Files
OSGKeyboard/ModelTraining/ClipboardSemantics/baselines/2026-08-27-open-data-v3-license-safe/runtime-golden-report.json
T
2026-08-27 18:01:46 +08:00

4006 lines
104 KiB
JSON

{
"binaryMacro" : {
"accuracy" : 0.9528,
"f1" : 0.7488,
"precision" : 0.9414,
"recall" : 0.6528
},
"binaryMacroByLanguage" : {
"en" : {
"accuracy" : 0.9533,
"f1" : 0.7582,
"precision" : 0.9756,
"recall" : 0.6573
},
"zh-Hans" : {
"accuracy" : 0.9524,
"f1" : 0.7309,
"precision" : 0.9189,
"recall" : 0.6482
}
},
"classifiers" : [
{
"falseNegativeExamples" : [
{
"confidence" : 0.9079,
"family" : "follow_up_reminder_golden",
"id" : "golden-en-0185",
"language" : "en",
"text" : "Do not forget to check whether the refund arrives on Friday."
},
{
"confidence" : 0.8882,
"family" : "task_question",
"id" : "golden-zh-Hans-0007",
"language" : "zh-Hans",
"text" : "这些材料可以在月底前准备好吗?"
},
{
"confidence" : 0.8873,
"family" : "follow_up_reminder_golden",
"id" : "golden-zh-Hans-0181",
"language" : "zh-Hans",
"text" : "这是下一项行动:测试通过后创建发布标签。"
},
{
"confidence" : 0.8627,
"family" : "task_question",
"id" : "golden-en-0053",
"language" : "en",
"text" : "Could these documents be ready by the end of the month?"
},
{
"confidence" : 0.8291,
"family" : "task_statement",
"id" : "golden-en-0048",
"language" : "en",
"text" : "Alex owns the meeting notes and should post them in the project channel today."
}
],
"falsePositiveExamples" : [
{
"confidence" : 0.9909,
"family" : "self_plan",
"id" : "golden-zh-Hans-0021",
"language" : "zh-Hans",
"text" : "明天我要去财务核对发票,不用你帮忙。"
},
{
"confidence" : 0.9212,
"family" : "invitation_question",
"id" : "golden-zh-Hans-0013",
"language" : "zh-Hans",
"text" : "下班后要不要一起喝杯咖啡?"
}
],
"id" : "task",
"metrics" : {
"accuracy" : 0.9325,
"f1" : 0.6383,
"falseNegative" : 15,
"falsePositive" : 2,
"precision" : 0.8824,
"recall" : 0.5,
"total" : 252,
"trueNegative" : 220,
"truePositive" : 15
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9524,
"f1" : 0.75,
"falseNegative" : 6,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6,
"total" : 126,
"trueNegative" : 111,
"truePositive" : 9
},
"zh-Hans" : {
"accuracy" : 0.9127,
"f1" : 0.5217,
"falseNegative" : 9,
"falsePositive" : 2,
"precision" : 0.75,
"recall" : 0.4,
"total" : 126,
"trueNegative" : 109,
"truePositive" : 6
}
},
"metricsBySource" : {
"acknowledgment" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
},
"blessing_boundary" : {
"accuracy" : 0.9,
"f1" : 0,
"falseNegative" : 2,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 18,
"truePositive" : 0
},
"blessing_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"complaint_request" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"complaint_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"confirmation_decision_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"confirmation_decision_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"conversational_message" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"event_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"follow_up_reminder_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"follow_up_reminder_golden" : {
"accuracy" : 0.6,
"f1" : 0.6,
"falseNegative" : 8,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.4286,
"total" : 20,
"trueNegative" : 6,
"truePositive" : 6
},
"information_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"invitation_question" : {
"accuracy" : 0.875,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 1,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 7,
"truePositive" : 0
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"quoted_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"schedule_negotiation_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"schedule_negotiation_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"self_plan" : {
"accuracy" : 0.8333,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 1,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 5,
"truePositive" : 0
},
"task_question" : {
"accuracy" : 0.5,
"f1" : 0.6667,
"falseNegative" : 3,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.5,
"total" : 6,
"trueNegative" : 0,
"truePositive" : 3
},
"task_statement" : {
"accuracy" : 0.75,
"f1" : 0.8571,
"falseNegative" : 2,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.75,
"total" : 8,
"trueNegative" : 0,
"truePositive" : 6
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9365,
"f1" : 0.6522,
"falseNegative" : 15,
"falsePositive" : 1,
"precision" : 0.9375,
"recall" : 0.5,
"total" : 252,
"trueNegative" : 221,
"truePositive" : 15
},
"threshold" : 0.93
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9524,
"f1" : 0.7692,
"falseNegative" : 5,
"falsePositive" : 1,
"precision" : 0.9091,
"recall" : 0.6667,
"total" : 126,
"trueNegative" : 110,
"truePositive" : 10
},
"threshold" : 0.89
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9524,
"f1" : 0.75,
"falseNegative" : 6,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6,
"total" : 126,
"trueNegative" : 111,
"truePositive" : 9
},
"threshold" : 0.91
}
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.9881,
"family" : "information_question",
"id" : "golden-en-0054",
"language" : "en",
"text" : "Which documents are required for this refund?"
},
{
"confidence" : 0.9847,
"family" : "invitation_question",
"id" : "golden-zh-Hans-0013",
"language" : "zh-Hans",
"text" : "下班后要不要一起喝杯咖啡?"
},
{
"confidence" : 0.9827,
"family" : "schedule_negotiation_golden",
"id" : "golden-en-0105",
"language" : "en",
"text" : "Two or three works for me. Which time suits you better?"
},
{
"confidence" : 0.9801,
"family" : "schedule_negotiation_golden",
"id" : "golden-zh-Hans-0097",
"language" : "zh-Hans",
"text" : "这个时段太早了,晚半小时是否方便?"
},
{
"confidence" : 0.9638,
"family" : "schedule_negotiation_golden",
"id" : "golden-en-0106",
"language" : "en",
"text" : "The client is unavailable, so how about next Monday afternoon instead?"
}
],
"falsePositiveExamples" : [
],
"id" : "question",
"metrics" : {
"accuracy" : 0.9365,
"f1" : 0.7895,
"falseNegative" : 16,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6522,
"total" : 252,
"trueNegative" : 206,
"truePositive" : 30
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9048,
"f1" : 0.6471,
"falseNegative" : 12,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.4783,
"total" : 126,
"trueNegative" : 103,
"truePositive" : 11
},
"zh-Hans" : {
"accuracy" : 0.9683,
"f1" : 0.9048,
"falseNegative" : 4,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.8261,
"total" : 126,
"trueNegative" : 103,
"truePositive" : 19
}
},
"metricsBySource" : {
"acknowledgment" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
},
"blessing_boundary" : {
"accuracy" : 0.9,
"f1" : 0,
"falseNegative" : 2,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 18,
"truePositive" : 0
},
"blessing_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"complaint_request" : {
"accuracy" : 0.6667,
"f1" : 0.6667,
"falseNegative" : 2,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.5,
"total" : 6,
"trueNegative" : 2,
"truePositive" : 2
},
"complaint_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"confirmation_decision_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"confirmation_decision_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"conversational_message" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"event_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"follow_up_reminder_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"follow_up_reminder_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"information_question" : {
"accuracy" : 0.5,
"f1" : 0.6667,
"falseNegative" : 2,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.5,
"total" : 4,
"trueNegative" : 0,
"truePositive" : 2
},
"invitation_question" : {
"accuracy" : 0.75,
"f1" : 0.8571,
"falseNegative" : 2,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.75,
"total" : 8,
"trueNegative" : 0,
"truePositive" : 6
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"quoted_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"schedule_negotiation_boundary" : {
"accuracy" : 0.95,
"f1" : 0.8571,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.75,
"total" : 20,
"trueNegative" : 16,
"truePositive" : 3
},
"schedule_negotiation_golden" : {
"accuracy" : 0.65,
"f1" : 0.7586,
"falseNegative" : 7,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6111,
"total" : 20,
"trueNegative" : 2,
"truePositive" : 11
},
"self_plan" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"task_question" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 6,
"trueNegative" : 0,
"truePositive" : 6
},
"task_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9802,
"f1" : 0.9462,
"falseNegative" : 2,
"falsePositive" : 3,
"precision" : 0.9362,
"recall" : 0.9565,
"total" : 252,
"trueNegative" : 203,
"truePositive" : 44
},
"threshold" : 0.76
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.9722,
"f1" : 0.9213,
"falseNegative" : 5,
"falsePositive" : 2,
"precision" : 0.9535,
"recall" : 0.8913,
"total" : 252,
"trueNegative" : 204,
"truePositive" : 41
},
"threshold" : 0.87
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9762,
"f1" : 0.9362,
"falseNegative" : 1,
"falsePositive" : 2,
"precision" : 0.9167,
"recall" : 0.9565,
"total" : 126,
"trueNegative" : 101,
"truePositive" : 22
},
"threshold" : 0.74
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9841,
"f1" : 0.9565,
"falseNegative" : 1,
"falsePositive" : 1,
"precision" : 0.9565,
"recall" : 0.9565,
"total" : 126,
"trueNegative" : 102,
"truePositive" : 22
},
"threshold" : 0.76
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9603,
"f1" : 0.8837,
"falseNegative" : 4,
"falsePositive" : 1,
"precision" : 0.95,
"recall" : 0.8261,
"total" : 126,
"trueNegative" : 102,
"truePositive" : 19
},
"threshold" : 0.87
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9841,
"f1" : 0.9565,
"falseNegative" : 1,
"falsePositive" : 1,
"precision" : 0.9565,
"recall" : 0.9565,
"total" : 126,
"trueNegative" : 102,
"truePositive" : 22
},
"threshold" : 0.76
}
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.7467,
"family" : "invitation_question",
"id" : "golden-en-0059",
"language" : "en",
"text" : "Would you like to get coffee after work?"
},
{
"confidence" : 0.4502,
"family" : "schedule_negotiation_boundary",
"id" : "golden-en-0123",
"language" : "en",
"text" : "The kickoff is fixed for Monday at nine; please attend on time."
},
{
"confidence" : 0.4117,
"family" : "schedule_negotiation_boundary",
"id" : "golden-en-0132",
"language" : "en",
"text" : "Want to see a movie this weekend? The tickets are for Saturday at eight."
},
{
"confidence" : 0.3534,
"family" : "schedule_negotiation_boundary",
"id" : "golden-zh-Hans-0122",
"language" : "zh-Hans",
"text" : "周末一起看电影吗?票是周六晚八点的。"
},
{
"confidence" : 0.3085,
"family" : "invitation_question",
"id" : "golden-en-0058",
"language" : "en",
"text" : "I'd like to invite you to Monday's project kickoff. Are you available?"
}
],
"falsePositiveExamples" : [
{
"confidence" : 0.8146,
"family" : "schedule_negotiation_golden",
"id" : "golden-zh-Hans-0096",
"language" : "zh-Hans",
"text" : "客户临时有事,咱们另约下周一下午怎么样?"
}
],
"id" : "invitation",
"metrics" : {
"accuracy" : 0.9762,
"f1" : 0.7857,
"falseNegative" : 5,
"falsePositive" : 1,
"precision" : 0.9167,
"recall" : 0.6875,
"total" : 252,
"trueNegative" : 235,
"truePositive" : 11
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9683,
"f1" : 0.6667,
"falseNegative" : 4,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.5,
"total" : 126,
"trueNegative" : 118,
"truePositive" : 4
},
"zh-Hans" : {
"accuracy" : 0.9841,
"f1" : 0.875,
"falseNegative" : 1,
"falsePositive" : 1,
"precision" : 0.875,
"recall" : 0.875,
"total" : 126,
"trueNegative" : 117,
"truePositive" : 7
}
},
"metricsBySource" : {
"acknowledgment" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
},
"blessing_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"blessing_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"complaint_request" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"complaint_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"confirmation_decision_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"confirmation_decision_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"conversational_message" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"event_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"follow_up_reminder_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"follow_up_reminder_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"information_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"invitation_question" : {
"accuracy" : 0.75,
"f1" : 0.8571,
"falseNegative" : 2,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.75,
"total" : 8,
"trueNegative" : 0,
"truePositive" : 6
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"quoted_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"schedule_negotiation_boundary" : {
"accuracy" : 0.85,
"f1" : 0.7692,
"falseNegative" : 3,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.625,
"total" : 20,
"trueNegative" : 12,
"truePositive" : 5
},
"schedule_negotiation_golden" : {
"accuracy" : 0.95,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 1,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 19,
"truePositive" : 0
},
"self_plan" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"task_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"task_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9802,
"f1" : 0.8276,
"falseNegative" : 4,
"falsePositive" : 1,
"precision" : 0.9231,
"recall" : 0.75,
"total" : 252,
"trueNegative" : 235,
"truePositive" : 12
},
"threshold" : 0.64
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.9802,
"f1" : 0.8148,
"falseNegative" : 5,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6875,
"total" : 252,
"trueNegative" : 236,
"truePositive" : 11
},
"threshold" : 0.82
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9762,
"f1" : 0.7692,
"falseNegative" : 3,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.625,
"total" : 126,
"trueNegative" : 118,
"truePositive" : 5
},
"threshold" : 0.47
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9921,
"f1" : 0.9333,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.875,
"total" : 126,
"trueNegative" : 118,
"truePositive" : 7
},
"threshold" : 0.82
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9762,
"f1" : 0.7692,
"falseNegative" : 3,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.625,
"total" : 126,
"trueNegative" : 118,
"truePositive" : 5
},
"threshold" : 0.47
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9921,
"f1" : 0.9333,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.875,
"total" : 126,
"trueNegative" : 118,
"truePositive" : 7
},
"threshold" : 0.82
}
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.7094,
"family" : "complaint_request",
"id" : "golden-zh-Hans-0019",
"language" : "zh-Hans",
"text" : "客服已经三天没有回复了,请问什么时候能处理?"
},
{
"confidence" : 0.5898,
"family" : "complaint_request",
"id" : "golden-zh-Hans-0017",
"language" : "zh-Hans",
"text" : "账号无故被锁了,能请你们今天恢复吗?"
},
{
"confidence" : 0.5679,
"family" : "complaint_request",
"id" : "golden-en-0063",
"language" : "en",
"text" : "My account was locked for no reason. Can you restore it today?"
},
{
"confidence" : 0.2716,
"family" : "complaint_request",
"id" : "golden-zh-Hans-0018",
"language" : "zh-Hans",
"text" : "消息一直发送失败,请尽快给我一个解决方案。"
}
],
"falsePositiveExamples" : [
],
"id" : "complaint",
"metrics" : {
"accuracy" : 0.9841,
"f1" : 0.8,
"falseNegative" : 4,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6667,
"total" : 252,
"trueNegative" : 240,
"truePositive" : 8
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9921,
"f1" : 0.9091,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.8333,
"total" : 126,
"trueNegative" : 120,
"truePositive" : 5
},
"zh-Hans" : {
"accuracy" : 0.9762,
"f1" : 0.6667,
"falseNegative" : 3,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.5,
"total" : 126,
"trueNegative" : 120,
"truePositive" : 3
}
},
"metricsBySource" : {
"acknowledgment" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
},
"blessing_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"blessing_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"complaint_request" : {
"accuracy" : 0.3333,
"f1" : 0.5,
"falseNegative" : 4,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.3333,
"total" : 6,
"trueNegative" : 0,
"truePositive" : 2
},
"complaint_statement" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 6,
"trueNegative" : 0,
"truePositive" : 6
},
"confirmation_decision_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"confirmation_decision_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"conversational_message" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"event_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"follow_up_reminder_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"follow_up_reminder_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"information_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"invitation_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"quoted_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"schedule_negotiation_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"schedule_negotiation_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"self_plan" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"task_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"task_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9841,
"f1" : 0.8,
"falseNegative" : 4,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6667,
"total" : 252,
"trueNegative" : 240,
"truePositive" : 8
},
"threshold" : 0.74
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.9841,
"f1" : 0.8,
"falseNegative" : 4,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6667,
"total" : 252,
"trueNegative" : 240,
"truePositive" : 8
},
"threshold" : 0.74
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9921,
"f1" : 0.9091,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.8333,
"total" : 126,
"trueNegative" : 120,
"truePositive" : 5
},
"threshold" : 0.74
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9841,
"f1" : 0.8,
"falseNegative" : 2,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6667,
"total" : 126,
"trueNegative" : 120,
"truePositive" : 4
},
"threshold" : 0.67
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9921,
"f1" : 0.9091,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.8333,
"total" : 126,
"trueNegative" : 120,
"truePositive" : 5
},
"threshold" : 0.74
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9841,
"f1" : 0.8,
"falseNegative" : 2,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6667,
"total" : 126,
"trueNegative" : 120,
"truePositive" : 4
},
"threshold" : 0.67
}
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.4706,
"family" : "schedule_negotiation_golden",
"id" : "golden-en-0112",
"language" : "en",
"text" : "I suggest a one-day delay, with Thursday as the new deadline. Thoughts?"
},
{
"confidence" : 0.4243,
"family" : "schedule_negotiation_golden",
"id" : "golden-zh-Hans-0102",
"language" : "zh-Hans",
"text" : "我提议延期一天,新的截止时间定在周四如何?"
}
],
"falsePositiveExamples" : [
{
"confidence" : 0.7708,
"family" : "task_question",
"id" : "golden-zh-Hans-0006",
"language" : "zh-Hans",
"text" : "方便帮我约一下周三下午的会议室吗?"
},
{
"confidence" : 0.6345,
"family" : "neutral_fact",
"id" : "golden-zh-Hans-0033",
"language" : "zh-Hans",
"text" : "门店营业时间是上午九点到晚上十点。"
},
{
"confidence" : 0.6327,
"family" : "task_question",
"id" : "golden-zh-Hans-0005",
"language" : "zh-Hans",
"text" : "你能明天上午把报价单核对一遍吗?"
},
{
"confidence" : 0.6062,
"family" : "task_statement",
"id" : "golden-zh-Hans-0003",
"language" : "zh-Hans",
"text" : "记得把发票抬头改好以后重新提交。"
}
],
"id" : "scheduleNegotiation",
"metrics" : {
"accuracy" : 0.9762,
"f1" : 0.8571,
"falseNegative" : 2,
"falsePositive" : 4,
"precision" : 0.8182,
"recall" : 0.9,
"total" : 252,
"trueNegative" : 228,
"truePositive" : 18
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9921,
"f1" : 0.9474,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.9,
"total" : 126,
"trueNegative" : 116,
"truePositive" : 9
},
"zh-Hans" : {
"accuracy" : 0.9603,
"f1" : 0.7826,
"falseNegative" : 1,
"falsePositive" : 4,
"precision" : 0.6923,
"recall" : 0.9,
"total" : 126,
"trueNegative" : 112,
"truePositive" : 9
}
},
"metricsBySource" : {
"acknowledgment" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
},
"blessing_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"blessing_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"complaint_request" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"complaint_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"confirmation_decision_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"confirmation_decision_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"conversational_message" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"event_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"follow_up_reminder_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"follow_up_reminder_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"information_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"invitation_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 0.9,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 1,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 9,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"quoted_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"schedule_negotiation_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"schedule_negotiation_golden" : {
"accuracy" : 0.9,
"f1" : 0.9474,
"falseNegative" : 2,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.9,
"total" : 20,
"trueNegative" : 0,
"truePositive" : 18
},
"self_plan" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"task_question" : {
"accuracy" : 0.6667,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 2,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 4,
"truePositive" : 0
},
"task_statement" : {
"accuracy" : 0.875,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 1,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 7,
"truePositive" : 0
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9881,
"f1" : 0.9231,
"falseNegative" : 2,
"falsePositive" : 1,
"precision" : 0.9474,
"recall" : 0.9,
"total" : 252,
"trueNegative" : 231,
"truePositive" : 18
},
"threshold" : 0.64
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.9802,
"f1" : 0.8571,
"falseNegative" : 5,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.75,
"total" : 252,
"trueNegative" : 232,
"truePositive" : 15
},
"threshold" : 0.78
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 126,
"trueNegative" : 116,
"truePositive" : 10
},
"threshold" : 0.47
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9841,
"f1" : 0.9,
"falseNegative" : 1,
"falsePositive" : 1,
"precision" : 0.9,
"recall" : 0.9,
"total" : 126,
"trueNegative" : 115,
"truePositive" : 9
},
"threshold" : 0.64
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 126,
"trueNegative" : 116,
"truePositive" : 10
},
"threshold" : 0.47
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9841,
"f1" : 0.8889,
"falseNegative" : 2,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.8,
"total" : 126,
"trueNegative" : 116,
"truePositive" : 8
},
"threshold" : 0.78
}
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.9868,
"family" : "confirmation_decision_golden",
"id" : "golden-zh-Hans-0140",
"language" : "zh-Hans",
"text" : "不用再讨论了,方案 A 正式通过。"
},
{
"confidence" : 0.986,
"family" : "confirmation_decision_golden",
"id" : "golden-en-0145",
"language" : "en",
"text" : "Final decision: use vendor B and stop comparing bids."
},
{
"confidence" : 0.986,
"family" : "confirmation_decision_golden",
"id" : "golden-en-0146",
"language" : "en",
"text" : "I confirm the monthly plan. Please proceed with the contract."
},
{
"confidence" : 0.9851,
"family" : "confirmation_decision_golden",
"id" : "golden-zh-Hans-0135",
"language" : "zh-Hans",
"text" : "最终拍板用供应商乙,不再比价。"
},
{
"confidence" : 0.9838,
"family" : "confirmation_decision_golden",
"id" : "golden-en-0147",
"language" : "en",
"text" : "I approve this release scope; execute it as written."
}
],
"falsePositiveExamples" : [
],
"id" : "confirmationDecision",
"metrics" : {
"accuracy" : 0.9444,
"f1" : 0.4615,
"falseNegative" : 14,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.3,
"total" : 252,
"trueNegative" : 232,
"truePositive" : 6
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9444,
"f1" : 0.4615,
"falseNegative" : 7,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.3,
"total" : 126,
"trueNegative" : 116,
"truePositive" : 3
},
"zh-Hans" : {
"accuracy" : 0.9444,
"f1" : 0.4615,
"falseNegative" : 7,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.3,
"total" : 126,
"trueNegative" : 116,
"truePositive" : 3
}
},
"metricsBySource" : {
"acknowledgment" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
},
"blessing_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"blessing_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"complaint_request" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"complaint_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"confirmation_decision_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"confirmation_decision_golden" : {
"accuracy" : 0.3,
"f1" : 0.4615,
"falseNegative" : 14,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.3,
"total" : 20,
"trueNegative" : 0,
"truePositive" : 6
},
"conversational_message" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"event_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"follow_up_reminder_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"follow_up_reminder_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"information_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"invitation_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"quoted_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"schedule_negotiation_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"schedule_negotiation_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"self_plan" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"task_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"task_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9683,
"f1" : 0.7647,
"falseNegative" : 7,
"falsePositive" : 1,
"precision" : 0.9286,
"recall" : 0.65,
"total" : 252,
"trueNegative" : 231,
"truePositive" : 13
},
"threshold" : 0.96
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.9643,
"f1" : 0.7097,
"falseNegative" : 9,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.55,
"total" : 252,
"trueNegative" : 232,
"truePositive" : 11
},
"threshold" : 0.98
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9683,
"f1" : 0.75,
"falseNegative" : 4,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6,
"total" : 126,
"trueNegative" : 116,
"truePositive" : 6
},
"threshold" : 0.98
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9762,
"f1" : 0.8235,
"falseNegative" : 3,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.7,
"total" : 126,
"trueNegative" : 116,
"truePositive" : 7
},
"threshold" : 0.72
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9683,
"f1" : 0.75,
"falseNegative" : 4,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6,
"total" : 126,
"trueNegative" : 116,
"truePositive" : 6
},
"threshold" : 0.98
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9762,
"f1" : 0.8235,
"falseNegative" : 3,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.7,
"total" : 126,
"trueNegative" : 116,
"truePositive" : 7
},
"threshold" : 0.72
}
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.9131,
"family" : "self_plan",
"id" : "golden-zh-Hans-0022",
"language" : "zh-Hans",
"text" : "先记一下:月底前我自己联系客户。"
},
{
"confidence" : 0.8917,
"family" : "follow_up_reminder_golden",
"id" : "golden-en-0184",
"language" : "en",
"text" : "Once the client replies, send the final quote to Finance."
},
{
"confidence" : 0.8891,
"family" : "follow_up_reminder_golden",
"id" : "golden-en-0189",
"language" : "en",
"text" : "Follow up with the vendor about the delivery date next Monday."
},
{
"confidence" : 0.8677,
"family" : "follow_up_reminder_golden",
"id" : "golden-zh-Hans-0173",
"language" : "zh-Hans",
"text" : "明早九点提醒我给牙医打电话确认复诊。"
},
{
"confidence" : 0.8568,
"family" : "follow_up_reminder_golden",
"id" : "golden-en-0186",
"language" : "en",
"text" : "After the meeting, summarize the three decisions in the project channel."
}
],
"falsePositiveExamples" : [
],
"id" : "followUpReminder",
"metrics" : {
"accuracy" : 0.9444,
"f1" : 0.6316,
"falseNegative" : 14,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.4615,
"total" : 252,
"trueNegative" : 226,
"truePositive" : 12
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9444,
"f1" : 0.6316,
"falseNegative" : 7,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.4615,
"total" : 126,
"trueNegative" : 113,
"truePositive" : 6
},
"zh-Hans" : {
"accuracy" : 0.9444,
"f1" : 0.6316,
"falseNegative" : 7,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.4615,
"total" : 126,
"trueNegative" : 113,
"truePositive" : 6
}
},
"metricsBySource" : {
"acknowledgment" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
},
"blessing_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"blessing_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"complaint_request" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"complaint_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"confirmation_decision_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"confirmation_decision_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"conversational_message" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"event_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"follow_up_reminder_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"follow_up_reminder_golden" : {
"accuracy" : 0.5,
"f1" : 0.6667,
"falseNegative" : 10,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.5,
"total" : 20,
"trueNegative" : 0,
"truePositive" : 10
},
"information_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"invitation_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"quoted_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"schedule_negotiation_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"schedule_negotiation_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"self_plan" : {
"accuracy" : 0.8333,
"f1" : 0.6667,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.5,
"total" : 6,
"trueNegative" : 4,
"truePositive" : 1
},
"task_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"task_statement" : {
"accuracy" : 0.625,
"f1" : 0.4,
"falseNegative" : 3,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.25,
"total" : 8,
"trueNegative" : 4,
"truePositive" : 1
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9762,
"f1" : 0.875,
"falseNegative" : 5,
"falsePositive" : 1,
"precision" : 0.9545,
"recall" : 0.8077,
"total" : 252,
"trueNegative" : 225,
"truePositive" : 21
},
"threshold" : 0.76
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.9762,
"f1" : 0.875,
"falseNegative" : 5,
"falsePositive" : 1,
"precision" : 0.9545,
"recall" : 0.8077,
"total" : 252,
"trueNegative" : 225,
"truePositive" : 21
},
"threshold" : 0.76
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9921,
"f1" : 0.96,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.9231,
"total" : 126,
"trueNegative" : 113,
"truePositive" : 12
},
"threshold" : 0.58
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9683,
"f1" : 0.8333,
"falseNegative" : 3,
"falsePositive" : 1,
"precision" : 0.9091,
"recall" : 0.7692,
"total" : 126,
"trueNegative" : 112,
"truePositive" : 10
},
"threshold" : 0.76
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9921,
"f1" : 0.96,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.9231,
"total" : 126,
"trueNegative" : 113,
"truePositive" : 12
},
"threshold" : 0.58
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9444,
"f1" : 0.6316,
"falseNegative" : 7,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.4615,
"total" : 126,
"trueNegative" : 113,
"truePositive" : 6
},
"threshold" : 0.93
}
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.9652,
"family" : "blessing_golden",
"id" : "golden-en-0226",
"language" : "en",
"text" : "Wishing the newlyweds a lifetime of love, laughter, and wonderful memories."
},
{
"confidence" : 0.9337,
"family" : "blessing_golden",
"id" : "golden-zh-Hans-0217",
"language" : "zh-Hans",
"text" : "祝两位新婚快乐,往后的日子相互陪伴,长长久久。"
},
{
"confidence" : 0.7616,
"family" : "blessing_golden",
"id" : "golden-zh-Hans-0220",
"language" : "zh-Hans",
"text" : "祝宝宝健康成长,也祝新手爸妈每天都有好睡眠。"
},
{
"confidence" : 0.7188,
"family" : "blessing_golden",
"id" : "golden-zh-Hans-0215",
"language" : "zh-Hans",
"text" : "中秋团圆,愿大家所念皆如愿,所行皆坦途。"
}
],
"falsePositiveExamples" : [
{
"confidence" : 1,
"family" : "blessing_boundary",
"id" : "golden-en-0246",
"language" : "en",
"text" : "This article explains the history of the phrase “best wishes.”"
}
],
"id" : "blessing",
"metrics" : {
"accuracy" : 0.9802,
"f1" : 0.8649,
"falseNegative" : 4,
"falsePositive" : 1,
"precision" : 0.9412,
"recall" : 0.8,
"total" : 252,
"trueNegative" : 231,
"truePositive" : 16
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9841,
"f1" : 0.9,
"falseNegative" : 1,
"falsePositive" : 1,
"precision" : 0.9,
"recall" : 0.9,
"total" : 126,
"trueNegative" : 115,
"truePositive" : 9
},
"zh-Hans" : {
"accuracy" : 0.9762,
"f1" : 0.8235,
"falseNegative" : 3,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.7,
"total" : 126,
"trueNegative" : 116,
"truePositive" : 7
}
},
"metricsBySource" : {
"acknowledgment" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
},
"blessing_boundary" : {
"accuracy" : 0.95,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 1,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 19,
"truePositive" : 0
},
"blessing_golden" : {
"accuracy" : 0.8,
"f1" : 0.8889,
"falseNegative" : 4,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.8,
"total" : 20,
"trueNegative" : 0,
"truePositive" : 16
},
"complaint_request" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"complaint_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"confirmation_decision_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"confirmation_decision_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"conversational_message" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"event_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"follow_up_reminder_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"follow_up_reminder_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"information_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"invitation_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 10,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"quoted_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"schedule_negotiation_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"schedule_negotiation_golden" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 20,
"truePositive" : 0
},
"self_plan" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"task_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"task_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9802,
"f1" : 0.8649,
"falseNegative" : 4,
"falsePositive" : 1,
"precision" : 0.9412,
"recall" : 0.8,
"total" : 252,
"trueNegative" : 231,
"truePositive" : 16
},
"threshold" : 0.05
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9841,
"f1" : 0.9,
"falseNegative" : 1,
"falsePositive" : 1,
"precision" : 0.9,
"recall" : 0.9,
"total" : 126,
"trueNegative" : 115,
"truePositive" : 9
},
"threshold" : 0.05
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9762,
"f1" : 0.8235,
"falseNegative" : 3,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.7,
"total" : 126,
"trueNegative" : 116,
"truePositive" : 7
},
"threshold" : 0.05
}
},
"thresholdsAt95PrecisionByLanguage" : {
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9762,
"f1" : 0.8235,
"falseNegative" : 3,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.7,
"total" : 126,
"trueNegative" : 116,
"truePositive" : 7
},
"threshold" : 0.05
}
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.6485,
"family" : "task_question",
"id" : "golden-zh-Hans-0007",
"language" : "zh-Hans",
"text" : "这些材料可以在月底前准备好吗?"
},
{
"confidence" : 0.639,
"family" : "follow_up_reminder_golden",
"id" : "golden-en-0186",
"language" : "en",
"text" : "After the meeting, summarize the three decisions in the project channel."
},
{
"confidence" : 0.5827,
"family" : "complaint_request",
"id" : "golden-zh-Hans-0019",
"language" : "zh-Hans",
"text" : "客服已经三天没有回复了,请问什么时候能处理?"
},
{
"confidence" : 0.5425,
"family" : "confirmation_decision_golden",
"id" : "golden-en-0143",
"language" : "en",
"text" : "Between the two versions, I choose the second. Ship that one."
},
{
"confidence" : 0.5211,
"family" : "follow_up_reminder_golden",
"id" : "golden-zh-Hans-0178",
"language" : "zh-Hans",
"text" : "等审批结果出来,请联系申请人说明原因。"
}
],
"falsePositiveExamples" : [
{
"confidence" : 0.9928,
"family" : "follow_up_reminder_boundary",
"id" : "golden-en-0210",
"language" : "en",
"text" : "There is no owner and no next step."
},
{
"confidence" : 0.9847,
"family" : "blessing_boundary",
"id" : "golden-en-0244",
"language" : "en",
"text" : "It is Maya's birthday today, and the cake is already in the meeting room."
},
{
"confidence" : 0.9846,
"family" : "neutral_fact",
"id" : "golden-en-0079",
"language" : "en",
"text" : "The store is open from nine in the morning until ten at night."
},
{
"confidence" : 0.9473,
"family" : "self_plan",
"id" : "golden-zh-Hans-0021",
"language" : "zh-Hans",
"text" : "明天我要去财务核对发票,不用你帮忙。"
},
{
"confidence" : 0.8938,
"family" : "confirmation_decision_boundary",
"id" : "golden-en-0165",
"language" : "en",
"text" : "Sure, let us wait until everyone has discussed it."
}
],
"id" : "replyableMessage",
"metrics" : {
"accuracy" : 0.9008,
"f1" : 0.9104,
"falseNegative" : 13,
"falsePositive" : 12,
"precision" : 0.9137,
"recall" : 0.9071,
"total" : 252,
"trueNegative" : 100,
"truePositive" : 127
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.8968,
"f1" : 0.9103,
"falseNegative" : 4,
"falsePositive" : 9,
"precision" : 0.88,
"recall" : 0.9429,
"total" : 126,
"trueNegative" : 47,
"truePositive" : 66
},
"zh-Hans" : {
"accuracy" : 0.9048,
"f1" : 0.9104,
"falseNegative" : 9,
"falsePositive" : 3,
"precision" : 0.9531,
"recall" : 0.8714,
"total" : 126,
"trueNegative" : 53,
"truePositive" : 61
}
},
"metricsBySource" : {
"acknowledgment" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 8,
"trueNegative" : 8,
"truePositive" : 0
},
"blessing_boundary" : {
"accuracy" : 0.95,
"f1" : 0.8889,
"falseNegative" : 0,
"falsePositive" : 1,
"precision" : 0.8,
"recall" : 1,
"total" : 20,
"trueNegative" : 15,
"truePositive" : 4
},
"blessing_golden" : {
"accuracy" : 0.95,
"f1" : 0.9744,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.95,
"total" : 20,
"trueNegative" : 0,
"truePositive" : 19
},
"complaint_request" : {
"accuracy" : 0.8333,
"f1" : 0.9091,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.8333,
"total" : 6,
"trueNegative" : 0,
"truePositive" : 5
},
"complaint_statement" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 6,
"trueNegative" : 0,
"truePositive" : 6
},
"confirmation_decision_boundary" : {
"accuracy" : 0.9,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 2,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 18,
"truePositive" : 0
},
"confirmation_decision_golden" : {
"accuracy" : 0.85,
"f1" : 0.9189,
"falseNegative" : 3,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.85,
"total" : 20,
"trueNegative" : 0,
"truePositive" : 17
},
"conversational_message" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 10,
"trueNegative" : 0,
"truePositive" : 10
},
"event_statement" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"follow_up_reminder_boundary" : {
"accuracy" : 0.8,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 4,
"precision" : 0,
"recall" : 0,
"total" : 20,
"trueNegative" : 16,
"truePositive" : 0
},
"follow_up_reminder_golden" : {
"accuracy" : 0.75,
"f1" : 0.8,
"falseNegative" : 4,
"falsePositive" : 1,
"precision" : 0.9091,
"recall" : 0.7143,
"total" : 20,
"trueNegative" : 5,
"truePositive" : 10
},
"information_question" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 4,
"trueNegative" : 0,
"truePositive" : 4
},
"invitation_question" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 8,
"trueNegative" : 0,
"truePositive" : 8
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 6,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 0.9,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 1,
"precision" : 0,
"recall" : 0,
"total" : 10,
"trueNegative" : 9,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 6,
"trueNegative" : 0,
"truePositive" : 6
},
"quoted_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 4,
"trueNegative" : 4,
"truePositive" : 0
},
"schedule_negotiation_boundary" : {
"accuracy" : 0.9,
"f1" : 0.875,
"falseNegative" : 1,
"falsePositive" : 1,
"precision" : 0.875,
"recall" : 0.875,
"total" : 20,
"trueNegative" : 11,
"truePositive" : 7
},
"schedule_negotiation_golden" : {
"accuracy" : 0.9,
"f1" : 0.9474,
"falseNegative" : 2,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.9,
"total" : 20,
"trueNegative" : 0,
"truePositive" : 18
},
"self_plan" : {
"accuracy" : 0.6667,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 2,
"precision" : 0,
"recall" : 0,
"total" : 6,
"trueNegative" : 4,
"truePositive" : 0
},
"task_question" : {
"accuracy" : 0.8333,
"f1" : 0.9091,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.8333,
"total" : 6,
"trueNegative" : 0,
"truePositive" : 5
},
"task_statement" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 8,
"trueNegative" : 0,
"truePositive" : 8
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9048,
"f1" : 0.9155,
"falseNegative" : 10,
"falsePositive" : 14,
"precision" : 0.9028,
"recall" : 0.9286,
"total" : 252,
"trueNegative" : 98,
"truePositive" : 130
},
"threshold" : 0.58
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.8889,
"f1" : 0.8939,
"falseNegative" : 22,
"falsePositive" : 6,
"precision" : 0.9516,
"recall" : 0.8429,
"total" : 252,
"trueNegative" : 106,
"truePositive" : 118
},
"threshold" : 0.83
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.881,
"f1" : 0.8889,
"falseNegative" : 10,
"falsePositive" : 5,
"precision" : 0.9231,
"recall" : 0.8571,
"total" : 126,
"trueNegative" : 51,
"truePositive" : 60
},
"threshold" : 0.8
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9048,
"f1" : 0.9155,
"falseNegative" : 5,
"falsePositive" : 7,
"precision" : 0.9028,
"recall" : 0.9286,
"total" : 126,
"trueNegative" : 49,
"truePositive" : 65
},
"threshold" : 0.46
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.6508,
"f1" : 0.551,
"falseNegative" : 43,
"falsePositive" : 1,
"precision" : 0.9643,
"recall" : 0.3857,
"total" : 126,
"trueNegative" : 55,
"truePositive" : 27
},
"threshold" : 0.99
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9127,
"f1" : 0.9185,
"falseNegative" : 8,
"falsePositive" : 3,
"precision" : 0.9538,
"recall" : 0.8857,
"total" : 126,
"trueNegative" : 53,
"truePositive" : 62
},
"threshold" : 0.63
}
}
}
],
"corpusRecordCount" : 252,
"exactTrainingOverlapCount" : 252,
"familyCount" : 22,
"generatedAt" : "2026-08-27T05:29:36Z",
"languageCounts" : {
"en" : 126,
"zh-Hans" : 126
},
"manifestSchemaVersion" : 2,
"seed" : 20260826,
"sentiment" : {
"accuracy" : 0.7579,
"correct" : 191,
"macroF1" : 0.7981,
"perLabelF1" : {
"negative" : 0.6452,
"neutral" : 0.8603,
"positive" : 0.8889
},
"total" : 252,
"unknown" : 54,
"unknownRate" : 0.2143
},
"sentimentBySource" : {
"acknowledgment" : {
"accuracy" : 0.375,
"correct" : 3,
"macroF1" : 0.1818,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.5455,
"positive" : 0
},
"total" : 8,
"unknown" : 5,
"unknownRate" : 0.625
},
"blessing_boundary" : {
"accuracy" : 0.45,
"correct" : 9,
"macroF1" : 0.2069,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.6207,
"positive" : 0
},
"total" : 20,
"unknown" : 11,
"unknownRate" : 0.55
},
"blessing_golden" : {
"accuracy" : 0.9,
"correct" : 18,
"macroF1" : 0.3158,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0,
"positive" : 0.9474
},
"total" : 20,
"unknown" : 2,
"unknownRate" : 0.1
},
"complaint_request" : {
"accuracy" : 0.3333,
"correct" : 2,
"macroF1" : 0.1667,
"perLabelF1" : {
"negative" : 0.5,
"neutral" : 0,
"positive" : 0
},
"total" : 6,
"unknown" : 4,
"unknownRate" : 0.6667
},
"complaint_statement" : {
"accuracy" : 1,
"correct" : 6,
"macroF1" : 0.3333,
"perLabelF1" : {
"negative" : 1,
"neutral" : 0,
"positive" : 0
},
"total" : 6,
"unknown" : 0,
"unknownRate" : 0
},
"confirmation_decision_boundary" : {
"accuracy" : 0.75,
"correct" : 15,
"macroF1" : 0.2857,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.8571,
"positive" : 0
},
"total" : 20,
"unknown" : 4,
"unknownRate" : 0.2
},
"confirmation_decision_golden" : {
"accuracy" : 0.85,
"correct" : 17,
"macroF1" : 0.3063,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.9189,
"positive" : 0
},
"total" : 20,
"unknown" : 2,
"unknownRate" : 0.1
},
"conversational_message" : {
"accuracy" : 0.6,
"correct" : 6,
"macroF1" : 0.25,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.75,
"positive" : 0
},
"total" : 10,
"unknown" : 1,
"unknownRate" : 0.1
},
"event_statement" : {
"accuracy" : 1,
"correct" : 4,
"macroF1" : 0.3333,
"perLabelF1" : {
"negative" : 0,
"neutral" : 1,
"positive" : 0
},
"total" : 4,
"unknown" : 0,
"unknownRate" : 0
},
"follow_up_reminder_boundary" : {
"accuracy" : 0.45,
"correct" : 9,
"macroF1" : 0.2069,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.6207,
"positive" : 0
},
"total" : 20,
"unknown" : 10,
"unknownRate" : 0.5
},
"follow_up_reminder_golden" : {
"accuracy" : 0.95,
"correct" : 19,
"macroF1" : 0.3248,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.9744,
"positive" : 0
},
"total" : 20,
"unknown" : 1,
"unknownRate" : 0.05
},
"information_question" : {
"accuracy" : 0.75,
"correct" : 3,
"macroF1" : 0.2857,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.8571,
"positive" : 0
},
"total" : 4,
"unknown" : 1,
"unknownRate" : 0.25
},
"invitation_question" : {
"accuracy" : 1,
"correct" : 8,
"macroF1" : 0.3333,
"perLabelF1" : {
"negative" : 0,
"neutral" : 1,
"positive" : 0
},
"total" : 8,
"unknown" : 0,
"unknownRate" : 0
},
"negative_news" : {
"accuracy" : 0.3333,
"correct" : 2,
"macroF1" : 0.1667,
"perLabelF1" : {
"negative" : 0.5,
"neutral" : 0,
"positive" : 0
},
"total" : 6,
"unknown" : 4,
"unknownRate" : 0.6667
},
"neutral_fact" : {
"accuracy" : 0.6,
"correct" : 6,
"macroF1" : 0.25,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.75,
"positive" : 0
},
"total" : 10,
"unknown" : 3,
"unknownRate" : 0.3
},
"positive_feedback" : {
"accuracy" : 1,
"correct" : 6,
"macroF1" : 0.3333,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0,
"positive" : 1
},
"total" : 6,
"unknown" : 0,
"unknownRate" : 0
},
"quoted_question" : {
"accuracy" : 1,
"correct" : 4,
"macroF1" : 0.3333,
"perLabelF1" : {
"negative" : 0,
"neutral" : 1,
"positive" : 0
},
"total" : 4,
"unknown" : 0,
"unknownRate" : 0
},
"schedule_negotiation_boundary" : {
"accuracy" : 0.9,
"correct" : 18,
"macroF1" : 0.3158,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.9474,
"positive" : 0
},
"total" : 20,
"unknown" : 2,
"unknownRate" : 0.1
},
"schedule_negotiation_golden" : {
"accuracy" : 0.9,
"correct" : 18,
"macroF1" : 0.3158,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.9474,
"positive" : 0
},
"total" : 20,
"unknown" : 2,
"unknownRate" : 0.1
},
"self_plan" : {
"accuracy" : 0.8333,
"correct" : 5,
"macroF1" : 0.303,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.9091,
"positive" : 0
},
"total" : 6,
"unknown" : 1,
"unknownRate" : 0.1667
},
"task_question" : {
"accuracy" : 1,
"correct" : 6,
"macroF1" : 0.3333,
"perLabelF1" : {
"negative" : 0,
"neutral" : 1,
"positive" : 0
},
"total" : 6,
"unknown" : 0,
"unknownRate" : 0
},
"task_statement" : {
"accuracy" : 0.875,
"correct" : 7,
"macroF1" : 0.3111,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.9333,
"positive" : 0
},
"total" : 8,
"unknown" : 1,
"unknownRate" : 0.125
}
}
}