exp(action-extraction): record EXP-0129 (rougeL 0.4594)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 9s
maintenance
exp(action-extraction): record EXP-0117 (rougeL 0.4600)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 6s
maintenance
exp(action-extraction): record EXP-0104 (rougeL 0.4588)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 8s
maintenance
exp(grounded-prompting): record EXP-0094 (rougeL 0.4600)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 7s
maintenance
exp(grounded-prompting): promote EXP-0090 (rougeL 0.4600)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 6s
maintenance
exp(grounded-prompting): promote EXP-0086 (rougeL 0.4366)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 9s
maintenance
exp(grounded-prompting): promote EXP-0079 (rougeL 0.4024)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 6s
maintenance
exp(grounded-prompting): promote EXP-0074 (rougeL 0.3638)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 6s
maintenance
exp(structured-output): promote EXP-0070 (rougeL 0.3258)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 6s
maintenance
exp(structured-output): record EXP-0069 (rougeL 0.3132)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 6s
maintenance
exp(structured-output): promote EXP-0068 (rougeL 0.3184)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 6s
maintenance
exp(structured-output): promote EXP-0067 (rougeL 0.3128)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 5s
maintenance
exp(structured-output): promote EXP-0066 (rougeL 0.3069)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 6s
maintenance
exp(structured-output): record EXP-0065 (rougeL 0.2918)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 5s
maintenance
exp(structured-output): promote EXP-0063 (rougeL 0.2782)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 5s
maintenance
exp(structured-output): reject EXP-0061 (rougeL 0.2729)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 7s
maintenance
exp(lora-mt5): record EXP-0048 (rougeL 0.2395)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 7s
maintenance
exp(lora-mt5): record EXP-0044 (rougeL 0.2227)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 8s
maintenance
exp(lora-mt5): promote EXP-0041 (rougeL 0.2192)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 6s
maintenance
exp(meetings-baseline): record EXP-0038 (rougeL 0.2032)
All checks were successful
research / Validate and evaluate experiments (push) Successful in 7s
maintenance