Files
decision-models-benchmark/reports/test/errors-high-impact-semif-cuda.jsonl
2026-10-07 20:53:56 -03:00

29 lines
5.3 KiB
JSON

{"id": "g0108-internet_consumo-regionalismo-03-D1", "gold": "sem_correspondencia", "pred": "recarga_saldo", "confidence": 0.9863, "class": "intencao_fora_das_opcoes", "profile": "regionalismo"}
{"id": "g0123-vas_cancelamento-emocional-00-D1", "gold": "sem_correspondencia", "pred": "conta_contestacao", "confidence": 0.9759, "class": "intencao_fora_das_opcoes", "profile": "emocional"}
{"id": "g0236-roaming_pacote-longo_contexto-01-D1", "gold": "sem_correspondencia", "pred": "roaming_duvida", "confidence": 0.9749, "class": "intencao_fora_das_opcoes", "profile": "longo_contexto"}
{"id": "g0286-reclamacao_atendimento-indireto_multiplo-03-D1", "gold": "reclamacao_atendimento", "pred": "suporte_sem_sinal", "confidence": 0.9658, "class": "ambiguidade", "profile": "indireto_multiplo"}
{"id": "g0108-internet_consumo-regionalismo-10-D1", "gold": "internet_consumo", "pred": "recarga_saldo", "confidence": 0.9649, "class": "taxonomia_par_dificil", "profile": "regionalismo"}
{"id": "g0234-roaming_pacote-regionalismo-05-D1", "gold": "sem_correspondencia", "pred": "roaming_duvida", "confidence": 0.9645, "class": "intencao_fora_das_opcoes", "profile": "regionalismo"}
{"id": "g0259-portabilidade-curto_neutro-00-D1", "gold": "sem_correspondencia", "pred": "troca_numero", "confidence": 0.9606, "class": "intencao_fora_das_opcoes", "profile": "curto_neutro"}
{"id": "g0069-recarga_saldo-indireto_multiplo-07-D1", "gold": "recarga_saldo", "pred": "vas_cancelamento", "confidence": 0.9594, "class": "ambiguidade", "profile": "indireto_multiplo"}
{"id": "g0125-vas_cancelamento-indireto_multiplo-01-D1", "gold": "vas_cancelamento", "pred": "conta_contestacao", "confidence": 0.9579, "class": "taxonomia_par_dificil", "profile": "indireto_multiplo"}
{"id": "g0316-oos_conversa-emocional-4-04-D1", "gold": "reclamacao_atendimento", "pred": "sem_correspondencia", "confidence": 0.9536, "class": "abstencao_indevida", "profile": "emocional"}
{"id": "g0079-plano_consulta-erros_digitacao-09-D1", "gold": "sem_correspondencia", "pred": "beneficios_consulta", "confidence": 0.9528, "class": "intencao_fora_das_opcoes", "profile": "erros_digitacao"}
{"id": "g0245-roaming_cobranca-curto_neutro-06-D1", "gold": "roaming_cobranca", "pred": "conta_contestacao", "confidence": 0.952, "class": "taxonomia_par_dificil", "profile": "curto_neutro"}
{"id": "g0053-negociacao_religacao-emocional-06-D1", "gold": "sem_correspondencia", "pred": "suporte_sem_sinal", "confidence": 0.9504, "class": "intencao_fora_das_opcoes", "profile": "emocional"}
{"id": "g0142-beneficios_consulta-erros_digitacao-11-D1", "gold": "sem_correspondencia", "pred": "plano_consulta", "confidence": 0.9497, "class": "intencao_fora_das_opcoes", "profile": "erros_digitacao"}
{"id": "g0316-oos_conversa-emocional-4-00-D1", "gold": "reclamacao_atendimento", "pred": "sem_correspondencia", "confidence": 0.9433, "class": "abstencao_indevida", "profile": "emocional"}
{"id": "g0081-plano_consulta-emocional-05-D1", "gold": "plano_consulta", "pred": "internet_consumo", "confidence": 0.9433, "class": "taxonomia_par_dificil", "profile": "emocional"}
{"id": "g0190-parceiros_ofertas-informal_abreviado-05-D1", "gold": "parceiros_ofertas", "pred": "vas_contratacao", "confidence": 0.9404, "class": "taxonomia_par_dificil", "profile": "informal_abreviado"}
{"id": "g0186-marketplace_pedido-emocional-07-D1", "gold": "marketplace_pedido", "pred": "sem_correspondencia", "confidence": 0.9349, "class": "abstencao_indevida", "profile": "emocional"}
{"id": "g0249-roaming_cobranca-emocional-08-D1", "gold": "roaming_cobranca", "pred": "conta_contestacao", "confidence": 0.9318, "class": "taxonomia_par_dificil", "profile": "emocional"}
{"id": "g0265-portabilidade-indireto_multiplo-09-D1", "gold": "sem_correspondencia", "pred": "troca_numero", "confidence": 0.9308, "class": "intencao_fora_das_opcoes", "profile": "indireto_multiplo"}
{"id": "g0236-roaming_pacote-longo_contexto-08-D1", "gold": "sem_correspondencia", "pred": "roaming_duvida", "confidence": 0.9305, "class": "intencao_fora_das_opcoes", "profile": "longo_contexto"}
{"id": "g0234-roaming_pacote-regionalismo-11-D1", "gold": "sem_correspondencia", "pred": "roaming_duvida", "confidence": 0.9224, "class": "intencao_fora_das_opcoes", "profile": "regionalismo"}
{"id": "g0250-roaming_cobranca-longo_contexto-07-D1", "gold": "roaming_cobranca", "pred": "conta_contestacao", "confidence": 0.922, "class": "taxonomia_par_dificil", "profile": "longo_contexto"}
{"id": "g0162-fidelidade_resgate-informal_abreviado-11-D1", "gold": "sem_correspondencia", "pred": "fidelidade_pontos", "confidence": 0.918, "class": "intencao_fora_das_opcoes", "profile": "informal_abreviado"}
{"id": "g0123-vas_cancelamento-emocional-02-D1", "gold": "vas_cancelamento", "pred": "conta_contestacao", "confidence": 0.9165, "class": "taxonomia_par_dificil", "profile": "emocional"}
{"id": "g0097-plano_nova_linha-indireto_multiplo-01-D1", "gold": "plano_nova_linha", "pred": "roaming_duvida", "confidence": 0.9165, "class": "ambiguidade", "profile": "indireto_multiplo"}
{"id": "g0308-oos_outra_empresa-longo_contexto-5-11-D1", "gold": "sem_correspondencia", "pred": "reclamacao_atendimento", "confidence": 0.9162, "class": "fora_de_escopo_aceito", "profile": "longo_contexto"}
{"id": "g0210-suporte_chip_esim-curto_neutro-04-D1", "gold": "suporte_chip_esim", "pred": "suporte_sem_sinal", "confidence": 0.9151, "class": "ambiguidade", "profile": "curto_neutro"}