reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_madversarial_insert_wrong_fact_t90
Viewer • Updated • 600 • 6
Reasoning Project
community
AI & ML interests
None defined yet.
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_mbenign_complete_step_t90
Viewer • Updated • 600 • 5
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_madversarial_cont_wrong_reasoning_t70
Viewer • Updated • 600 • 6
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_madversarial_insert_wrong_fact_t70
Viewer • Updated • 600 • 5
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_mbenign_complete_step_t70
Viewer • Updated • 600 • 6
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_madversarial_cont_wrong_reasoning_t50
Viewer • Updated • 600 • 6
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_madversarial_continue_unrelated_t90
Viewer • Updated • 600 • 5
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_madversarial_insert_wrong_fact_t50
Viewer • Updated • 600 • 6
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_madversarial_continue_unrelated_t70
Viewer • Updated • 600 • 5
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_mbenign_complete_step_t50
Viewer • Updated • 600 • 6
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_madversarial_cont_wrong_reasoning_t30
Viewer • Updated • 600 • 5
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_madversarial_insert_wrong_fact_t30
Viewer • Updated • 600 • 6
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_madversarial_continue_unrelated_t50
Viewer • Updated • 600 • 6
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_mbenign_complete_step_t30
Viewer • Updated • 600 • 6
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_madversarial_continue_unrelated_t30
Viewer • Updated • 600 • 6
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_madversarial_cont_wrong_reasoning_t10
Viewer • Updated • 600 • 6
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_madversarial_insert_wrong_fact_t10
Viewer • Updated • 600 • 6
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_madversarial_continue_unrelated_t10
Viewer • Updated • 600 • 6
reasoning-proj/exp_rob_dfiltered_DeepSeek-R1-Distill-Qwen-32B_2_mbenign_complete_step_t10
Viewer • Updated • 600 • 6
reasoning-proj/filtered_math_traces_original_EXAONE-Deep-32B_2
Viewer • Updated • 600 • 6
reasoning-proj/filtered_math_traces_original_Phi-4-reasoning-plus_2
Viewer • Updated • 600 • 6
reasoning-proj/filtered_math_traces_original_QwQ-32B_2
Viewer • Updated • 600 • 6
reasoning-proj/filtered_math_traces_original_DeepSeek-R1-Distill-Qwen-32B_2
Viewer • Updated • 600 • 5
reasoning-proj/_judged_math_traces_original_QwQ-32B
Viewer • Updated • 2.36k • 5
reasoning-proj/_judged_math_traces_original_EXAONE-Deep-32B
Viewer • Updated • 2.36k • 5
reasoning-proj/_judged_math_traces_original_Phi-4-reasoning-plus
Viewer • Updated • 2.36k • 6
reasoning-proj/_judged_math_traces_original_DeepSeek-R1-Distill-Qwen-32B
Viewer • Updated • 2.36k • 5
reasoning-proj/math_traces_original_EXAONE-Deep-32B
Viewer • Updated • 2.36k • 6
reasoning-proj/math_traces_original_Phi-4-reasoning-plus
Viewer • Updated • 2.36k • 6
reasoning-proj/severity_ablation_logic
Viewer • Updated • 293k • 7