Name: ACSci/evaluation_0408
Creator: ACSci
Published: 2026-04-08 17:31:52
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/ACSci/evaluation_0408

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: Qwen3-4B-Instruct-SFT-v00.01-checkpoint-60 features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 3903110 num_examples: 222 download_size: 723475 dataset_size: 3903110 - config_name: aicsi-rl-v00.00-step-000050 features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 2501547 num_examples: 222 download_size: 1240818 dataset_size: 2501547 - config_name: aicsi-rl-v00.00-step-000100 features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 2685011 num_examples: 222 download_size: 1326934 dataset_size: 2685011 - config_name: aicsi-rl-v00.00-step-000150 features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 2844731 num_examples: 222 download_size: 1407230 dataset_size: 2844731 - config_name: aicsi-rl-v00.00-step-000200 features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 3024841 num_examples: 222 download_size: 1485617 dataset_size: 3024841 - config_name: aicsi-rl-v00.00-step-000300 features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 3362524 num_examples: 222 download_size: 1625392 dataset_size: 3362524 - config_name: aicsi-rl-v00.01-step-000050 features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 2349548 num_examples: 222 download_size: 1166102 dataset_size: 2349548 - config_name: aicsi-rl-v00.01-step-000100 features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 1856014 num_examples: 222 download_size: 946419 dataset_size: 1856014 - config_name: aicsi-rl-v00.01-step-000150 features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 1499143 num_examples: 222 download_size: 742690 dataset_size: 1499143 - config_name: aicsi-rl-v00.01-step-000200 features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 1383780 num_examples: 222 download_size: 673117 dataset_size: 1383780 - config_name: aicsi-rl-v00.01-step-000300 features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 1444773 num_examples: 222 download_size: 704099 dataset_size: 1444773 - config_name: aicsi-rl-v00.01-step-000400 features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 1464890 num_examples: 222 download_size: 701398 dataset_size: 1464890 - config_name: azure-openai-gpt-5.4 features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 4415397 num_examples: 222 download_size: 2251784 dataset_size: 4415397 - config_name: gcp-google-gemini-3-flash-preview features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 1822760 num_examples: 222 download_size: 982708 dataset_size: 1822760 - config_name: nvidia-openai-gpt-oss-120b features: - name: paper_id dtype: string - name: title dtype: string - name: condition dtype: string - name: ground_truth dtype: string - name: generated_output dtype: string - name: equivalence_label dtype: string - name: similarity_score dtype: string - name: novelty_score dtype: string - name: feasibility_score dtype: string - name: specificity_score dtype: string - name: significance_score dtype: string - name: justification dtype: string - name: strengths dtype: string - name: weaknesses dtype: string - name: raw_evaluation dtype: string - name: evaluated dtype: bool splits: - name: ICLR_2026_oral num_bytes: 3235267 num_examples: 222 download_size: 1734022 dataset_size: 3235267 configs: - config_name: Qwen3-4B-Instruct-SFT-v00.01-checkpoint-60 data_files: - split: ICLR_2026_oral path: Qwen3-4B-Instruct-SFT-v00.01-checkpoint-60/ICLR_2026_oral-* - config_name: aicsi-rl-v00.00-step-000050 data_files: - split: ICLR_2026_oral path: aicsi-rl-v00.00-step-000050/ICLR_2026_oral-* - config_name: aicsi-rl-v00.00-step-000100 data_files: - split: ICLR_2026_oral path: aicsi-rl-v00.00-step-000100/ICLR_2026_oral-* - config_name: aicsi-rl-v00.00-step-000150 data_files: - split: ICLR_2026_oral path: aicsi-rl-v00.00-step-000150/ICLR_2026_oral-* - config_name: aicsi-rl-v00.00-step-000200 data_files: - split: ICLR_2026_oral path: aicsi-rl-v00.00-step-000200/ICLR_2026_oral-* - config_name: aicsi-rl-v00.00-step-000300 data_files: - split: ICLR_2026_oral path: aicsi-rl-v00.00-step-000300/ICLR_2026_oral-* - config_name: aicsi-rl-v00.01-step-000050 data_files: - split: ICLR_2026_oral path: aicsi-rl-v00.01-step-000050/ICLR_2026_oral-* - config_name: aicsi-rl-v00.01-step-000100 data_files: - split: ICLR_2026_oral path: aicsi-rl-v00.01-step-000100/ICLR_2026_oral-* - config_name: aicsi-rl-v00.01-step-000150 data_files: - split: ICLR_2026_oral path: aicsi-rl-v00.01-step-000150/ICLR_2026_oral-* - config_name: aicsi-rl-v00.01-step-000200 data_files: - split: ICLR_2026_oral path: aicsi-rl-v00.01-step-000200/ICLR_2026_oral-* - config_name: aicsi-rl-v00.01-step-000300 data_files: - split: ICLR_2026_oral path: aicsi-rl-v00.01-step-000300/ICLR_2026_oral-* - config_name: aicsi-rl-v00.01-step-000400 data_files: - split: ICLR_2026_oral path: aicsi-rl-v00.01-step-000400/ICLR_2026_oral-* - config_name: azure-openai-gpt-5.4 data_files: - split: ICLR_2026_oral path: azure-openai-gpt-5.4/ICLR_2026_oral-* - config_name: gcp-google-gemini-3-flash-preview data_files: - split: ICLR_2026_oral path: gcp-google-gemini-3-flash-preview/ICLR_2026_oral-* - config_name: nvidia-openai-gpt-oss-120b data_files: - split: ICLR_2026_oral path: nvidia-openai-gpt-oss-120b/ICLR_2026_oral-* ---

应用场景：