localization": {
|
| 445 |
+
"person_to_fact": {
|
| 446 |
+
"query_count": 274,
|
| 447 |
+
"recall_at_k": {
|
| 448 |
+
"1": 0.9187955856323242,
|
| 449 |
+
"3": 0.9881386756896973,
|
| 450 |
+
"5": 0.9881386756896973
|
| 451 |
+
},
|
| 452 |
+
"all_support_em_at_k": {
|
| 453 |
+
"3": 0.985401451587677,
|
| 454 |
+
"5": 0.985401451587677
|
| 455 |
+
}
|
| 456 |
+
},
|
| 457 |
+
"self_to_fact": {
|
| 458 |
+
"query_count": 21,
|
| 459 |
+
"recall_at_k": {
|
| 460 |
+
"1": 0.5,
|
| 461 |
+
"3": 0.682539701461792,
|
| 462 |
+
"5": 0.7301587462425232
|
| 463 |
+
},
|
| 464 |
+
"all_support_em_at_k": {
|
| 465 |
+
"3": 0.5238094925880432,
|
| 466 |
+
"5": 0.5714285969734192
|
| 467 |
+
}
|
| 468 |
+
},
|
| 469 |
+
"speaker_independent": {
|
| 470 |
+
"query_count": 424,
|
| 471 |
+
"recall_at_k": {
|
| 472 |
+
"1": 0.8624213337898254,
|
| 473 |
+
"3": 0.9363208413124084,
|
| 474 |
+
"5": 0.9536163806915283
|
| 475 |
+
},
|
| 476 |
+
"all_support_em_at_k": {
|
| 477 |
+
"3": 0.9103773832321167,
|
| 478 |
+
"5": 0.9292452931404114
|
| 479 |
+
}
|
| 480 |
+
}
|
| 481 |
+
}
|
| 482 |
+
},
|
| 483 |
+
"by_task": {
|
| 484 |
+
"change_comparison": {
|
| 485 |
+
"query_count": 470,
|
| 486 |
+
"recall_at_k": {
|
| 487 |
+
"1": 0.4156028628349304,
|
| 488 |
+
"3": 0.8804963827133179,
|
| 489 |
+
"5": 0.9608155488967896
|
| 490 |
+
},
|
| 491 |
+
"all_support_em_at_k": {
|
| 492 |
+
"3": 0.785106360912323,
|
| 493 |
+
"5": 0.9234042763710022
|
| 494 |
+
}
|
| 495 |
+
},
|
| 496 |
+
"direct_recall": {
|
| 497 |
+
"query_count": 1491,
|
| 498 |
+
"recall_at_k": {
|
| 499 |
+
"1": 0.8416610360145569,
|
| 500 |
+
"3": 0.9213054776191711,
|
| 501 |
+
"5": 0.9381287693977356
|
| 502 |
+
},
|
| 503 |
+
"all_support_em_at_k": {
|
| 504 |
+
"3": 0.8980550169944763,
|
| 505 |
+
"5": 0.9141515493392944
|
| 506 |
+
}
|
| 507 |
+
},
|
| 508 |
+
"historical_state": {
|
| 509 |
+
"query_count": 500,
|
| 510 |
+
"recall_at_k": {
|
| 511 |
+
"1": 0.7860000133514404,
|
| 512 |
+
"3": 0.9909999966621399,
|
| 513 |
+
"5": 0.9990000128746033
|
| 514 |
+
},
|
| 515 |
+
"all_support_em_at_k": {
|
| 516 |
+
"3": 0.9900000095367432,
|
| 517 |
+
"5": 0.9980000257492065
|
| 518 |
+
}
|
| 519 |
+
},
|
| 520 |
+
"latest_state": {
|
| 521 |
+
"query_count": 457,
|
| 522 |
+
"recall_at_k": {
|
| 523 |
+
"1": 0.4124726355075836,
|
| 524 |
+
"3": 0.9617067575454712,
|
| 525 |
+
"5": 0.9989058971405029
|
| 526 |
+
},
|
| 527 |
+
"all_support_em_at_k": {
|
| 528 |
+
"3": 0.9606127142906189,
|
| 529 |
+
"5": 0.9978117942810059
|
| 530 |
+
}
|
| 531 |
+
},
|
| 532 |
+
"multi_hop_composition": {
|
| 533 |
+
"query_count": 348,
|
| 534 |
+
"recall_at_k": {
|
| 535 |
+
"1": 0.30845990777015686,
|
| 536 |
+
"3": 0.695320188999176,
|
| 537 |
+
"5": 0.9008620381355286
|
| 538 |
+
},
|
| 539 |
+
"all_support_em_at_k": {
|
| 540 |
+
"3": 0.4396551847457886,
|
| 541 |
+
"5": 0.8304597735404968
|
| 542 |
+
}
|
| 543 |
+
},
|
| 544 |
+
"temporal_localization": {
|
| 545 |
+
"query_count": 719,
|
| 546 |
+
"recall_at_k": {
|
| 547 |
+
"1": 0.8733193874359131,
|
| 548 |
+
"3": 0.9486554861068726,
|
| 549 |
+
"5": 0.9602457284927368
|
| 550 |
+
},
|
| 551 |
+
"all_support_em_at_k": {
|
| 552 |
+
"3": 0.92767733335495,
|
| 553 |
+
"5": 0.9401947259902954
|
| 554 |
+
}
|
| 555 |
+
}
|
| 556 |
+
},
|
| 557 |
+
"semantic_only": {
|
| 558 |
+
"query_count": 3985,
|
| 559 |
+
"recall_at_k": {
|
| 560 |
+
"1": 0.6349337697029114,
|
| 561 |
+
"3": 0.9045097827911377,
|
| 562 |
+
"5": 0.9561062455177307
|
| 563 |
+
},
|
| 564 |
+
"all_support_em_at_k": {
|
| 565 |
+
"3": 0.8587201833724976,
|
| 566 |
+
"5": 0.9324968457221985
|
| 567 |
+
},
|
| 568 |
+
"by_speaker_query_type": {
|
| 569 |
+
"fact_to_person": {
|
| 570 |
+
"query_count": 786,
|
| 571 |
+
"recall_at_k": {
|
| 572 |
+
"1": 0.7658624649047852,
|
| 573 |
+
"3": 0.9737535119056702,
|
| 574 |
+
"5": 0.982141375541687
|
| 575 |
+
},
|
| 576 |
+
"all_support_em_at_k": {
|
| 577 |
+
"3": 0.9618320465087891,
|
| 578 |
+
"5": 0.9694656729698181
|
| 579 |
+
}
|
| 580 |
+
},
|
| 581 |
+
"person_to_fact": {
|
| 582 |
+
"query_count": 969,
|
| 583 |
+
"recall_at_k": {
|
| 584 |
+
"1": 0.6729888916015625,
|
| 585 |
+
"3": 0.9353727102279663,
|
| 586 |
+
"5": 0.974057674407959
|
| 587 |
+
},
|
| 588 |
+
"all_support_em_at_k": {
|
| 589 |
+
"3": 0.8998968005180359,
|
| 590 |
+
"5": 0.9649122953414917
|
| 591 |
+
}
|
| 592 |
+
},
|
| 593 |
+
"self_to_fact": {
|
| 594 |
+
"query_count": 509,
|
| 595 |
+
"recall_at_k": {
|
| 596 |
+
"1": 0.24476097524166107,
|
| 597 |
+
"3": 0.6501309275627136,
|
| 598 |
+
"5": 0.8966928124427795
|
| 599 |
+
},
|
| 600 |
+
"all_support_em_at_k": {
|
| 601 |
+
"3": 0.45186641812324524,
|
| 602 |
+
"5": 0.8251473307609558
|
| 603 |
+
}
|
| 604 |
+
},
|
| 605 |
+
"speaker_independent": {
|
| 606 |
+
"query_count": 1721,
|
| 607 |
+
"recall_at_k": {
|
| 608 |
+
"1": 0.6691070795059204,
|
| 609 |
+
"3": 0.9307428002357483,
|
| 610 |
+
"5": 0.9516802430152893
|
| 611 |
+
},
|
| 612 |
+
"all_support_em_at_k": {
|
| 613 |
+
"3": 0.9087739586830139,
|
| 614 |
+
"5": 0.9291110038757324
|
| 615 |
+
}
|
| 616 |
+
}
|
| 617 |
+
},
|
| 618 |
+
"by_task_and_speaker_query_type": {
|
| 619 |
+
"change_comparison": {
|
| 620 |
+
"fact_to_person": {
|
| 621 |
+
"query_count": 74,
|
| 622 |
+
"recall_at_k": {
|
| 623 |
+
"1": 0.5,
|
| 624 |
+
"3": 1.0,
|
| 625 |
+
"5": 1.0
|
| 626 |
+
},
|
| 627 |
+
"all_support_em_at_k": {
|
| 628 |
+
"3": 1.0,
|
| 629 |
+
"5": 1.0
|
| 630 |
+
}
|
| 631 |
+
},
|
| 632 |
+
"person_to_fact": {
|
| 633 |
+
"query_count": 88,
|
| 634 |
+
"recall_at_k": {
|
| 635 |
+
"1": 0.5,
|
| 636 |
+
"3": 0.9545454382896423,
|
| 637 |
+
"5": 1.0
|
| 638 |
+
},
|
| 639 |
+
"all_support_em_at_k": {
|
| 640 |
+
"3": 0.9090908765792847,
|
| 641 |
+
"5": 1.0
|
| 642 |
+
}
|
| 643 |
+
},
|
| 644 |
+
"self_to_fact": {
|
| 645 |
+
"query_count": 99,
|
| 646 |
+
"recall_at_k": {
|
| 647 |
+
"1": 0.1111111119389534,
|
| 648 |
+
"3": 0.47979798913002014,
|
| 649 |
+
"5": 0.8383838534355164
|
| 650 |
+
},
|
| 651 |
+
"all_support_em_at_k": {
|
| 652 |
+
"3": 0.10101009905338287,
|
| 653 |
+
"5": 0.6767676472663879
|
| 654 |
+
}
|
| 655 |
+
},
|
| 656 |
+
"speaker_independent": {
|
| 657 |
+
"query_count": 209,
|
| 658 |
+
"recall_at_k": {
|
| 659 |
+
"1": 0.48963314294815063,
|
| 660 |
+
"3": 0.9908294081687927,
|
| 661 |
+
"5": 0.9932217597961426
|
| 662 |
+
},
|
| 663 |
+
"all_support_em_at_k": {
|
| 664 |
+
"3": 0.9856459498405457,
|
| 665 |
+
"5": 0.9904305934906006
|
| 666 |
+
}
|
| 667 |
+
}
|
| 668 |
+
},
|
| 669 |
+
"direct_recall": {
|
| 670 |
+
"fact_to_person": {
|
| 671 |
+
"query_count": 524,
|
| 672 |
+
"recall_at_k": {
|
| 673 |
+
"1": 0.9285942316055298,
|
| 674 |
+
"3": 0.9726463556289673,
|
| 675 |
+
"5": 0.9820291996002197
|
| 676 |
+
},
|
| 677 |
+
"all_support_em_at_k": {
|
| 678 |
+
"3": 0.9599236249923706,
|
| 679 |
+
"5": 0.9694656133651733
|
| 680 |
+
}
|
| 681 |
+
},
|
| 682 |
+
"person_to_fact": {
|
| 683 |
+
"query_count": 306,
|
| 684 |
+
"recall_at_k": {
|
| 685 |
+
"1": 0.7990195751190186,
|
| 686 |
+
"3": 0.9327342510223389,
|
| 687 |
+
"5": 0.9507080912590027
|
| 688 |
+
},
|
| 689 |
+
"all_support_em_at_k": {
|
| 690 |
+
"3": 0.9215686321258545,
|
| 691 |
+
"5": 0.9346405267715454
|
| 692 |
+
}
|
| 693 |
+
},
|
| 694 |
+
"self_to_fact": {
|
| 695 |
+
"query_count": 57,
|
| 696 |
+
"recall_at_k": {
|
| 697 |
+
"1": 0.4312865138053894,
|
| 698 |
+
"3": 0.6067252159118652,
|
| 699 |
+
"5": 0.694444477558136
|
| 700 |
+
},
|
| 701 |
+
"all_support_em_at_k": {
|
| 702 |
+
"3": 0.4385964870452881,
|
| 703 |
+
"5": 0.5614035129547119
|
| 704 |
+
}
|
| 705 |
+
},
|
| 706 |
+
"speaker_independent": {
|
| 707 |
+
"query_count": 604,
|
| 708 |
+
"recall_at_k": {
|
| 709 |
+
"1": 0.8083609342575073,
|
| 710 |
+
"3": 0.9050771594047546,
|
| 711 |
+
"5": 0.9199779629707336
|
| 712 |
+
},
|
| 713 |
+
"all_support_em_at_k": {
|
| 714 |
+
"3": 0.8807947039604187,
|
| 715 |
+
"5": 0.8923841118812561
|
| 716 |
+
}
|
| 717 |
+
}
|
| 718 |
+
},
|
| 719 |
+
"historical_state": {
|
| 720 |
+
"fact_to_person": {
|
| 721 |
+
"query_count": 91,
|
| 722 |
+
"recall_at_k": {
|
| 723 |
+
"1": 0.3956044018268585,
|
| 724 |
+
"3": 0.9890109896659851,
|
| 725 |
+
"5": 1.0
|
| 726 |
+
},
|
| 727 |
+
"all_support_em_at_k": {
|
| 728 |
+
"3": 0.9890109896659851,
|
| 729 |
+
"5": 1.0
|
| 730 |
+
}
|
| 731 |
+
},
|
| 732 |
+
"person_to_fact": {
|
| 733 |
+
"query_count": 125,
|
| 734 |
+
"recall_at_k": {
|
| 735 |
+
"1": 0.47200000286102295,
|
| 736 |
+
"3": 0.9919999837875366,
|
| 737 |
+
"5": 1.0
|
| 738 |
+
},
|
| 739 |
+
"all_support_em_at_k": {
|
| 740 |
+
"3": 0.9919999837875366,
|
| 741 |
+
"5": 1.0
|
| 742 |
+
}
|
| 743 |
+
},
|
| 744 |
+
"self_to_fact": {
|
| 745 |
+
"query_count": 82,
|
| 746 |
+
"recall_at_k": {
|
| 747 |
+
"1": 0.2195121943950653,
|
| 748 |
+
"3": 0.7804877758026123,
|
| 749 |
+
"5": 1.0
|
| 750 |
+
},
|
| 751 |
+
"all_support_em_at_k": {
|
| 752 |
+
"3": 0.7804877758026123,
|
| 753 |
+
"5": 1.0
|
| 754 |
+
}
|
| 755 |
+
},
|
| 756 |
+
"speaker_independent": {
|
| 757 |
+
"query_count": 202,
|
| 758 |
+
"recall_at_k": {
|
| 759 |
+
"1": 0.5990098714828491,
|
| 760 |
+
"3": 0.9876237511634827,
|
| 761 |
+
"5": 0.9975247383117676
|
| 762 |
+
},
|
| 763 |
+
"all_support_em_at_k": {
|
| 764 |
+
"3": 0.9851484894752502,
|
| 765 |
+
"5": 0.9950494766235352
|
| 766 |
+
}
|
| 767 |
+
}
|
| 768 |
+
},
|
| 769 |
+
"latest_state": {
|
| 770 |
+
"fact_to_person": {
|
| 771 |
+
"query_count": 31,
|
| 772 |
+
"recall_at_k": {
|
| 773 |
+
"1": 0.3870967626571655,
|
| 774 |
+
"3": 1.0,
|
| 775 |
+
"5": 1.0
|
| 776 |
+
},
|
| 777 |
+
"all_support_em_at_k": {
|
| 778 |
+
"3": 1.0,
|
| 779 |
+
"5": 1.0
|
| 780 |
+
}
|
| 781 |
+
},
|
| 782 |
+
"person_to_fact": {
|
| 783 |
+
"query_count": 92,
|
| 784 |
+
"recall_at_k": {
|
| 785 |
+
"1": 0.34239131212234497,
|
| 786 |
+
"3": 0.97826087474823,
|
| 787 |
+
"5": 1.0
|
| 788 |
+
},
|
| 789 |
+
"all_support_em_at_k": {
|
| 790 |
+
"3": 0.97826087474823,
|
| 791 |
+
"5": 1.0
|
| 792 |
+
}
|
| 793 |
+
},
|
| 794 |
+
"self_to_fact": {
|
| 795 |
+
"query_count": 82,
|
| 796 |
+
"recall_at_k": {
|
| 797 |
+
"1": 0.13414634764194489,
|
| 798 |
+
"3": 0.6951219439506531,
|
| 799 |
+
"5": 0.9634146094322205
|
| 800 |
+
},
|
| 801 |
+
"all_support_em_at_k": {
|
| 802 |
+
"3": 0.6951219439506531,
|
| 803 |
+
"5": 0.9634146094322205
|
| 804 |
+
}
|
| 805 |
+
},
|
| 806 |
+
"speaker_independent": {
|
| 807 |
+
"query_count": 252,
|
| 808 |
+
"recall_at_k": {
|
| 809 |
+
"1": 0.2698412835597992,
|
| 810 |
+
"3": 0.9384920597076416,
|
| 811 |
+
"5": 0.9980158805847168
|
| 812 |
+
},
|
| 813 |
+
"all_support_em_at_k": {
|
| 814 |
+
"3": 0.9365079402923584,
|
| 815 |
+
"5": 0.9960317611694336
|
| 816 |
+
}
|
| 817 |
+
}
|
| 818 |
+
},
|
| 819 |
+
"multi_hop_composition": {
|
| 820 |
+
"fact_to_person": {
|
| 821 |
+
"query_count": 66,
|
| 822 |
+
"recall_at_k": {
|
| 823 |
+
"1": 0.46037158370018005,
|
| 824 |
+
"3": 0.9197511076927185,
|
| 825 |
+
"5": 0.9299963712692261
|
| 826 |
+
},
|
| 827 |
+
"all_support_em_at_k": {
|
| 828 |
+
"3": 0.8787878751754761,
|
| 829 |
+
"5": 0.8787878751754761
|
| 830 |
+
}
|
| 831 |
+
},
|
| 832 |
+
"person_to_fact": {
|
| 833 |
+
"query_count": 84,
|
| 834 |
+
"recall_at_k": {
|
| 835 |
+
"1": 0.25447848439216614,
|
| 836 |
+
"3": 0.6393990516662598,
|
| 837 |
+
"5": 0.9189909100532532
|
| 838 |
+
},
|
| 839 |
+
"all_support_em_at_k": {
|
| 840 |
+
"3": 0.3333333432674408,
|
| 841 |
+
"5": 0.8809523582458496
|
| 842 |
+
}
|
| 843 |
+
},
|
| 844 |
+
"self_to_fact": {
|
| 845 |
+
"query_count": 168,
|
| 846 |
+
"recall_at_k": {
|
| 847 |
+
"1": 0.2946428656578064,
|
| 848 |
+
"3": 0.6696428656578064,
|
| 849 |
+
"5": 0.9375
|
| 850 |
+
},
|
| 851 |
+
"all_support_em_at_k": {
|
| 852 |
+
"3": 0.369047611951828,
|
| 853 |
+
"5": 0.8809523582458496
|
| 854 |
+
}
|
| 855 |
+
},
|
| 856 |
+
"speaker_independent": {
|
| 857 |
+
"query_count": 30,
|
| 858 |
+
"recall_at_k": {
|
| 859 |
+
"1": 0.2761111259460449,
|
| 860 |
+
"3": 0.5019444227218628,
|
| 861 |
+
"5": 0.5586110949516296
|
| 862 |
+
},
|
| 863 |
+
"all_support_em_at_k": {
|
| 864 |
+
"3": 0.1666666716337204,
|
| 865 |
+
"5": 0.23333333432674408
|
| 866 |
+
}
|
| 867 |
+
}
|
| 868 |
+
},
|
| 869 |
+
"temporal_localization": {
|
| 870 |
+
"person_to_fact": {
|
| 871 |
+
"query_count": 274,
|
| 872 |
+
"recall_at_k": {
|
| 873 |
+
"1": 0.9187955856323242,
|
| 874 |
+
"3": 0.9826642274856567,
|
| 875 |
+
"5": 0.9881386756896973
|
| 876 |
+
},
|
| 877 |
+
"all_support_em_at_k": {
|
| 878 |
+
"3": 0.9781022071838379,
|
| 879 |
+
"5": 0.985401451587677
|
| 880 |
+
}
|
| 881 |
+
},
|
| 882 |
+
"self_to_fact": {
|
| 883 |
+
"query_count": 21,
|
| 884 |
+
"recall_at_k": {
|
| 885 |
+
"1": 0.5,
|
| 886 |
+
"3": 0.7301587462425232,
|
| 887 |
+
"5": 0.7301587462425232
|
| 888 |
+
},
|
| 889 |
+
"all_support_em_at_k": {
|
| 890 |
+
"3": 0.5714285969734192,
|
| 891 |
+
"5": 0.5714285969734192
|
| 892 |
+
}
|
| 893 |
+
},
|
| 894 |
+
"speaker_independent": {
|
| 895 |
+
"query_count": 424,
|
| 896 |
+
"recall_at_k": {
|
| 897 |
+
"1": 0.8577044010162354,
|
| 898 |
+
"3": 0.9363208413124084,
|
| 899 |
+
"5": 0.9547955989837646
|
| 900 |
+
},
|
| 901 |
+
"all_support_em_at_k": {
|
| 902 |
+
"3": 0.9103773832321167,
|
| 903 |
+
"5": 0.9292452931404114
|
| 904 |
+
}
|
| 905 |
+
}
|
| 906 |
+
}
|
| 907 |
+
},
|
| 908 |
+
"by_task": {
|
| 909 |
+
"change_comparison": {
|
| 910 |
+
"query_count": 470,
|
| 911 |
+
"recall_at_k": {
|
| 912 |
+
"1": 0.4134751856327057,
|
| 913 |
+
"3": 0.8778368234634399,
|
| 914 |
+
"5": 0.9629431962966919
|
| 915 |
+
},
|
| 916 |
+
"all_support_em_at_k": {
|
| 917 |
+
"3": 0.7872340679168701,
|
| 918 |
+
"5": 0.9276595711708069
|
| 919 |
+
}
|
| 920 |
+
},
|
| 921 |
+
"direct_recall": {
|
| 922 |
+
"query_count": 1491,
|
| 923 |
+
"recall_at_k": {
|
| 924 |
+
"1": 0.8342834711074829,
|
| 925 |
+
"3": 0.9230940937995911,
|
| 926 |
+
"5": 0.9394700527191162
|
| 927 |
+
},
|
| 928 |
+
"all_support_em_at_k": {
|
| 929 |
+
"3": 0.9000670909881592,
|
| 930 |
+
"5": 0.9154929518699646
|
| 931 |
+
}
|
| 932 |
+
},
|
| 933 |
+
"historical_state": {
|
| 934 |
+
"query_count": 500,
|
| 935 |
+
"recall_at_k": {
|
| 936 |
+
"1": 0.46799999475479126,
|
| 937 |
+
"3": 0.9549999833106995,
|
| 938 |
+
"5": 0.9990000128746033
|
| 939 |
+
},
|
| 940 |
+
"all_support_em_at_k": {
|
| 941 |
+
"3": 0.9539999961853027,
|
| 942 |
+
"5": 0.9980000257492065
|
| 943 |
+
}
|
| 944 |
+
},
|
| 945 |
+
"latest_state": {
|
| 946 |
+
"query_count": 457,
|
| 947 |
+
"recall_at_k": {
|
| 948 |
+
"1": 0.26805251836776733,
|
| 949 |
+
"3": 0.9070022106170654,
|
| 950 |
+
"5": 0.9923413395881653
|
| 951 |
+
},
|
| 952 |
+
"all_support_em_at_k": {
|
| 953 |
+
"3": 0.9059081077575684,
|
| 954 |
+
"5": 0.9912472367286682
|
| 955 |
+
}
|
| 956 |
+
},
|
| 957 |
+
"multi_hop_composition": {
|
| 958 |
+
"query_count": 348,
|
| 959 |
+
"recall_at_k": {
|
| 960 |
+
"1": 0.31478172540664673,
|
| 961 |
+
"3": 0.6953202486038208,
|
| 962 |
+
"5": 0.8989464044570923
|
| 963 |
+
},
|
| 964 |
+
"all_support_em_at_k": {
|
| 965 |
+
"3": 0.4396551847457886,
|
| 966 |
+
"5": 0.8247126340866089
|
| 967 |
+
}
|
| 968 |
+
},
|
| 969 |
+
"temporal_localization": {
|
| 970 |
+
"query_count": 719,
|
| 971 |
+
"recall_at_k": {
|
| 972 |
+
"1": 0.8705376982688904,
|
| 973 |
+
"3": 0.9479600787162781,
|
| 974 |
+
"5": 0.9609411358833313
|
| 975 |
+
},
|
| 976 |
+
"all_support_em_at_k": {
|
| 977 |
+
"3": 0.926286518573761,
|
| 978 |
+
"5": 0.9401947259902954
|
| 979 |
+
}
|
| 980 |
+
}
|
| 981 |
+
}
|
| 982 |
+
},
|
| 983 |
+
"skipped_control_query_count": 0,
|
| 984 |
+
"score_analysis": {
|
| 985 |
+
"overall": {
|
| 986 |
+
"rag_query_count": 3985,
|
| 987 |
+
"control_query_count": 111,
|
| 988 |
+
"gold_score": {
|
| 989 |
+
"count": 5141,
|
| 990 |
+
"mean": 0.7154593990645001,
|
| 991 |
+
"std": 0.17573212749321732,
|
| 992 |
+
"min": -0.12303857505321503,
|
| 993 |
+
"p05": 0.3636300265789032,
|
| 994 |
+
"p25": 0.6405549645423889,
|
| 995 |
+
"median": 0.7480038404464722,
|
| 996 |
+
"p75": 0.8282420039176941,
|
| 997 |
+
"p95": 0.9467622637748718,
|
| 998 |
+
"max": 1.1032496690750122
|
| 999 |
+
},
|
| 1000 |
+
"best_gold_score": {
|
| 1001 |
+
"count": 3985,
|
| 1002 |
+
"mean": 0.7544670392907549,
|
| 1003 |
+
"std": 0.14403546974973816,
|
| 1004 |
+
"min": 0.02280385047197342,
|
| 1005 |
+
"p05": 0.48611941933631897,
|
| 1006 |
+
"p25": 0.6786033511161804,
|
| 1007 |
+
"median": 0.7758575081825256,
|
| 1008 |
+
"p75": 0.845791757106781,
|
| 1009 |
+
"p95": 0.9638454675674438,
|
| 1010 |
+
"max": 1.1032496690750122
|
| 1011 |
+
},
|
| 1012 |
+
"rag_max_candidate_score": {
|
| 1013 |
+
"count": 3985,
|
| 1014 |
+
"mean": 0.7627401347104997,
|
| 1015 |
+
"std": 0.13235941487299727,
|
| 1016 |
+
"min": 0.21979452669620514,
|
| 1017 |
+
"p05": 0.5201244235038758,
|
| 1018 |
+
"p25": 0.6830075979232788,
|
| 1019 |
+
"median": 0.7791073322296143,
|
| 1020 |
+
"p75": 0.8487366437911987,
|
| 1021 |
+
"p95": 0.9649398803710937,
|
| 1022 |
+
"max": 1.1042900085449219
|
| 1023 |
+
},
|
| 1024 |
+
"control_max_candidate_score": {
|
| 1025 |
+
"count": 111,
|
| 1026 |
+
"mean": 0.3775643181928375,
|
| 1027 |
+
"std": 0.14569058322524672,
|
| 1028 |
+
"min": 0.018502261489629745,
|
| 1029 |
+
"p05": 0.14916608482599258,
|
| 1030 |
+
"p25": 0.2863771915435791,
|
| 1031 |
+
"median": 0.3824880123138428,
|
| 1032 |
+
"p75": 0.4608069360256195,
|
| 1033 |
+
"p95": 0.6159006059169769,
|
| 1034 |
+
"max": 0.8022838234901428
|
| 1035 |
+
},
|
| 1036 |
+
"max_non_gold_score": {
|
| 1037 |
+
"count": 3985,
|
| 1038 |
+
"mean": 0.6269493476958616,
|
| 1039 |
+
"std": 0.179593426300524,
|
| 1040 |
+
"min": 0.08614442497491837,
|
| 1041 |
+
"p05": 0.34568926095962527,
|
| 1042 |
+
"p25": 0.49576282501220703,
|
| 1043 |
+
"median": 0.61491858959198,
|
| 1044 |
+
"p75": 0.7543556690216064,
|
| 1045 |
+
"p95": 0.9488252282142638,
|
| 1046 |
+
"max": 1.1042900085449219
|
| 1047 |
+
},
|
| 1048 |
+
"query_temporal_norm": {
|
| 1049 |
+
"count": 4096,
|
| 1050 |
+
"mean": 0.3116771188815619,
|
| 1051 |
+
"std": 0.12893400789015785,
|
| 1052 |
+
"min": 0.12013464421033859,
|
| 1053 |
+
"p05": 0.1599961407482624,
|
| 1054 |
+
"p25": 0.203378327190876,
|
| 1055 |
+
"median": 0.2639659196138382,
|
| 1056 |
+
"p75": 0.4172542244195938,
|
| 1057 |
+
"p95": 0.5408022552728653,
|
| 1058 |
+
"max": 0.5694292783737183
|
| 1059 |
+
},
|
| 1060 |
+
"best_gold_margin": {
|
| 1061 |
+
"count": 3985,
|
| 1062 |
+
"mean": 0.12751769159489323,
|
| 1063 |
+
"std": 0.14761390159917398,
|
| 1064 |
+
"min": -0.41839342564344406,
|
| 1065 |
+
"p05": -0.050421607494354245,
|
| 1066 |
+
"p25": 0.0031561851501464844,
|
| 1067 |
+
"median": 0.0983622670173645,
|
| 1068 |
+
"p75": 0.2348206639289856,
|
| 1069 |
+
"p95": 0.3919700920581816,
|
| 1070 |
+
"max": 0.7321364879608154
|
| 1071 |
+
},
|
| 1072 |
+
"weakest_gold_margin": {
|
| 1073 |
+
"count": 3985,
|
| 1074 |
+
"mean": 0.10261004417278738,
|
| 1075 |
+
"std": 0.16404433255357592,
|
| 1076 |
+
"min": -0.6536026895046234,
|
| 1077 |
+
"p05": -0.13799275159835814,
|
| 1078 |
+
"p25": -0.0018881559371948242,
|
| 1079 |
+
"median": 0.08711892366409302,
|
| 1080 |
+
"p75": 0.2224733829498291,
|
| 1081 |
+
"p95": 0.3672234594821928,
|
| 1082 |
+
"max": 0.6410713195800781
|
| 1083 |
+
},
|
| 1084 |
+
"top_score_best_balanced_threshold": {
|
| 1085 |
+
"threshold": 0.5664574205875397,
|
| 1086 |
+
"balanced_accuracy": 0.911291215933625,
|
| 1087 |
+
"true_positive_rate": 0.91267252195734,
|
| 1088 |
+
"false_positive_rate": 0.09009009009009009
|
| 1089 |
+
},
|
| 1090 |
+
"gold_score_best_balanced_threshold": {
|
| 1091 |
+
"threshold": 0.5665663480758667,
|
| 1092 |
+
"balanced_accuracy": 0.9048922196977405,
|
| 1093 |
+
"true_positive_rate": 0.8998745294855709,
|
| 1094 |
+
"false_positive_rate": 0.09009009009009009
|
| 1095 |
+
}
|
| 1096 |
+
},
|
| 1097 |
+
"by_task": {
|
| 1098 |
+
"change_comparison": {
|
| 1099 |
+
"rag_query_count": 470,
|
| 1100 |
+
"control_query_count": 0,
|
| 1101 |
+
"gold_score": {
|
| 1102 |
+
"count": 942,
|
| 1103 |
+
"mean": 0.7326939189905447,
|
| 1104 |
+
"std": 0.10824093478227866,
|
| 1105 |
+
"min": 0.07003629952669144,
|
| 1106 |
+
"p05": 0.5355867475271225,
|
| 1107 |
+
"p25": 0.6708965450525284,
|
| 1108 |
+
"median": 0.7509642839431763,
|
| 1109 |
+
"p75": 0.8066658228635788,
|
| 1110 |
+
"p95": 0.8816887825727461,
|
| 1111 |
+
"max": 0.9440944790840149
|
| 1112 |
+
},
|
| 1113 |
+
"best_gold_score": {
|
| 1114 |
+
"count": 470,
|
| 1115 |
+
"mean": 0.7679149062075513,
|
| 1116 |
+
"std": 0.09213641523962647,
|
| 1117 |
+
"min": 0.3496818542480469,
|
| 1118 |
+
"p05": 0.6097596526145935,
|
| 1119 |
+
"p25": 0.7119392454624176,
|
| 1120 |
+
"median": 0.7841155230998993,
|
| 1121 |
+
"p75": 0.8302914351224899,
|
| 1122 |
+
"p95": 0.8930411905050277,
|
| 1123 |
+
"max": 0.9440944790840149
|
| 1124 |
+
},
|
| 1125 |
+
"rag_max_candidate_score": {
|
| 1126 |
+
"count": 470,
|
| 1127 |
+
"mean": 0.7722497434058088,
|
| 1128 |
+
"std": 0.09157903790860208,
|
| 1129 |
+
"min": 0.3496818542480469,
|
| 1130 |
+
"p05": 0.6142909288406372,
|
| 1131 |
+
"p25": 0.7141461968421936,
|
| 1132 |
+
"median": 0.7864619791507721,
|
| 1133 |
+
"p75": 0.8346060365438461,
|
| 1134 |
+
"p95": 0.8946467816829681,
|
| 1135 |
+
"max": 0.9440944790840149
|
| 1136 |
+
},
|
| 1137 |
+
"control_max_candidate_score": null,
|
| 1138 |
+
"max_non_gold_score": {
|
| 1139 |
+
"count": 470,
|
| 1140 |
+
"mean": 0.547240946980867,
|
| 1141 |
+
"std": 0.19383881040767714,
|
| 1142 |
+
"min": 0.08614442497491837,
|
| 1143 |
+
"p05": 0.2577131509780884,
|
| 1144 |
+
"p25": 0.3841584548354149,
|
| 1145 |
+
"median": 0.5354843437671661,
|
| 1146 |
+
"p75": 0.7122959047555923,
|
| 1147 |
+
"p95": 0.843116596341133,
|
| 1148 |
+
"max": 0.9219087958335876
|
| 1149 |
+
},
|
| 1150 |
+
"query_temporal_norm": {
|
| 1151 |
+
"count": 470,
|
| 1152 |
+
"mean": 0.40276982140667894,
|
| 1153 |
+
"std": 0.03980443605509354,
|
| 1154 |
+
"min": 0.17388875782489777,
|
| 1155 |
+
"p05": 0.328983274102211,
|
| 1156 |
+
"p25": 0.38821743428707123,
|
| 1157 |
+
"median": 0.40812453627586365,
|
| 1158 |
+
"p75": 0.424331434071064,
|
| 1159 |
+
"p95": 0.4521392062306403,
|
| 1160 |
+
"max": 0.5628159642219543
|
| 1161 |
+
},
|
| 1162 |
+
"best_gold_margin": {
|
| 1163 |
+
"count": 470,
|
| 1164 |
+
"mean": 0.22067395922668437,
|
| 1165 |
+
"std": 0.1824797004933215,
|
| 1166 |
+
"min": -0.09542953968048096,
|
| 1167 |
+
"p05": -0.03293478488922119,
|
| 1168 |
+
"p25": 0.06616732478141785,
|
| 1169 |
+
"median": 0.2181701958179474,
|
| 1170 |
+
"p75": 0.3659444600343704,
|
| 1171 |
+
"p95": 0.51416195705533,
|
| 1172 |
+
"max": 0.7321364879608154
|
| 1173 |
+
},
|
| 1174 |
+
"weakest_gold_margin": {
|
| 1175 |
+
"count": 470,
|
| 1176 |
+
"mean": 0.15360000450560388,
|
| 1177 |
+
"std": 0.1851890519021113,
|
| 1178 |
+
"min": -0.4024420902132988,
|
| 1179 |
+
"p05": -0.10997549891471863,
|
| 1180 |
+
"p25": 0.003862246870994568,
|
| 1181 |
+
"median": 0.14909625053405762,
|
| 1182 |
+
"p75": 0.3048042953014374,
|
| 1183 |
+
"p95": 0.45087446719408025,
|
| 1184 |
+
"max": 0.6410713195800781
|
| 1185 |
+
},
|
| 1186 |
+
"top_score_best_balanced_threshold": null,
|
| 1187 |
+
"gold_score_best_balanced_threshold": null
|
| 1188 |
+
},
|
| 1189 |
+
"current_only_control": {
|
| 1190 |
+
"rag_query_count": 0,
|
| 1191 |
+
"control_query_count": 110,
|
| 1192 |
+
"gold_score": null,
|
| 1193 |
+
"best_gold_score": null,
|
| 1194 |
+
"rag_max_candidate_score": null,
|
| 1195 |
+
"control_max_candidate_score": {
|
| 1196 |
+
"count": 110,
|
| 1197 |
+
"mean": 0.3769120380790396,
|
| 1198 |
+
"std": 0.14618987745617867,
|
| 1199 |
+
"min": 0.018502261489629745,
|
| 1200 |
+
"p05": 0.14905614629387856,
|
| 1201 |
+
"p25": 0.2858238220214844,
|
| 1202 |
+
"median": 0.3782581090927124,
|
| 1203 |
+
"p75": 0.46130822598934174,
|
| 1204 |
+
"p95": 0.6162560909986495,
|
| 1205 |
+
"max": 0.8022838234901428
|
| 1206 |
+
},
|
| 1207 |
+
"max_non_gold_score": null,
|
| 1208 |
+
"query_temporal_norm": {
|
| 1209 |
+
"count": 110,
|
| 1210 |
+
"mean": 0.26989374445243314,
|
| 1211 |
+
"std": 0.0766767531184094,
|
| 1212 |
+
"min": 0.13687971234321594,
|
| 1213 |
+
"p05": 0.16108160167932511,
|
| 1214 |
+
"p25": 0.215445127338171,
|
| 1215 |
+
"median": 0.2581220120191574,
|
| 1216 |
+
"p75": 0.3229278400540352,
|
| 1217 |
+
"p95": 0.4131780833005905,
|
| 1218 |
+
"max": 0.4925289750099182
|
| 1219 |
+
},
|
| 1220 |
+
"best_gold_margin": null,
|
| 1221 |
+
"weakest_gold_margin": null,
|
| 1222 |
+
"top_score_best_balanced_threshold": null,
|
| 1223 |
+
"gold_score_best_balanced_threshold": null
|
| 1224 |
+
},
|
| 1225 |
+
"direct_recall": {
|
| 1226 |
+
"rag_query_count": 1491,
|
| 1227 |
+
"control_query_count": 0,
|
| 1228 |
+
"gold_score": {
|
| 1229 |
+
"count": 1669,
|
| 1230 |
+
"mean": 0.6795029017735003,
|
| 1231 |
+
"std": 0.1983251415999637,
|
| 1232 |
+
"min": -0.12303857505321503,
|
| 1233 |
+
"p05": 0.2784222841262817,
|
| 1234 |
+
"p25": 0.5722606182098389,
|
| 1235 |
+
"median": 0.7289072275161743,
|
| 1236 |
+
"p75": 0.8250808119773865,
|
| 1237 |
+
"p95": 0.9214394807815551,
|
| 1238 |
+
"max": 1.063254952430725
|
| 1239 |
+
},
|
| 1240 |
+
"best_gold_score": {
|
| 1241 |
+
"count": 1491,
|
| 1242 |
+
"mean": 0.7199413462833699,
|
| 1243 |
+
"std": 0.15911103886386538,
|
| 1244 |
+
"min": 0.02280385047197342,
|
| 1245 |
+
"p05": 0.4366766959428787,
|
| 1246 |
+
"p25": 0.6310526430606842,
|
| 1247 |
+
"median": 0.7523093819618225,
|
| 1248 |
+
"p75": 0.8343758881092072,
|
| 1249 |
+
"p95": 0.9265364408493042,
|
| 1250 |
+
"max": 1.063254952430725
|
| 1251 |
+
},
|
| 1252 |
+
"rag_max_candidate_score": {
|
| 1253 |
+
"count": 1491,
|
| 1254 |
+
"mean": 0.7315587912786734,
|
| 1255 |
+
"std": 0.1390575200032724,
|
| 1256 |
+
"min": 0.21979452669620514,
|
| 1257 |
+
"p05": 0.4833293706178665,
|
| 1258 |
+
"p25": 0.6411759853363037,
|
| 1259 |
+
"median": 0.7542001605033875,
|
| 1260 |
+
"p75": 0.8348446488380432,
|
| 1261 |
+
"p95": 0.9265364408493042,
|
| 1262 |
+
"max": 1.063254952430725
|
| 1263 |
+
},
|
| 1264 |
+
"control_max_candidate_score": null,
|
| 1265 |
+
"max_non_gold_score": {
|
| 1266 |
+
"count": 1491,
|
| 1267 |
+
"mean": 0.5671377542393068,
|
| 1268 |
+
"std": 0.13058292145303427,
|
| 1269 |
+
"min": 0.08767721056938171,
|
| 1270 |
+
"p05": 0.35685819387435913,
|
| 1271 |
+
"p25": 0.48237597942352295,
|
| 1272 |
+
"median": 0.5671817064285278,
|
| 1273 |
+
"p75": 0.6538146734237671,
|
| 1274 |
+
"p95": 0.7913401126861572,
|
| 1275 |
+
"max": 0.9612478017807007
|
| 1276 |
+
},
|
| 1277 |
+
"query_temporal_norm": {
|
| 1278 |
+
"count": 1491,
|
| 1279 |
+
"mean": 0.2383564575847006,
|
| 1280 |
+
"std": 0.08033840921935426,
|
| 1281 |
+
"min": 0.12013464421033859,
|
| 1282 |
+
"p05": 0.1468081772327423,
|
| 1283 |
+
"p25": 0.18328498303890228,
|
| 1284 |
+
"median": 0.21576981246471405,
|
| 1285 |
+
"p75": 0.2750905752182007,
|
| 1286 |
+
"p95": 0.39991748332977295,
|
| 1287 |
+
"max": 0.5644786357879639
|
| 1288 |
+
},
|
| 1289 |
+
"best_gold_margin": {
|
| 1290 |
+
"count": 1491,
|
| 1291 |
+
"mean": 0.1528035920440631,
|
| 1292 |
+
"std": 0.14736356526555025,
|
| 1293 |
+
"min": -0.41839342564344406,
|
| 1294 |
+
"p05": -0.08735679090023041,
|
| 1295 |
+
"p25": 0.058132946491241455,
|
| 1296 |
+
"median": 0.15042370557785034,
|
| 1297 |
+
"p75": 0.2618226259946823,
|
| 1298 |
+
"p95": 0.3783687353134155,
|
| 1299 |
+
"max": 0.6177643090486526
|
| 1300 |
+
},
|
| 1301 |
+
"weakest_gold_margin": {
|
| 1302 |
+
"count": 1491,
|
| 1303 |
+
"mean": 0.13596027125220303,
|
| 1304 |
+
"std": 0.17475061101661918,
|
| 1305 |
+
"min": -0.6536026895046234,
|
| 1306 |
+
"p05": -0.1832170933485031,
|
| 1307 |
+
"p25": 0.04592122137546539,
|
| 1308 |
+
"median": 0.14661788940429688,
|
| 1309 |
+
"p75": 0.26139336824417114,
|
| 1310 |
+
"p95": 0.3783687353134155,
|
| 1311 |
+
"max": 0.6177643090486526
|
| 1312 |
+
},
|
| 1313 |
+
"top_score_best_balanced_threshold": null,
|
| 1314 |
+
"gold_score_best_balanced_threshold": null
|
| 1315 |
+
},
|
| 1316 |
+
"historical_state": {
|
| 1317 |
+
"rag_query_count": 500,
|
| 1318 |
+
"control_query_count": 0,
|
| 1319 |
+
"gold_score": {
|
| 1320 |
+
"count": 502,
|
| 1321 |
+
"mean": 0.7761994309396858,
|
| 1322 |
+
"std": 0.10471581264550778,
|
| 1323 |
+
"min": 0.16526609659194946,
|
| 1324 |
+
"p05": 0.5885683983564377,
|
| 1325 |
+
"p25": 0.7164510041475296,
|
| 1326 |
+
"median": 0.7957707047462463,
|
| 1327 |
+
"p75": 0.8472662419080734,
|
| 1328 |
+
"p95": 0.9122402310371399,
|
| 1329 |
+
"max": 0.9831515550613403
|
| 1330 |
+
},
|
| 1331 |
+
"best_gold_score": {
|
| 1332 |
+
"count": 500,
|
| 1333 |
+
"mean": 0.777970435500145,
|
| 1334 |
+
"std": 0.10054288277351174,
|
| 1335 |
+
"min": 0.40203285217285156,
|
| 1336 |
+
"p05": 0.5916313827037811,
|
| 1337 |
+
"p25": 0.7174811512231827,
|
| 1338 |
+
"median": 0.7958914339542389,
|
| 1339 |
+
"p75": 0.8473147451877594,
|
| 1340 |
+
"p95": 0.9122692972421645,
|
| 1341 |
+
"max": 0.9831515550613403
|
| 1342 |
+
},
|
| 1343 |
+
"rag_max_candidate_score": {
|
| 1344 |
+
"count": 500,
|
| 1345 |
+
"mean": 0.7819046204090119,
|
| 1346 |
+
"std": 0.09902156513217696,
|
| 1347 |
+
"min": 0.40203285217285156,
|
| 1348 |
+
"p05": 0.6030461072921753,
|
| 1349 |
+
"p25": 0.7233852297067642,
|
| 1350 |
+
"median": 0.7978901863098145,
|
| 1351 |
+
"p75": 0.8500061184167862,
|
| 1352 |
+
"p95": 0.912781223654747,
|
| 1353 |
+
"max": 0.9831515550613403
|
| 1354 |
+
},
|
| 1355 |
+
"control_max_candidate_score": null,
|
| 1356 |
+
"max_non_gold_score": {
|
| 1357 |
+
"count": 500,
|
| 1358 |
+
"mean": 0.6704996504485607,
|
| 1359 |
+
"std": 0.14438779622177209,
|
| 1360 |
+
"min": 0.17858107388019562,
|
| 1361 |
+
"p05": 0.4236251160502434,
|
| 1362 |
+
"p25": 0.5728582739830017,
|
| 1363 |
+
"median": 0.6769407391548157,
|
| 1364 |
+
"p75": 0.7875670939683914,
|
| 1365 |
+
"p95": 0.8805044949054718,
|
| 1366 |
+
"max": 0.9633103013038635
|
| 1367 |
+
},
|
| 1368 |
+
"query_temporal_norm": {
|
| 1369 |
+
"count": 500,
|
| 1370 |
+
"mean": 0.4810723942518234,
|
| 1371 |
+
"std": 0.0908062463914881,
|
| 1372 |
+
"min": 0.16505520045757294,
|
| 1373 |
+
"p05": 0.2751061350107193,
|
| 1374 |
+
"p25": 0.44165537506341934,
|
| 1375 |
+
"median": 0.5179827213287354,
|
| 1376 |
+
"p75": 0.54570671916008,
|
| 1377 |
+
"p95": 0.5624057739973068,
|
| 1378 |
+
"max": 0.5694292783737183
|
| 1379 |
+
},
|
| 1380 |
+
"best_gold_margin": {
|
| 1381 |
+
"count": 500,
|
| 1382 |
+
"mean": 0.10747078505158425,
|
| 1383 |
+
"std": 0.11929718685672921,
|
| 1384 |
+
"min": -0.17465877532958984,
|
| 1385 |
+
"p05": -0.029424968361854553,
|
| 1386 |
+
"p25": 0.001565694808959961,
|
| 1387 |
+
"median": 0.08554309606552124,
|
| 1388 |
+
"p75": 0.17575012892484665,
|
| 1389 |
+
"p95": 0.3152986243367195,
|
| 1390 |
+
"max": 0.5076251327991486
|
| 1391 |
+
},
|
| 1392 |
+
"weakest_gold_margin": {
|
| 1393 |
+
"count": 500,
|
| 1394 |
+
"mean": 0.1064475021660328,
|
| 1395 |
+
"std": 0.12140862200311647,
|
| 1396 |
+
"min": -0.3940350413322449,
|
| 1397 |
+
"p05": -0.03014567494392395,
|
| 1398 |
+
"p25": 0.0015095025300979614,
|
| 1399 |
+
"median": 0.08444157242774963,
|
| 1400 |
+
"p75": 0.17575012892484665,
|
| 1401 |
+
"p95": 0.3152986243367195,
|
| 1402 |
+
"max": 0.5076251327991486
|
| 1403 |
+
},
|
| 1404 |
+
"top_score_best_balanced_threshold": null,
|
| 1405 |
+
"gold_score_best_balanced_threshold": null
|
| 1406 |
+
},
|
| 1407 |
+
"latest_state": {
|
| 1408 |
+
"rag_query_count": 457,
|
| 1409 |
+
"control_query_count": 0,
|
| 1410 |
+
"gold_score": {
|
| 1411 |
+
"count": 460,
|
| 1412 |
+
"mean": 0.9076748492925063,
|
| 1413 |
+
"std": 0.11461868176356446,
|
| 1414 |
+
"min": 0.24560272693634033,
|
| 1415 |
+
"p05": 0.6936595916748047,
|
| 1416 |
+
"p25": 0.8535026013851166,
|
| 1417 |
+
"median": 0.9299749135971069,
|
| 1418 |
+
"p75": 0.9843438863754272,
|
| 1419 |
+
"p95": 1.0409013211727143,
|
| 1420 |
+
"max": 1.1032496690750122
|
| 1421 |
+
},
|
| 1422 |
+
"best_gold_score": {
|
| 1423 |
+
"count": 457,
|
| 1424 |
+
"mean": 0.9106951447884416,
|
| 1425 |
+
"std": 0.1083083226667221,
|
| 1426 |
+
"min": 0.24560272693634033,
|
| 1427 |
+
"p05": 0.7078387379646301,
|
| 1428 |
+
"p25": 0.8549481630325317,
|
| 1429 |
+
"median": 0.9306370615959167,
|
| 1430 |
+
"p75": 0.9854380488395691,
|
| 1431 |
+
"p95": 1.0409518003463745,
|
| 1432 |
+
"max": 1.1032496690750122
|
| 1433 |
+
},
|
| 1434 |
+
"rag_max_candidate_score": {
|
| 1435 |
+
"count": 457,
|
| 1436 |
+
"mean": 0.9170270060684279,
|
| 1437 |
+
"std": 0.10489952671179081,
|
| 1438 |
+
"min": 0.34878870844841003,
|
| 1439 |
+
"p05": 0.718699598312378,
|
| 1440 |
+
"p25": 0.8615692853927612,
|
| 1441 |
+
"median": 0.9357645511627197,
|
| 1442 |
+
"p75": 0.9880915880203247,
|
| 1443 |
+
"p95": 1.0481631994247436,
|
| 1444 |
+
"max": 1.1042900085449219
|
| 1445 |
+
},
|
| 1446 |
+
"control_max_candidate_score": null,
|
| 1447 |
+
"max_non_gold_score": {
|
| 1448 |
+
"count": 457,
|
| 1449 |
+
"mean": 0.9147816273002708,
|
| 1450 |
+
"std": 0.10795329594168684,
|
| 1451 |
+
"min": 0.3380759358406067,
|
| 1452 |
+
"p05": 0.718699598312378,
|
| 1453 |
+
"p25": 0.8614855408668518,
|
| 1454 |
+
"median": 0.935660183429718,
|
| 1455 |
+
"p75": 0.9872651696205139,
|
| 1456 |
+
"p95": 1.0466254949569702,
|
| 1457 |
+
"max": 1.1042900085449219
|
| 1458 |
+
},
|
| 1459 |
+
"query_temporal_norm": {
|
| 1460 |
+
"count": 457,
|
| 1461 |
+
"mean": 0.48360304671382487,
|
| 1462 |
+
"std": 0.0791067935911107,
|
| 1463 |
+
"min": 0.1427229642868042,
|
| 1464 |
+
"p05": 0.30160648822784425,
|
| 1465 |
+
"p25": 0.46912088990211487,
|
| 1466 |
+
"median": 0.513687789440155,
|
| 1467 |
+
"p75": 0.5321373343467712,
|
| 1468 |
+
"p95": 0.545603621006012,
|
| 1469 |
+
"max": 0.5621570348739624
|
| 1470 |
+
},
|
| 1471 |
+
"best_gold_margin": {
|
| 1472 |
+
"count": 457,
|
| 1473 |
+
"mean": -0.004086482511829234,
|
| 1474 |
+
"std": 0.01985870933325241,
|
| 1475 |
+
"min": -0.14556145668029785,
|
| 1476 |
+
"p05": -0.04004968404769897,
|
| 1477 |
+
"p25": -0.00482553243637085,
|
| 1478 |
+
"median": -0.0011156201362609863,
|
| 1479 |
+
"p75": 0.001955687999725342,
|
| 1480 |
+
"p95": 0.008001494407653806,
|
| 1481 |
+
"max": 0.18877702951431274
|
| 1482 |
+
},
|
| 1483 |
+
"weakest_gold_margin": {
|
| 1484 |
+
"count": 457,
|
| 1485 |
+
"mean": -0.004729862351386239,
|
| 1486 |
+
"std": 0.016954887432432158,
|
| 1487 |
+
"min": -0.14556145668029785,
|
| 1488 |
+
"p05": -0.04004968404769897,
|
| 1489 |
+
"p25": -0.004851281642913818,
|
| 1490 |
+
"median": -0.0011196136474609375,
|
| 1491 |
+
"p75": 0.0019491314888000488,
|
| 1492 |
+
"p95": 0.007873499393463134,
|
| 1493 |
+
"max": 0.09029287099838257
|
| 1494 |
+
},
|
| 1495 |
+
"top_score_best_balanced_threshold": null,
|
| 1496 |
+
"gold_score_best_balanced_threshold": null
|
| 1497 |
+
},
|
| 1498 |
+
"multi_hop_composition": {
|
| 1499 |
+
"rag_query_count": 348,
|
| 1500 |
+
"control_query_count": 0,
|
| 1501 |
+
"gold_score": {
|
| 1502 |
+
"count": 773,
|
| 1503 |
+
"mean": 0.6477225914014381,
|
| 1504 |
+
"std": 0.1696077516567076,
|
| 1505 |
+
"min": -0.10431600362062454,
|
| 1506 |
+
"p05": 0.28633753657341005,
|
| 1507 |
+
"p25": 0.5937712788581848,
|
| 1508 |
+
"median": 0.6980624198913574,
|
| 1509 |
+
"p75": 0.7609883546829224,
|
| 1510 |
+
"p95": 0.8197827219963074,
|
| 1511 |
+
"max": 0.8692178726196289
|
| 1512 |
+
},
|
| 1513 |
+
"best_gold_score": {
|
| 1514 |
+
"count": 348,
|
| 1515 |
+
"mean": 0.7196337887267957,
|
| 1516 |
+
"std": 0.09670981163335679,
|
| 1517 |
+
"min": 0.35165759921073914,
|
| 1518 |
+
"p05": 0.5244349539279938,
|
| 1519 |
+
"p25": 0.6749561429023743,
|
| 1520 |
+
"median": 0.7393551766872406,
|
| 1521 |
+
"p75": 0.7847351729869843,
|
| 1522 |
+
"p95": 0.8334286898374558,
|
| 1523 |
+
"max": 0.8692178726196289
|
| 1524 |
+
},
|
| 1525 |
+
"rag_max_candidate_score": {
|
| 1526 |
+
"count": 348,
|
| 1527 |
+
"mean": 0.7297802659115572,
|
| 1528 |
+
"std": 0.0901932536288958,
|
| 1529 |
+
"min": 0.3799307644367218,
|
| 1530 |
+
"p05": 0.5428706228733062,
|
| 1531 |
+
"p25": 0.684001088142395,
|
| 1532 |
+
"median": 0.751622200012207,
|
| 1533 |
+
"p75": 0.7945983111858368,
|
| 1534 |
+
"p95": 0.8368684709072113,
|
| 1535 |
+
"max": 0.8703596591949463
|
| 1536 |
+
},
|
| 1537 |
+
"control_max_candidate_score": null,
|
| 1538 |
+
"max_non_gold_score": {
|
| 1539 |
+
"count": 348,
|
| 1540 |
+
"mean": 0.6496828974535068,
|
| 1541 |
+
"std": 0.1525620029439476,
|
| 1542 |
+
"min": 0.11702252179384232,
|
| 1543 |
+
"p05": 0.3462520882487297,
|
| 1544 |
+
"p25": 0.5447135716676712,
|
| 1545 |
+
"median": 0.7023131251335144,
|
| 1546 |
+
"p75": 0.7659444659948349,
|
| 1547 |
+
"p95": 0.8243616819381714,
|
| 1548 |
+
"max": 0.8703596591949463
|
| 1549 |
+
},
|
| 1550 |
+
"query_temporal_norm": {
|
| 1551 |
+
"count": 348,
|
| 1552 |
+
"mean": 0.2268703466859357,
|
| 1553 |
+
"std": 0.031543356431370365,
|
| 1554 |
+
"min": 0.12830781936645508,
|
| 1555 |
+
"p05": 0.18497471064329146,
|
| 1556 |
+
"p25": 0.20330190658569336,
|
| 1557 |
+
"median": 0.22173745930194855,
|
| 1558 |
+
"p75": 0.24691196158528328,
|
| 1559 |
+
"p95": 0.2863227754831314,
|
| 1560 |
+
"max": 0.3312945067882538
|
| 1561 |
+
},
|
| 1562 |
+
"best_gold_margin": {
|
| 1563 |
+
"count": 348,
|
| 1564 |
+
"mean": 0.06995089127328889,
|
| 1565 |
+
"std": 0.13036276721273612,
|
| 1566 |
+
"min": -0.1642531156539917,
|
| 1567 |
+
"p05": -0.05332456827163696,
|
| 1568 |
+
"p25": -0.011286526918411255,
|
| 1569 |
+
"median": 0.0241546630859375,
|
| 1570 |
+
"p75": 0.09257993847131729,
|
| 1571 |
+
"p95": 0.3807756379246711,
|
| 1572 |
+
"max": 0.4885251224040985
|
| 1573 |
+
},
|
| 1574 |
+
"weakest_gold_margin": {
|
| 1575 |
+
"count": 348,
|
| 1576 |
+
"mean": -0.015732982335076934,
|
| 1577 |
+
"std": 0.15913426710387032,
|
| 1578 |
+
"min": -0.5917035602033138,
|
| 1579 |
+
"p05": -0.2659562837332487,
|
| 1580 |
+
"p25": -0.07573521137237549,
|
| 1581 |
+
"median": -0.030487626791000366,
|
| 1582 |
+
"p75": 0.006903454661369324,
|
| 1583 |
+
"p95": 0.3199440449476241,
|
| 1584 |
+
"max": 0.454546719789505
|
| 1585 |
+
},
|
| 1586 |
+
"top_score_best_balanced_threshold": null,
|
| 1587 |
+
"gold_score_best_balanced_threshold": null
|
| 1588 |
+
},
|
| 1589 |
+
"recent_context_control": {
|
| 1590 |
+
"rag_query_count": 0,
|
| 1591 |
+
"control_query_count": 1,
|
| 1592 |
+
"gold_score": null,
|
| 1593 |
+
"best_gold_score": null,
|
| 1594 |
+
"rag_max_candidate_score": null,
|
| 1595 |
+
"control_max_candidate_score": {
|
| 1596 |
+
"count": 1,
|
| 1597 |
+
"mean": 0.4493151307106018,
|
| 1598 |
+
"std": 0.0,
|
| 1599 |
+
"min": 0.4493151307106018,
|
| 1600 |
+
"p05": 0.4493151307106018,
|
| 1601 |
+
"p25": 0.4493151307106018,
|
| 1602 |
+
"median": 0.4493151307106018,
|
| 1603 |
+
"p75": 0.4493151307106018,
|
| 1604 |
+
"p95": 0.4493151307106018,
|
| 1605 |
+
"max": 0.4493151307106018
|
| 1606 |
+
},
|
| 1607 |
+
"max_non_gold_score": null,
|
| 1608 |
+
"query_temporal_norm": {
|
| 1609 |
+
"count": 1,
|
| 1610 |
+
"mean": 0.1407139152288437,
|
| 1611 |
+
"std": 0.0,
|
| 1612 |
+
"min": 0.1407139152288437,
|
| 1613 |
+
"p05": 0.1407139152288437,
|
| 1614 |
+
"p25": 0.1407139152288437,
|
| 1615 |
+
"median": 0.1407139152288437,
|
| 1616 |
+
"p75": 0.1407139152288437,
|
| 1617 |
+
"p95": 0.1407139152288437,
|
| 1618 |
+
"max": 0.1407139152288437
|
| 1619 |
+
},
|
| 1620 |
+
"best_gold_margin": null,
|
| 1621 |
+
"weakest_gold_margin": null,
|
| 1622 |
+
"top_score_best_balanced_threshold": null,
|
| 1623 |
+
"gold_score_best_balanced_threshold": null
|
| 1624 |
+
},
|
| 1625 |
+
"temporal_localization": {
|
| 1626 |
+
"rag_query_count": 719,
|
| 1627 |
+
"control_query_count": 0,
|
| 1628 |
+
"gold_score": {
|
| 1629 |
+
"count": 795,
|
| 1630 |
+
"mean": 0.6868133933106203,
|
| 1631 |
+
"std": 0.16939127613428318,
|
| 1632 |
+
"min": -0.10412678867578506,
|
| 1633 |
+
"p05": 0.3516594350337982,
|
| 1634 |
+
"p25": 0.6090777516365051,
|
| 1635 |
+
"median": 0.7244535684585571,
|
| 1636 |
+
"p75": 0.8079478740692139,
|
| 1637 |
+
"p95": 0.8911272704601287,
|
| 1638 |
+
"max": 1.0223890542984009
|
| 1639 |
+
},
|
| 1640 |
+
"best_gold_score": {
|
| 1641 |
+
"count": 719,
|
| 1642 |
+
"mean": 0.7184883740643798,
|
| 1643 |
+
"std": 0.13249211277583256,
|
| 1644 |
+
"min": 0.12042880803346634,
|
| 1645 |
+
"p05": 0.4689896821975708,
|
| 1646 |
+
"p25": 0.6429046988487244,
|
| 1647 |
+
"median": 0.7374533414840698,
|
| 1648 |
+
"p75": 0.8162335455417633,
|
| 1649 |
+
"p95": 0.8952352583408356,
|
| 1650 |
+
"max": 1.0223890542984009
|
| 1651 |
+
},
|
| 1652 |
+
"rag_max_candidate_score": {
|
| 1653 |
+
"count": 719,
|
| 1654 |
+
"mean": 0.7257450836009873,
|
| 1655 |
+
"std": 0.12004393947778003,
|
| 1656 |
+
"min": 0.3028644323348999,
|
| 1657 |
+
"p05": 0.4953923970460892,
|
| 1658 |
+
"p25": 0.6520695090293884,
|
| 1659 |
+
"median": 0.7405902147293091,
|
| 1660 |
+
"p75": 0.8165587782859802,
|
| 1661 |
+
"p95": 0.8952352583408356,
|
| 1662 |
+
"max": 1.0223890542984009
|
| 1663 |
+
},
|
| 1664 |
+
"control_max_candidate_score": null,
|
| 1665 |
+
"max_non_gold_score": {
|
| 1666 |
+
"count": 719,
|
| 1667 |
+
"mean": 0.5788495642585118,
|
| 1668 |
+
"std": 0.13251074801721197,
|
| 1669 |
+
"min": 0.24814382195472717,
|
| 1670 |
+
"p05": 0.36748895347118377,
|
| 1671 |
+
"p25": 0.4737658351659775,
|
| 1672 |
+
"median": 0.5815503597259521,
|
| 1673 |
+
"p75": 0.6805538833141327,
|
| 1674 |
+
"p95": 0.803080928325653,
|
| 1675 |
+
"max": 0.9469888210296631
|
| 1676 |
+
},
|
| 1677 |
+
"query_temporal_norm": {
|
| 1678 |
+
"count": 719,
|
| 1679 |
+
"mean": 0.22477814839098484,
|
| 1680 |
+
"std": 0.05035853463905679,
|
| 1681 |
+
"min": 0.13936284184455872,
|
| 1682 |
+
"p05": 0.16335002928972245,
|
| 1683 |
+
"p25": 0.18785642832517624,
|
| 1684 |
+
"median": 0.2102562040090561,
|
| 1685 |
+
"p75": 0.2554599493741989,
|
| 1686 |
+
"p95": 0.3239457279443741,
|
| 1687 |
+
"max": 0.49927112460136414
|
| 1688 |
+
},
|
| 1689 |
+
"best_gold_margin": {
|
| 1690 |
+
"count": 719,
|
| 1691 |
+
"mean": 0.13963880980586807,
|
| 1692 |
+
"std": 0.12473303118320828,
|
| 1693 |
+
"min": -0.3510739803314209,
|
| 1694 |
+
"p05": -0.04535098373889923,
|
| 1695 |
+
"p25": 0.06478071212768555,
|
| 1696 |
+
"median": 0.11660575866699219,
|
| 1697 |
+
"p75": 0.23043745756149292,
|
| 1698 |
+
"p95": 0.35062283277511597,
|
| 1699 |
+
"max": 0.5024953782558441
|
| 1700 |
+
},
|
| 1701 |
+
"weakest_gold_margin": {
|
| 1702 |
+
"count": 719,
|
| 1703 |
+
"mean": 0.12295567919063008,
|
| 1704 |
+
"std": 0.14893883801184157,
|
| 1705 |
+
"min": -0.5288597047328949,
|
| 1706 |
+
"p05": -0.1383767902851105,
|
| 1707 |
+
"p25": 0.054179370403289795,
|
| 1708 |
+
"median": 0.11057806015014648,
|
| 1709 |
+
"p75": 0.22584694623947144,
|
| 1710 |
+
"p95": 0.348681515455246,
|
| 1711 |
+
"max": 0.5024953782558441
|
| 1712 |
+
},
|
| 1713 |
+
"top_score_best_balanced_threshold": null,
|
| 1714 |
+
"gold_score_best_balanced_threshold": null
|
| 1715 |
+
}
|
| 1716 |
+
}
|
| 1717 |
+
}
|
| 1718 |
+
}
|
| 1719 |
+
}
|
baseline/temporal_wordings.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
baseline/validation_scores.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
report.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
retriever.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1e92872900d628e3a168a89be4e6e593bece461104637de102cac52f1ef2c4f
|
| 3 |
+
size 48836585
|
retriever_epoch_01.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:457529a8b8087ecbf7839c40d2805033291af6b77d3cd4b71f2273c414cbf945
|
| 3 |
+
size 48836585
|
retriever_epoch_02.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1e92872900d628e3a168a89be4e6e593bece461104637de102cac52f1ef2c4f
|
| 3 |
+
size 48836585
|
temporal_wordings.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
validation_scores_epoch_01.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
validation_scores_epoch_02.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|