rocky/OSGKeyboard
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
cursor/cloud-agent-1787824905651-vxuwc
OSGKeyboard/ModelTraining/ClipboardSemantics/baselines/2026-08-27-open-data-v3-license-safe/random-holdout-report.json
T
Rocky 42e6252f01 Cursor: Apply local changes for cloud agent
2026-08-27 18:01:46 +08:00

3443 lines
93 KiB
JSON
Raw Permalink Blame History

{
"binaryMacro" : {
"accuracy" : 0.9456,
"f1" : 0.5738,
"precision" : 0.8592,
"recall" : 0.4714
},
"binaryMacroByLanguage" : {
"en" : {
"accuracy" : 0.9382,
"f1" : 0.5313,
"precision" : 0.8532,
"recall" : 0.4313
},
"zh-Hans" : {
"accuracy" : 0.953,
"f1" : 0.6084,
"precision" : 0.8688,
"recall" : 0.5115
}
},
"classifiers" : [
{
"falseNegativeExamples" : [
{
"confidence" : 0.9141,
"family" : "task_next_action",
"id" : "random-20260826-en-task_next_action-016",
"language" : "en",
"text" : "In short, Your next action is to prepare the test findings before the next review for Support."
},
{
"confidence" : 0.9138,
"family" : "follow_up_instruction",
"id" : "random-20260826-en-follow_up_instruction-001",
"language" : "en",
"text" : "For the record, Once the sample arrives, check with the doctor the next day about resolution progress."
},
{
"confidence" : 0.9127,
"family" : "follow_up_instruction",
"id" : "random-20260826-en-follow_up_instruction-009",
"language" : "en",
"text" : "One more thing: Once the contract is signed, check with the landlord the next day about the missing documents."
},
{
"confidence" : 0.8972,
"family" : "follow_up_instruction",
"id" : "random-20260826-zh-Hans-follow_up_instruction-002",
"language" : "zh-Hans",
"text" : "单独记一下，等补丁上线后第二天再找房东确认最终结论，别漏了。"
},
{
"confidence" : 0.8956,
"family" : "task_request",
"id" : "random-20260826-zh-Hans-task_request-008",
"language" : "zh-Hans",
"text" : "对了，项目负责人还缺测试结论，麻烦午休前补齐后在共享文档中留言。"
}
],
"falsePositiveExamples" : [
{
"confidence" : 0.9614,
"family" : "fixed_invitation",
"id" : "random-20260826-en-fixed_invitation-018",
"language" : "en",
"text" : "By the way, I saved you a spot to attend the celebration Saturday evening at meeting room three; can you make it?"
},
{
"confidence" : 0.9407,
"family" : "fixed_invitation",
"id" : "random-20260826-en-fixed_invitation-016",
"language" : "en",
"text" : "For context, I saved you a spot to join a small review tomorrow at 10:30 at meeting room three; can you make it?"
}
],
"id" : "task",
"metrics" : {
"accuracy" : 0.9397,
"f1" : 0.798,
"falseNegative" : 39,
"falsePositive" : 2,
"precision" : 0.9759,
"recall" : 0.675,
"total" : 680,
"trueNegative" : 558,
"truePositive" : 81
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9176,
"f1" : 0.7083,
"falseNegative" : 26,
"falsePositive" : 2,
"precision" : 0.9444,
"recall" : 0.5667,
"total" : 340,
"trueNegative" : 278,
"truePositive" : 34
},
"zh-Hans" : {
"accuracy" : 0.9618,
"f1" : 0.8785,
"falseNegative" : 13,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.7833,
"total" : 340,
"trueNegative" : 280,
"truePositive" : 47
}
},
"metricsBySource" : {
"acknowledgment_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"complaint_support" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"confirmation_decision" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"conversation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"event_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"fixed_invitation" : {
"accuracy" : 0.95,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 2,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 38,
"truePositive" : 0
},
"follow_up_instruction" : {
"accuracy" : 0.775,
"f1" : 0.8732,
"falseNegative" : 9,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.775,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 31
},
"follow_up_personal_reminder" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"information_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"quoted_question_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"schedule_negotiation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"task_next_action" : {
"accuracy" : 0.525,
"f1" : 0.6885,
"falseNegative" : 19,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.525,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 21
},
"task_request" : {
"accuracy" : 0.725,
"f1" : 0.8406,
"falseNegative" : 11,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.725,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 29
},
"vague_future_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9544,
"f1" : 0.8634,
"falseNegative" : 22,
"falsePositive" : 9,
"precision" : 0.9159,
"recall" : 0.8167,
"total" : 680,
"trueNegative" : 551,
"truePositive" : 98
},
"threshold" : 0.79
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.9412,
"f1" : 0.8077,
"falseNegative" : 36,
"falsePositive" : 4,
"precision" : 0.9545,
"recall" : 0.7,
"total" : 680,
"trueNegative" : 556,
"truePositive" : 84
},
"threshold" : 0.9
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9206,
"f1" : 0.7327,
"falseNegative" : 23,
"falsePositive" : 4,
"precision" : 0.9024,
"recall" : 0.6167,
"total" : 340,
"trueNegative" : 276,
"truePositive" : 37
},
"threshold" : 0.9
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9765,
"f1" : 0.9333,
"falseNegative" : 4,
"falsePositive" : 4,
"precision" : 0.9333,
"recall" : 0.9333,
"total" : 340,
"trueNegative" : 276,
"truePositive" : 56
},
"threshold" : 0.59
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9147,
"f1" : 0.6882,
"falseNegative" : 28,
"falsePositive" : 1,
"precision" : 0.9697,
"recall" : 0.5333,
"total" : 340,
"trueNegative" : 279,
"truePositive" : 32
},
"threshold" : 0.95
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9735,
"f1" : 0.9217,
"falseNegative" : 7,
"falsePositive" : 2,
"precision" : 0.9636,
"recall" : 0.8833,
"total" : 340,
"trueNegative" : 278,
"truePositive" : 53
},
"threshold" : 0.79
}
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.9895,
"family" : "information_question",
"id" : "random-20260826-en-information_question-020",
"language" : "en",
"text" : "A quick note: Where does the release stand right now?"
},
{
"confidence" : 0.9891,
"family" : "fixed_invitation",
"id" : "random-20260826-zh-Hans-fixed_invitation-008",
"language" : "zh-Hans",
"text" : "先说重点，我给你留了位置，明天十点半到客户办公室看内部演示，能来不？"
},
{
"confidence" : 0.9889,
"family" : "schedule_negotiation",
"id" : "random-20260826-zh-Hans-schedule_negotiation-012",
"language" : "zh-Hans",
"text" : "对了，下周三午后赶不过去，换成周四午休后你觉得可行吗？"
},
{
"confidence" : 0.9886,
"family" : "complaint_support",
"id" : "random-20260826-zh-Hans-complaint_support-004",
"language" : "zh-Hans",
"text" : "顺便提一句，我已经重试三次，还是账号又被锁住，导致家人收不到商品。请问什么时候能处理？"
},
{
"confidence" : 0.9885,
"family" : "information_question",
"id" : "random-20260826-en-information_question-016",
"language" : "en",
"text" : "The main point is this: Where does the fee adjustment stand right now?"
}
],
"falsePositiveExamples" : [
],
"id" : "question",
"metrics" : {
"accuracy" : 0.85,
"f1" : 0.5321,
"falseNegative" : 102,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.3625,
"total" : 680,
"trueNegative" : 520,
"truePositive" : 58
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.8176,
"f1" : 0.3673,
"falseNegative" : 62,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.225,
"total" : 340,
"trueNegative" : 260,
"truePositive" : 18
},
"zh-Hans" : {
"accuracy" : 0.8824,
"f1" : 0.6667,
"falseNegative" : 40,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.5,
"total" : 340,
"trueNegative" : 260,
"truePositive" : 40
}
},
"metricsBySource" : {
"acknowledgment_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"complaint_support" : {
"accuracy" : 0.275,
"f1" : 0.4314,
"falseNegative" : 29,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.275,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 11
},
"confirmation_decision" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"conversation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"event_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"fixed_invitation" : {
"accuracy" : 0.55,
"f1" : 0.7097,
"falseNegative" : 18,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.55,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 22
},
"follow_up_instruction" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"follow_up_personal_reminder" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"information_question" : {
"accuracy" : 0.525,
"f1" : 0.6885,
"falseNegative" : 19,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.525,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 21
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"quoted_question_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"schedule_negotiation" : {
"accuracy" : 0.1,
"f1" : 0.1818,
"falseNegative" : 36,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.1,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 4
},
"task_next_action" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"task_request" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"vague_future_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9426,
"f1" : 0.8746,
"falseNegative" : 24,
"falsePositive" : 15,
"precision" : 0.9007,
"recall" : 0.85,
"total" : 680,
"trueNegative" : 505,
"truePositive" : 136
},
"threshold" : 0.48
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.9309,
"f1" : 0.8351,
"falseNegative" : 41,
"falsePositive" : 6,
"precision" : 0.952,
"recall" : 0.7438,
"total" : 680,
"trueNegative" : 514,
"truePositive" : 119
},
"threshold" : 0.71
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.8882,
"f1" : 0.7121,
"falseNegative" : 33,
"falsePositive" : 5,
"precision" : 0.9038,
"recall" : 0.5875,
"total" : 340,
"trueNegative" : 255,
"truePositive" : 47
},
"threshold" : 0.72
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9882,
"f1" : 0.9756,
"falseNegative" : 0,
"falsePositive" : 4,
"precision" : 0.9524,
"recall" : 1,
"total" : 340,
"trueNegative" : 256,
"truePositive" : 80
},
"threshold" : 0.16
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.8735,
"f1" : 0.6446,
"falseNegative" : 41,
"falsePositive" : 2,
"precision" : 0.9512,
"recall" : 0.4875,
"total" : 340,
"trueNegative" : 258,
"truePositive" : 39
},
"threshold" : 0.87
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9882,
"f1" : 0.9756,
"falseNegative" : 0,
"falsePositive" : 4,
"precision" : 0.9524,
"recall" : 1,
"total" : 340,
"trueNegative" : 256,
"truePositive" : 80
},
"threshold" : 0.16
}
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.7672,
"family" : "fixed_invitation",
"id" : "random-20260826-zh-Hans-fixed_invitation-004",
"language" : "zh-Hans",
"text" : "刚想到，我给你留了位置，下周三午后到客户办公室参加小范围评审，能来不？"
},
{
"confidence" : 0.7556,
"family" : "fixed_invitation",
"id" : "random-20260826-zh-Hans-fixed_invitation-015",
"language" : "zh-Hans",
"text" : "补充一下，我给你留了位置，明天十点半到三号会议室参加小范围评审，能来不？"
},
{
"confidence" : 0.7004,
"family" : "fixed_invitation",
"id" : "random-20260826-zh-Hans-fixed_invitation-003",
"language" : "zh-Hans",
"text" : "我给你留了位置，周六傍晚到楼下咖啡店碰面聊方案，能来不？"
},
{
"confidence" : 0.6708,
"family" : "fixed_invitation",
"id" : "random-20260826-zh-Hans-fixed_invitation-001",
"language" : "zh-Hans",
"text" : "简单说，我给你留了位置，今晚九点到园区北门参加庆功会，能来不？"
},
{
"confidence" : 0.6481,
"family" : "fixed_invitation",
"id" : "random-20260826-en-fixed_invitation-005",
"language" : "en",
"text" : "Just to add, I saved you a spot to meet to discuss the proposal Saturday evening at the client office; can you make it?"
}
],
"falsePositiveExamples" : [
],
"id" : "invitation",
"metrics" : {
"accuracy" : 0.9706,
"f1" : 0.6667,
"falseNegative" : 20,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.5,
"total" : 680,
"trueNegative" : 640,
"truePositive" : 20
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9676,
"f1" : 0.6207,
"falseNegative" : 11,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.45,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 9
},
"zh-Hans" : {
"accuracy" : 0.9735,
"f1" : 0.7097,
"falseNegative" : 9,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.55,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 11
}
},
"metricsBySource" : {
"acknowledgment_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"complaint_support" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"confirmation_decision" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"conversation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"event_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"fixed_invitation" : {
"accuracy" : 0.5,
"f1" : 0.6667,
"falseNegative" : 20,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.5,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 20
},
"follow_up_instruction" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"follow_up_personal_reminder" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"information_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"quoted_question_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"schedule_negotiation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"task_next_action" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"task_request" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"vague_future_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9824,
"f1" : 0.8378,
"falseNegative" : 9,
"falsePositive" : 3,
"precision" : 0.9118,
"recall" : 0.775,
"total" : 680,
"trueNegative" : 637,
"truePositive" : 31
},
"threshold" : 0.4
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.9824,
"f1" : 0.8286,
"falseNegative" : 11,
"falsePositive" : 1,
"precision" : 0.9667,
"recall" : 0.725,
"total" : 680,
"trueNegative" : 639,
"truePositive" : 29
},
"threshold" : 0.49
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 20
},
"threshold" : 0.13
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9853,
"f1" : 0.8649,
"falseNegative" : 4,
"falsePositive" : 1,
"precision" : 0.9412,
"recall" : 0.8,
"total" : 340,
"trueNegative" : 319,
"truePositive" : 16
},
"threshold" : 0.49
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 20
},
"threshold" : 0.13
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9853,
"f1" : 0.8571,
"falseNegative" : 5,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.75,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 15
},
"threshold" : 0.58
}
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.7414,
"family" : "complaint_support",
"id" : "random-20260826-en-complaint_support-009",
"language" : "en",
"text" : "Also, I have tried three times and tracking has not moved for five days; I cannot continue. When will this be fixed?"
},
{
"confidence" : 0.7278,
"family" : "complaint_support",
"id" : "random-20260826-en-complaint_support-016",
"language" : "en",
"text" : "A quick note: the account is locked again is still unresolved and delivery is now delayed. Can I get a clear answer?"
},
{
"confidence" : 0.721,
"family" : "complaint_support",
"id" : "random-20260826-zh-Hans-complaint_support-017",
"language" : "zh-Hans",
"text" : "顺便提一句，账号又被锁住到现在没解决，客户已经在催，能给一个明确答复吗？"
},
{
"confidence" : 0.6589,
"family" : "complaint_support",
"id" : "random-20260826-zh-Hans-complaint_support-020",
"language" : "zh-Hans",
"text" : "先说重点，付款结果重复扣款到现在没解决，客户已经在催，能给一个明确答复吗？"
},
{
"confidence" : 0.6338,
"family" : "complaint_support",
"id" : "random-20260826-en-complaint_support-006",
"language" : "en",
"text" : "For context, I have tried three times and the page stays blank; delivery is now delayed. When will this be fixed?"
}
],
"falsePositiveExamples" : [
],
"id" : "complaint",
"metrics" : {
"accuracy" : 0.9735,
"f1" : 0.7097,
"falseNegative" : 18,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.55,
"total" : 680,
"trueNegative" : 640,
"truePositive" : 22
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9647,
"f1" : 0.5714,
"falseNegative" : 12,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.4,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 8
},
"zh-Hans" : {
"accuracy" : 0.9824,
"f1" : 0.8235,
"falseNegative" : 6,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.7,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 14
}
},
"metricsBySource" : {
"acknowledgment_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"complaint_support" : {
"accuracy" : 0.55,
"f1" : 0.7097,
"falseNegative" : 18,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.55,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 22
},
"confirmation_decision" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"conversation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"event_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"fixed_invitation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"follow_up_instruction" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"follow_up_personal_reminder" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"information_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"quoted_question_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"schedule_negotiation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"task_next_action" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"task_request" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"vague_future_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9824,
"f1" : 0.8378,
"falseNegative" : 9,
"falsePositive" : 3,
"precision" : 0.9118,
"recall" : 0.775,
"total" : 680,
"trueNegative" : 637,
"truePositive" : 31
},
"threshold" : 0.52
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.9824,
"f1" : 0.8286,
"falseNegative" : 11,
"falsePositive" : 1,
"precision" : 0.9667,
"recall" : 0.725,
"total" : 680,
"trueNegative" : 639,
"truePositive" : 29
},
"threshold" : 0.56
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9794,
"f1" : 0.8,
"falseNegative" : 6,
"falsePositive" : 1,
"precision" : 0.9333,
"recall" : 0.7,
"total" : 340,
"trueNegative" : 319,
"truePositive" : 14
},
"threshold" : 0.5
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9882,
"f1" : 0.8947,
"falseNegative" : 3,
"falsePositive" : 1,
"precision" : 0.9444,
"recall" : 0.85,
"total" : 340,
"trueNegative" : 319,
"truePositive" : 17
},
"threshold" : 0.54
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9765,
"f1" : 0.75,
"falseNegative" : 8,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 12
},
"threshold" : 0.56
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9882,
"f1" : 0.8889,
"falseNegative" : 4,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.8,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 16
},
"threshold" : 0.64
}
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.4229,
"family" : "schedule_negotiation",
"id" : "random-20260826-zh-Hans-schedule_negotiation-002",
"language" : "zh-Hans",
"text" : "单独记一下，原来的时段卡住了，我只能周五临下班前，能不能对调？"
},
{
"confidence" : 0.4084,
"family" : "schedule_negotiation",
"id" : "random-20260826-zh-Hans-schedule_negotiation-018",
"language" : "zh-Hans",
"text" : "原来的时段卡住了，我只能周四午休后，能不能对调？"
},
{
"confidence" : 0.4037,
"family" : "schedule_negotiation",
"id" : "random-20260826-zh-Hans-schedule_negotiation-001",
"language" : "zh-Hans",
"text" : "先说重点，周一早会后赶不过去，换成周五临下班前你觉得可行吗？"
},
{
"confidence" : 0.3942,
"family" : "schedule_negotiation",
"id" : "random-20260826-zh-Hans-schedule_negotiation-007",
"language" : "zh-Hans",
"text" : "补充一下，原来的时段卡住了，我只能周五临下班前，能不能对调？"
},
{
"confidence" : 0.3468,
"family" : "schedule_negotiation",
"id" : "random-20260826-en-schedule_negotiation-018",
"language" : "en",
"text" : "By the way, The original slot is blocked for me; could we swap to next Monday afternoon?"
}
],
"falsePositiveExamples" : [
{
"confidence" : 0.6646,
"family" : "conversation",
"id" : "random-20260826-en-conversation-004",
"language" : "en",
"text" : "Just letting you know, the demo went better than expected; we can talk later."
},
{
"confidence" : 0.6627,
"family" : "conversation",
"id" : "random-20260826-en-conversation-010",
"language" : "en",
"text" : "Just to add, Just letting you know, the demo went better than expected; we can talk later."
},
{
"confidence" : 0.5963,
"family" : "conversation",
"id" : "random-20260826-en-conversation-012",
"language" : "en",
"text" : "Also, Just letting you know, the demo went better than expected; we can talk later."
},
{
"confidence" : 0.5892,
"family" : "conversation",
"id" : "random-20260826-en-conversation-017",
"language" : "en",
"text" : "A quick note: Just letting you know, the demo went better than expected; we can talk later."
},
{
"confidence" : 0.5281,
"family" : "complaint_support",
"id" : "random-20260826-zh-Hans-complaint_support-018",
"language" : "zh-Hans",
"text" : "补充一下，附件始终打不开到现在没解决，我无法继续操作，能给一个明确答复吗？"
}
],
"id" : "scheduleNegotiation",
"metrics" : {
"accuracy" : 0.9721,
"f1" : 0.7397,
"falseNegative" : 13,
"falsePositive" : 6,
"precision" : 0.8182,
"recall" : 0.675,
"total" : 680,
"trueNegative" : 634,
"truePositive" : 27
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9706,
"f1" : 0.75,
"falseNegative" : 5,
"falsePositive" : 5,
"precision" : 0.75,
"recall" : 0.75,
"total" : 340,
"trueNegative" : 315,
"truePositive" : 15
},
"zh-Hans" : {
"accuracy" : 0.9735,
"f1" : 0.7273,
"falseNegative" : 8,
"falsePositive" : 1,
"precision" : 0.9231,
"recall" : 0.6,
"total" : 340,
"trueNegative" : 319,
"truePositive" : 12
}
},
"metricsBySource" : {
"acknowledgment_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"complaint_support" : {
"accuracy" : 0.975,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 1,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 39,
"truePositive" : 0
},
"confirmation_decision" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"conversation" : {
"accuracy" : 0.9,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 4,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 36,
"truePositive" : 0
},
"event_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"fixed_invitation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"follow_up_instruction" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"follow_up_personal_reminder" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"information_question" : {
"accuracy" : 0.975,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 1,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 39,
"truePositive" : 0
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"quoted_question_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"schedule_negotiation" : {
"accuracy" : 0.675,
"f1" : 0.806,
"falseNegative" : 13,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.675,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 27
},
"task_next_action" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"task_request" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"vague_future_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9691,
"f1" : 0.6667,
"falseNegative" : 19,
"falsePositive" : 2,
"precision" : 0.913,
"recall" : 0.525,
"total" : 680,
"trueNegative" : 638,
"truePositive" : 21
},
"threshold" : 0.6
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.9618,
"f1" : 0.5185,
"falseNegative" : 26,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.35,
"total" : 680,
"trueNegative" : 640,
"truePositive" : 14
},
"threshold" : 0.67
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9588,
"f1" : 0.4615,
"falseNegative" : 14,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.3,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 6
},
"threshold" : 0.67
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9882,
"f1" : 0.9,
"falseNegative" : 2,
"falsePositive" : 2,
"precision" : 0.9,
"recall" : 0.9,
"total" : 340,
"trueNegative" : 318,
"truePositive" : 18
},
"threshold" : 0.32
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9588,
"f1" : 0.4615,
"falseNegative" : 14,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.3,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 6
},
"threshold" : 0.67
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9765,
"f1" : 0.75,
"falseNegative" : 8,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 12
},
"threshold" : 0.53
}
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.9897,
"family" : "confirmation_decision",
"id" : "random-20260826-zh-Hans-confirmation_decision-011",
"language" : "zh-Hans",
"text" : "顺便提一句，不用再比较了，就选线下处理方案，后续都按这个口径走。"
},
{
"confidence" : 0.9883,
"family" : "confirmation_decision",
"id" : "random-20260826-zh-Hans-confirmation_decision-014",
"language" : "zh-Hans",
"text" : "先说重点，不用再比较了，就选线下处理方案，后续都按这个口径走。"
},
{
"confidence" : 0.9883,
"family" : "confirmation_decision",
"id" : "random-20260826-zh-Hans-confirmation_decision-007",
"language" : "zh-Hans",
"text" : "单独记一下，不用再比较了，就选线下处理方案，后续都按这个口径走。"
},
{
"confidence" : 0.9848,
"family" : "confirmation_decision",
"id" : "random-20260826-en-confirmation_decision-002",
"language" : "en",
"text" : "No more comparisons: choose the second quote and use it as the final direction."
},
{
"confidence" : 0.9828,
"family" : "confirmation_decision",
"id" : "random-20260826-en-confirmation_decision-013",
"language" : "en",
"text" : "For the record, No more comparisons: choose a limited rollout first and use it as the final direction."
}
],
"falsePositiveExamples" : [
],
"id" : "confirmationDecision",
"metrics" : {
"accuracy" : 0.9456,
"f1" : 0.1395,
"falseNegative" : 37,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.075,
"total" : 680,
"trueNegative" : 640,
"truePositive" : 3
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9471,
"f1" : 0.1818,
"falseNegative" : 18,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.1,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 2
},
"zh-Hans" : {
"accuracy" : 0.9441,
"f1" : 0.0952,
"falseNegative" : 19,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.05,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 1
}
},
"metricsBySource" : {
"acknowledgment_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"complaint_support" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"confirmation_decision" : {
"accuracy" : 0.075,
"f1" : 0.1395,
"falseNegative" : 37,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.075,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 3
},
"conversation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"event_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"fixed_invitation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"follow_up_instruction" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"follow_up_personal_reminder" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"information_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"quoted_question_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"schedule_negotiation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"task_next_action" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"task_request" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"vague_future_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9603,
"f1" : 0.4906,
"falseNegative" : 27,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.325,
"total" : 680,
"trueNegative" : 640,
"truePositive" : 13
},
"threshold" : 0.97
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.9603,
"f1" : 0.4906,
"falseNegative" : 27,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.325,
"total" : 680,
"trueNegative" : 640,
"truePositive" : 13
},
"threshold" : 0.97
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9647,
"f1" : 0.5714,
"falseNegative" : 12,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.4,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 8
},
"threshold" : 0.97
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9853,
"f1" : 0.8649,
"falseNegative" : 4,
"falsePositive" : 1,
"precision" : 0.9412,
"recall" : 0.8,
"total" : 340,
"trueNegative" : 319,
"truePositive" : 16
},
"threshold" : 0.5
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9647,
"f1" : 0.5714,
"falseNegative" : 12,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.4,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 8
},
"threshold" : 0.97
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9794,
"f1" : 0.7879,
"falseNegative" : 7,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.65,
"total" : 340,
"trueNegative" : 320,
"truePositive" : 13
},
"threshold" : 0.56
}
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.9529,
"family" : "follow_up_personal_reminder",
"id" : "random-20260826-zh-Hans-follow_up_personal_reminder-009",
"language" : "zh-Hans",
"text" : "另外，个人备忘：提醒我下次评审前联系医生，追一下处理进度。"
},
{
"confidence" : 0.9461,
"family" : "follow_up_personal_reminder",
"id" : "random-20260826-zh-Hans-follow_up_personal_reminder-008",
"language" : "zh-Hans",
"text" : "顺便提一句，个人备忘：提醒我午休前联系医生，追一下到账情况。"
},
{
"confidence" : 0.9458,
"family" : "follow_up_personal_reminder",
"id" : "random-20260826-zh-Hans-follow_up_personal_reminder-001",
"language" : "zh-Hans",
"text" : "简单说，个人备忘：提醒我明晚之前联系招聘方，追一下处理进度。"
},
{
"confidence" : 0.9455,
"family" : "task_next_action",
"id" : "random-20260826-en-task_next_action-009",
"language" : "en",
"text" : "Also, Your next action is to prepare the acceptance screenshots before lunch for Finance."
},
{
"confidence" : 0.9437,
"family" : "task_next_action",
"id" : "random-20260826-en-task_next_action-019",
"language" : "en",
"text" : "For the record, Your next action is to prepare the acceptance screenshots as this week closes for the vendor."
}
],
"falsePositiveExamples" : [
{
"confidence" : 0.982,
"family" : "vague_future_boundary",
"id" : "random-20260826-zh-Hans-vague_future_boundary-016",
"language" : "zh-Hans",
"text" : "补充一下，哪天有心情再找医生聊下一步安排吧。"
},
{
"confidence" : 0.9791,
"family" : "vague_future_boundary",
"id" : "random-20260826-zh-Hans-vague_future_boundary-011",
"language" : "zh-Hans",
"text" : "另外，哪天有心情再找法务聊下一步安排吧。"
}
],
"id" : "followUpReminder",
"metrics" : {
"accuracy" : 0.9,
"f1" : 0.6136,
"falseNegative" : 66,
"falsePositive" : 2,
"precision" : 0.9643,
"recall" : 0.45,
"total" : 680,
"trueNegative" : 558,
"truePositive" : 54
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9029,
"f1" : 0.6207,
"falseNegative" : 33,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.45,
"total" : 340,
"trueNegative" : 280,
"truePositive" : 27
},
"zh-Hans" : {
"accuracy" : 0.8971,
"f1" : 0.6067,
"falseNegative" : 33,
"falsePositive" : 2,
"precision" : 0.931,
"recall" : 0.45,
"total" : 340,
"trueNegative" : 278,
"truePositive" : 27
}
},
"metricsBySource" : {
"acknowledgment_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"complaint_support" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"confirmation_decision" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"conversation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"event_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"fixed_invitation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"follow_up_instruction" : {
"accuracy" : 0.5,
"f1" : 0.6667,
"falseNegative" : 20,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.5,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 20
},
"follow_up_personal_reminder" : {
"accuracy" : 0.6,
"f1" : 0.75,
"falseNegative" : 16,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.6,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 24
},
"information_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"quoted_question_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"schedule_negotiation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"task_next_action" : {
"accuracy" : 0.25,
"f1" : 0.4,
"falseNegative" : 30,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.25,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 10
},
"task_request" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"vague_future_boundary" : {
"accuracy" : 0.95,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 2,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 38,
"truePositive" : 0
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9794,
"f1" : 0.944,
"falseNegative" : 2,
"falsePositive" : 12,
"precision" : 0.9077,
"recall" : 0.9833,
"total" : 680,
"trueNegative" : 548,
"truePositive" : 118
},
"threshold" : 0.33
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.9588,
"f1" : 0.8739,
"falseNegative" : 23,
"falsePositive" : 5,
"precision" : 0.951,
"recall" : 0.8083,
"total" : 680,
"trueNegative" : 555,
"truePositive" : 97
},
"threshold" : 0.64
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9824,
"f1" : 0.9524,
"falseNegative" : 0,
"falsePositive" : 6,
"precision" : 0.9091,
"recall" : 1,
"total" : 340,
"trueNegative" : 274,
"truePositive" : 60
},
"threshold" : 0.3
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9765,
"f1" : 0.9355,
"falseNegative" : 2,
"falsePositive" : 6,
"precision" : 0.9063,
"recall" : 0.9667,
"total" : 340,
"trueNegative" : 274,
"truePositive" : 58
},
"threshold" : 0.33
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9647,
"f1" : 0.8929,
"falseNegative" : 10,
"falsePositive" : 2,
"precision" : 0.9615,
"recall" : 0.8333,
"total" : 340,
"trueNegative" : 278,
"truePositive" : 50
},
"threshold" : 0.64
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.8882,
"f1" : 0.5476,
"falseNegative" : 37,
"falsePositive" : 1,
"precision" : 0.9583,
"recall" : 0.3833,
"total" : 340,
"trueNegative" : 279,
"truePositive" : 23
},
"threshold" : 0.98
}
}
},
{
"falseNegativeExamples" : [
],
"falsePositiveExamples" : [
],
"id" : "blessing",
"metrics" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 680,
"trueNegative" : 680,
"truePositive" : 0
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 340,
"trueNegative" : 340,
"truePositive" : 0
},
"zh-Hans" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 340,
"trueNegative" : 340,
"truePositive" : 0
}
},
"metricsBySource" : {
"acknowledgment_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"complaint_support" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"confirmation_decision" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"conversation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"event_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"fixed_invitation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"follow_up_instruction" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"follow_up_personal_reminder" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"information_question" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"negative_news" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"quoted_question_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"schedule_negotiation" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"task_next_action" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"task_request" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"vague_future_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
}
},
"thresholdsAt90PrecisionByLanguage" : {
},
"thresholdsAt95PrecisionByLanguage" : {
}
},
{
"falseNegativeExamples" : [
{
"confidence" : 0.6418,
"family" : "conversation",
"id" : "random-20260826-zh-Hans-conversation-020",
"language" : "zh-Hans",
"text" : "另外，路上有点堵，突然想到你可能会想知道。"
},
{
"confidence" : 0.623,
"family" : "confirmation_decision",
"id" : "random-20260826-en-confirmation_decision-001",
"language" : "en",
"text" : "A quick note: No more comparisons: choose quarterly billing and use it as the final direction."
},
{
"confidence" : 0.6078,
"family" : "follow_up_instruction",
"id" : "random-20260826-en-follow_up_instruction-006",
"language" : "en",
"text" : "For the record, Once the payment lands, check with the account manager the next day about the final decision."
},
{
"confidence" : 0.6069,
"family" : "task_next_action",
"id" : "random-20260826-en-task_next_action-009",
"language" : "en",
"text" : "Also, Your next action is to prepare the acceptance screenshots before lunch for Finance."
},
{
"confidence" : 0.5751,
"family" : "task_next_action",
"id" : "random-20260826-en-task_next_action-006",
"language" : "en",
"text" : "One more thing: Your next action is to prepare the test findings within two business days for Operations."
}
],
"falsePositiveExamples" : [
{
"confidence" : 0.9797,
"family" : "follow_up_personal_reminder",
"id" : "random-20260826-zh-Hans-follow_up_personal_reminder-004",
"language" : "zh-Hans",
"text" : "刚想到，个人备忘：提醒我两个工作日内联系客户经理，追一下到账情况。"
},
{
"confidence" : 0.9447,
"family" : "negative_news",
"id" : "random-20260826-en-negative_news-006",
"language" : "en",
"text" : "By the way, Data shows that many flights were delayed overnight, with no request for support."
},
{
"confidence" : 0.9364,
"family" : "vague_future_boundary",
"id" : "random-20260826-zh-Hans-vague_future_boundary-010",
"language" : "zh-Hans",
"text" : "刚想到，哪天有心情再找客户经理聊交付日期吧。"
},
{
"confidence" : 0.9273,
"family" : "event_boundary",
"id" : "random-20260826-zh-Hans-event_boundary-007",
"language" : "zh-Hans",
"text" : "刚想到，历史行程显示他们曾在园区北门碰面聊方案，没有邀请任何人。"
},
{
"confidence" : 0.9268,
"family" : "vague_future_boundary",
"id" : "random-20260826-zh-Hans-vague_future_boundary-006",
"language" : "zh-Hans",
"text" : "刚想到，哪天有心情再找医生聊交付日期吧。"
}
],
"id" : "replyableMessage",
"metrics" : {
"accuracy" : 0.9588,
"f1" : 0.9646,
"falseNegative" : 18,
"falsePositive" : 10,
"precision" : 0.9745,
"recall" : 0.955,
"total" : 680,
"trueNegative" : 270,
"truePositive" : 382
},
"metricsByLanguage" : {
"en" : {
"accuracy" : 0.9559,
"f1" : 0.9616,
"falseNegative" : 12,
"falsePositive" : 3,
"precision" : 0.9843,
"recall" : 0.94,
"total" : 340,
"trueNegative" : 137,
"truePositive" : 188
},
"zh-Hans" : {
"accuracy" : 0.9618,
"f1" : 0.9676,
"falseNegative" : 6,
"falsePositive" : 7,
"precision" : 0.9652,
"recall" : 0.97,
"total" : 340,
"trueNegative" : 133,
"truePositive" : 194
}
},
"metricsBySource" : {
"acknowledgment_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"complaint_support" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 40
},
"confirmation_decision" : {
"accuracy" : 0.975,
"f1" : 0.9873,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.975,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 39
},
"conversation" : {
"accuracy" : 0.85,
"f1" : 0.9189,
"falseNegative" : 6,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.85,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 34
},
"event_boundary" : {
"accuracy" : 0.975,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 1,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 39,
"truePositive" : 0
},
"fixed_invitation" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 40
},
"follow_up_instruction" : {
"accuracy" : 0.975,
"f1" : 0.9873,
"falseNegative" : 1,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.975,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 39
},
"follow_up_personal_reminder" : {
"accuracy" : 0.975,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 1,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 39,
"truePositive" : 0
},
"information_question" : {
"accuracy" : 0.95,
"f1" : 0.9744,
"falseNegative" : 2,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.95,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 38
},
"negative_news" : {
"accuracy" : 0.95,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 2,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 38,
"truePositive" : 0
},
"neutral_fact" : {
"accuracy" : 0.925,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 3,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 37,
"truePositive" : 0
},
"positive_feedback" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 40
},
"quoted_question_boundary" : {
"accuracy" : 1,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 40,
"truePositive" : 0
},
"schedule_negotiation" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 40
},
"task_next_action" : {
"accuracy" : 0.8,
"f1" : 0.8889,
"falseNegative" : 8,
"falsePositive" : 0,
"precision" : 1,
"recall" : 0.8,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 32
},
"task_request" : {
"accuracy" : 1,
"f1" : 1,
"falseNegative" : 0,
"falsePositive" : 0,
"precision" : 1,
"recall" : 1,
"total" : 40,
"trueNegative" : 0,
"truePositive" : 40
},
"vague_future_boundary" : {
"accuracy" : 0.925,
"f1" : 0,
"falseNegative" : 0,
"falsePositive" : 3,
"precision" : 0,
"recall" : 0,
"total" : 40,
"trueNegative" : 37,
"truePositive" : 0
}
},
"thresholdAt90Precision" : {
"metrics" : {
"accuracy" : 0.9353,
"f1" : 0.9474,
"falseNegative" : 4,
"falsePositive" : 40,
"precision" : 0.9083,
"recall" : 0.99,
"total" : 680,
"trueNegative" : 240,
"truePositive" : 396
},
"threshold" : 0.29
},
"thresholdAt95Precision" : {
"metrics" : {
"accuracy" : 0.9529,
"f1" : 0.9603,
"falseNegative" : 13,
"falsePositive" : 19,
"precision" : 0.9532,
"recall" : 0.9675,
"total" : 680,
"trueNegative" : 261,
"truePositive" : 387
},
"threshold" : 0.57
},
"thresholdsAt90PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9412,
"f1" : 0.9522,
"falseNegative" : 1,
"falsePositive" : 19,
"precision" : 0.9128,
"recall" : 0.995,
"total" : 340,
"trueNegative" : 121,
"truePositive" : 199
},
"threshold" : 0.23
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9353,
"f1" : 0.9474,
"falseNegative" : 2,
"falsePositive" : 20,
"precision" : 0.9083,
"recall" : 0.99,
"total" : 340,
"trueNegative" : 120,
"truePositive" : 198
},
"threshold" : 0.38
}
},
"thresholdsAt95PrecisionByLanguage" : {
"en" : {
"metrics" : {
"accuracy" : 0.9588,
"f1" : 0.9653,
"falseNegative" : 5,
"falsePositive" : 9,
"precision" : 0.9559,
"recall" : 0.975,
"total" : 340,
"trueNegative" : 131,
"truePositive" : 195
},
"threshold" : 0.52
},
"zh-Hans" : {
"metrics" : {
"accuracy" : 0.9706,
"f1" : 0.9749,
"falseNegative" : 6,
"falsePositive" : 4,
"precision" : 0.9798,
"recall" : 0.97,
"total" : 340,
"trueNegative" : 136,
"truePositive" : 194
},
"threshold" : 0.86
}
}
}
],
"corpusRecordCount" : 680,
"exactTrainingOverlapCount" : 0,
"familyCount" : 17,
"generatedAt" : "2026-08-27T05:29:37Z",
"languageCounts" : {
"en" : 340,
"zh-Hans" : 340
},
"manifestSchemaVersion" : 2,
"seed" : 20260826,
"sentiment" : {
"accuracy" : 0.8471,
"correct" : 576,
"macroF1" : 0.7142,
"perLabelF1" : {
"negative" : 0.5273,
"neutral" : 0.9486,
"positive" : 0.6667
},
"total" : 680,
"unknown" : 78,
"unknownRate" : 0.1147
},
"sentimentBySource" : {
"acknowledgment_boundary" : {
"accuracy" : 0.9,
"correct" : 36,
"macroF1" : 0.3158,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.9474,
"positive" : 0
},
"total" : 40,
"unknown" : 4,
"unknownRate" : 0.1
},
"complaint_support" : {
"accuracy" : 0.5,
"correct" : 20,
"macroF1" : 0.2222,
"perLabelF1" : {
"negative" : 0.6667,
"neutral" : 0,
"positive" : 0
},
"total" : 40,
"unknown" : 5,
"unknownRate" : 0.125
},
"confirmation_decision" : {
"accuracy" : 0.825,
"correct" : 33,
"macroF1" : 0.3014,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.9041,
"positive" : 0
},
"total" : 40,
"unknown" : 7,
"unknownRate" : 0.175
},
"conversation" : {
"accuracy" : 0.85,
"correct" : 34,
"macroF1" : 0.3063,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.9189,
"positive" : 0
},
"total" : 40,
"unknown" : 5,
"unknownRate" : 0.125
},
"event_boundary" : {
"accuracy" : 1,
"correct" : 40,
"macroF1" : 0.3333,
"perLabelF1" : {
"negative" : 0,
"neutral" : 1,
"positive" : 0
},
"total" : 40,
"unknown" : 0,
"unknownRate" : 0
},
"fixed_invitation" : {
"accuracy" : 0.95,
"correct" : 38,
"macroF1" : 0.3248,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.9744,
"positive" : 0
},
"total" : 40,
"unknown" : 2,
"unknownRate" : 0.05
},
"follow_up_instruction" : {
"accuracy" : 1,
"correct" : 40,
"macroF1" : 0.3333,
"perLabelF1" : {
"negative" : 0,
"neutral" : 1,
"positive" : 0
},
"total" : 40,
"unknown" : 0,
"unknownRate" : 0
},
"follow_up_personal_reminder" : {
"accuracy" : 1,
"correct" : 40,
"macroF1" : 0.3333,
"perLabelF1" : {
"negative" : 0,
"neutral" : 1,
"positive" : 0
},
"total" : 40,
"unknown" : 0,
"unknownRate" : 0
},
"information_question" : {
"accuracy" : 0.925,
"correct" : 37,
"macroF1" : 0.3203,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.961,
"positive" : 0
},
"total" : 40,
"unknown" : 3,
"unknownRate" : 0.075
},
"negative_news" : {
"accuracy" : 0.225,
"correct" : 9,
"macroF1" : 0.1224,
"perLabelF1" : {
"negative" : 0.3673,
"neutral" : 0,
"positive" : 0
},
"total" : 40,
"unknown" : 24,
"unknownRate" : 0.6
},
"neutral_fact" : {
"accuracy" : 0.85,
"correct" : 34,
"macroF1" : 0.3063,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.9189,
"positive" : 0
},
"total" : 40,
"unknown" : 6,
"unknownRate" : 0.15
},
"positive_feedback" : {
"accuracy" : 0.525,
"correct" : 21,
"macroF1" : 0.2295,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0,
"positive" : 0.6885
},
"total" : 40,
"unknown" : 16,
"unknownRate" : 0.4
},
"quoted_question_boundary" : {
"accuracy" : 0.925,
"correct" : 37,
"macroF1" : 0.3203,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.961,
"positive" : 0
},
"total" : 40,
"unknown" : 3,
"unknownRate" : 0.075
},
"schedule_negotiation" : {
"accuracy" : 1,
"correct" : 40,
"macroF1" : 0.3333,
"perLabelF1" : {
"negative" : 0,
"neutral" : 1,
"positive" : 0
},
"total" : 40,
"unknown" : 0,
"unknownRate" : 0
},
"task_next_action" : {
"accuracy" : 1,
"correct" : 40,
"macroF1" : 0.3333,
"perLabelF1" : {
"negative" : 0,
"neutral" : 1,
"positive" : 0
},
"total" : 40,
"unknown" : 0,
"unknownRate" : 0
},
"task_request" : {
"accuracy" : 1,
"correct" : 40,
"macroF1" : 0.3333,
"perLabelF1" : {
"negative" : 0,
"neutral" : 1,
"positive" : 0
},
"total" : 40,
"unknown" : 0,
"unknownRate" : 0
},
"vague_future_boundary" : {
"accuracy" : 0.925,
"correct" : 37,
"macroF1" : 0.3203,
"perLabelF1" : {
"negative" : 0,
"neutral" : 0.961,
"positive" : 0
},
"total" : 40,
"unknown" : 3,
"unknownRate" : 0.075
}
}
}
Reference in New Issue View Git Blame Copy Permalink