lihaoxin2020/rl_hard_gpt5_sft_gpt54rubric

--- dataset_info: features: - name: conversations list: - name: role dtype: string - name: content dtype: string - name: thinking dtype: string - name: metadata struct: - name: sample_id dtype: string - name: traj_idx dtype: int64 - name: turn_index dtype: int64 - name: tool_name dtype: string - name: tool_query dtype: string - name: refiner_mode dtype: string - name: stop_reason dtype: string - name: accepted dtype: bool - name: pass dtype: int64 - name: format_bonus dtype: float64 - name: citation_format_reward dtype: float64 - name: citation_paper_reward dtype: float64 - name: citation_metrics struct: - name: citation_format_reward dtype: float64 - name: citation_avg_claim_recall dtype: float64 - name: citation_avg_claim_precision dtype: float64 - name: citation_avg_claim_f1 dtype: float64 - name: citation_paper_reward dtype: float64 - name: citation_claim_count dtype: float64 - name: citation_uncited_claim_count dtype: float64 - name: citation_score_applicable dtype: float64 - name: gpt5_generation dtype: string - name: rubrics dtype: string splits: - name: train num_examples: 5195 configs: - config_name: default data_files: - split: train path: data/train-* ---