Evaluation
Evall log
{"files":{"EXIST2025_T1_3_en_es_hard_test_gold.json":{"description":"The file is correctly parser without errors or warnings.\\nFile name: EXIST2025_T1_3_en_es_hard_test_gold.json.","errors":{},"gold":true,"name":"EXIST2025_T1_3_en_es_hard_test_gold.json","status":"OK"},"task1_3_hard_CodeHerGuard_3.json":{"description":"The file is correctly parser without errors or warnings.\\nFile name: task1_3_hard_CodeHerGuard_3.json.","errors":{},"gold":false,"name":"task1_3_hard_CodeHerGuard_3.json","status":"OK"}},"metrics":{"FMeasure":{"acronym":"F1","description":"Coming soon!\\nThe evaluation WARNING.","name":"F-Measure","preconditions":{"METRIC_PRECONDITION_HIERARCHY_NOT_VALID_FOR_METRIC":{"description":"The hierarchy is provided for the evaluation but this metric does not allow to use it. Hierarchy is ignored.\\nThe metric name is: F-Measure.\\nTest case(s) name: EXIST2025.","name":"METRIC_PRECONDITION_HIERARCHY_NOT_VALID_FOR_METRIC","status":"WARNING","test_cases":["EXIST2025"]}},"results":{"average_per_test_case":0.5011435805092809,"test_cases":[{"average":0.5011435805092809,"classes":{"IDEOLOGICAL-INEQUALITY":0.4586466165413534,"MISOGYNY-NON-SEXUAL-VIOLENCE":0.4520795660036166,"NO":0.7816399286987522,"OBJECTIFICATION":0.497545008183306,"SEXUAL-VIOLENCE":0.3239171374764595,"STEREOTYPING-DOMINANCE":0.4930332261521972},"name":"EXIST2025"}]},"status":"WARNING"},"ICM":{"acronym":"ICM","description":"Coming soon!","name":"Information Contrast model","results":{"average_per_test_case":-0.2476004976323983,"test_cases":[{"average":-0.2476004976323983,"name":"EXIST2025"}]},"status":"OK"},"ICMNorm":{"acronym":"ICM-Norm","description":"Coming soon!","name":"Normalized Information Contrast Model","results":{"average_per_test_case":0.44250731039763325,"test_cases":[{"average":0.44250731039763325,"name":"EXIST2025"}]},"status":"OK"},"Precision":{"acronym":"Pr","description":"Coming soon!\\nThe evaluation WARNING.","name":"Precision","preconditions":{"METRIC_PRECONDITION_HIERARCHY_NOT_VALID_FOR_METRIC":{"description":"The hierarchy is provided for the evaluation but this metric does not allow to use it. Hierarchy is ignored.\\nThe metric name is: Precision.\\nTest case(s) name: EXIST2025.","name":"METRIC_PRECONDITION_HIERARCHY_NOT_VALID_FOR_METRIC","status":"WARNING","test_cases":["EXIST2025"]}},"results":{"average_per_test_case":0.4803084738143994,"test_cases":[{"average":0.4803084738143994,"classes":{"IDEOLOGICAL-INEQUALITY":0.4420289855072464,"MISOGYNY-NON-SEXUAL-VIOLENCE":0.44964028776978415,"NO":0.6938291139240507,"OBJECTIFICATION":0.5692883895131086,"SEXUAL-VIOLENCE":0.25671641791044775,"STEREOTYPING-DOMINANCE":0.4703476482617587},"name":"EXIST2025"}]},"status":"WARNING"},"Recall":{"acronym":"Re","description":"Coming soon!\\nThe evaluation WARNING.","name":"Recall","preconditions":{"METRIC_PRECONDITION_HIERARCHY_NOT_VALID_FOR_METRIC":{"description":"The hierarchy is provided for the evaluation but this metric does not allow to use it. Hierarchy is ignored.\\nThe metric name is: Recall.\\nTest case(s) name: EXIST2025.","name":"METRIC_PRECONDITION_HIERARCHY_NOT_VALID_FOR_METRIC","status":"WARNING","test_cases":["EXIST2025"]}},"results":{"average_per_test_case":0.5374433178445844,"test_cases":[{"average":0.5374433178445844,"classes":{"IDEOLOGICAL-INEQUALITY":0.4765625,"MISOGYNY-NON-SEXUAL-VIOLENCE":0.45454545454545453,"NO":0.8948979591836734,"OBJECTIFICATION":0.4418604651162791,"SEXUAL-VIOLENCE":0.4387755102040816,"STEREOTYPING-DOMINANCE":0.5180180180180181},"name":"EXIST2025"}]},"status":"WARNING"}}}
ICM Norm
0.44
metric_params
{"FMeasure":{"alfa_param":0.5,"custom":false},"ICM":{"alpha_1":2,"alpha_2":2,"beta":3,"custom":false}}
Sistema
EXist2025_hybridSexism
Partición resultados
All
Precisión
0.48
Recall
0.54
F1
0.50
ICM
-0.25

