scarletnotes STARTLUX step604 No Notes
run_90be2cba06ed490eb48e0c51795875ef · 第15.50分钟 · 请求step604 / 决策step604 / 执行step604 · REPEATED_SUPPORTED · 证据HIGH · 深入复核
一、模型为什么选择它
Native按exploratory-top3-v1聚合:没有confidence>0.5的SAME,存在可信DIFFERENT(p2 对step554=0.734038),因此PROMOTE。另有1条低置信SAME,不具有否决作用。模型未返回自然语言理由;这里解释可复核的判断与聚合,不推测模型内心原因。
当前审核范围 g43s152 / g43a2055;合法历史9条,比较3条。Pair缓存命中:False。
| Pair / 历史step | 原Evidence控件 | 原回答 | confidence | 可信阈值 |
|---|---|---|---|---|
| p1 / 384 | Add Item… | SAME_OPERATION | 0.25503173 | False |
| p2 / 554 | Add Heading… | DIFFERENT_OPERATION | 0.73403823 | True |
| p3 / 591 | 11245851 | DIFFERENT_OPERATION | 0.28780180 | False |
真正发送的state/questions · 原请求回执 · 原回答回执 · 本地审计(没有自动送模型)
展开原始Pair问题、回答和Witness字段
[
{
"pair_id": "p1",
"history_id": "h1",
"history_step": 384,
"history_input_id": "input-2231",
"choice": "SAME_OPERATION",
"confidence": 0.2550317347049713,
"probabilities": {
"SAME_OPERATION": 0.5033544898033142,
"DIFFERENT_OPERATION": 0.40340080857276917,
"INSUFFICIENT_EVIDENCE": 0.09324468672275543
},
"trusted": false,
"pair_cache_hit": false,
"original_question": {
"type": "choice",
"criteria": {
"SAME_OPERATION": "Same application-function operation; only parameter, data object, or entry point differs.",
"DIFFERENT_OPERATION": "Different application-function operations.",
"INSUFFICIENT_EVIDENCE": "The current visible GUI evidence is insufficient to determine the operation relation reliably."
},
"instructions": "Judge whether two concrete GUI actions represent the same application-function operation, using only the supplied GUI evidence and page context.\nSAME_OPERATION: the same application function, differing only in parameter, data object, or entry point.\nDIFFERENT_OPERATION: different application functions.\nINSUFFICIENT_EVIDENCE: the visible evidence is insufficient to judge reliably.\nThe same handler, class, resource ID, menu container, or switch is not sufficient evidence of operation equivalence. Judge application functions, not implementation form.\n\nIs candidate at `candidates.c4` the same application-function operation as executed action at `executed_actions.h1`? Interpret each action using its own source_page_id in pages.\n\nDecision standard:\nSAME_OPERATION means the candidate and the executed history are the same GUI operation pattern already represented; differences limited to data instances, entered values, or equivalent entry points are SAME.\nDIFFERENT_OPERATION means the candidate is a distinct command, feature entry, or interaction branch that the executed history does not represent and is reasonably worth one additional concrete-action attempt. Do not require proof of new method coverage, a new state, or successful completion.\nINSUFFICIENT_EVIDENCE means the supplied GUI and execution history do not support a reliable relation.\nTreat a visible menu-command label as evidence of the command. Do not equate a menu command with ordinary text entered into an EditText. Different Checklist rows with the same edit behavior are normally SAME. For a long-pressed EditText, do not infer a different block operation from the block name alone; it may be ordinary text selection. Similar class, resource ID, outer container, or ModelAction does not establish equivalence. Compare operation behavior, not wording alone."
},
"original_answer": {
"type": "choice",
"choice": "SAME_OPERATION",
"confidence": 0.2550317347049713,
"probabilities": {
"SAME_OPERATION": 0.5033544898033142,
"DIFFERENT_OPERATION": 0.40340080857276917,
"INSUFFICIENT_EVIDENCE": 0.09324468672275543
}
},
"model_visible_history": {
"class": "android.widget.EditText",
"resource_id": "com.bijoysingh.quicknote:id/edit",
"text": "Add Item…",
"content_desc": "",
"enabled": true,
"clickable": true,
"long_clickable": true,
"scrollable": false,
"checked": false,
"selected": false,
"action_type": "MODEL_CLICK",
"index": 1,
"concrete_identity": "MODEL_CLICK|/*[@class=\"android.widget.FrameLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.support.v7.widget.RecyclerView\"][@resource-id=\"com.bijoysingh.quicknote:id/advanced_note_recycler\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.LinearLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=2][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.EditText\"][@resource-id=\"com.bijoysingh.quicknote:id/edit\"][@text=\"Add Item\"][@content-desc=\"\"][@index=1][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='true'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='true'][@scrollable='false']",
"model_action_id": "g43a2055",
"source_state_id": "g43s152",
"bounds": [
221,
395,
1038,
516
],
"source_page_id": "page2",
"target_subtree": [
{
"class": "android.widget.EditText",
"resource_id": "com.bijoysingh.quicknote:id/edit",
"text": "Add Item…",
"content_desc": "",
"enabled": true,
"clickable": true,
"long_clickable": true,
"scrollable": false,
"checked": false,
"selected": false,
"path": []
}
],
"subtree_truncated": false,
"parent": {
"class": "android.widget.LinearLayout",
"resource_id": "",
"text": "",
"content_desc": "",
"enabled": true,
"clickable": false,
"long_clickable": false,
"scrollable": false,
"checked": false,
"selected": false
},
"local_context": {
"parent": {
"class": "android.widget.LinearLayout",
"resource_id": ""
},
"labels": [],
"truncated": false
},
"text_source": "retained_gui_text",
"generated_image_text": false,
"snapshot_provenance": "retained source GUI node; no inferred or reconstructed labels"
},
"offline_only_provenance": {
"source_tree": 479,
"source_gui_timestamp": 384,
"current_state": "g43s152",
"current_model_action": "g43a2055",
"current_version": 43,
"input_confirmed": true,
"confirmation_basis": "live confirmedInputs before review; not function completion",
"attributes_recoverable": true
}
},
{
"pair_id": "p2",
"history_id": "h6",
"history_step": 554,
"history_input_id": "input-3230",
"choice": "DIFFERENT_OPERATION",
"confidence": 0.734038233757019,
"probabilities": {
"SAME_OPERATION": 0.13179290294647217,
"DIFFERENT_OPERATION": 0.8226921558380127,
"INSUFFICIENT_EVIDENCE": 0.04551492631435394
},
"trusted": true,
"pair_cache_hit": false,
"original_question": {
"type": "choice",
"criteria": {
"SAME_OPERATION": "Same application-function operation; only parameter, data object, or entry point differs.",
"DIFFERENT_OPERATION": "Different application-function operations.",
"INSUFFICIENT_EVIDENCE": "The current visible GUI evidence is insufficient to determine the operation relation reliably."
},
"instructions": "Judge whether two concrete GUI actions represent the same application-function operation, using only the supplied GUI evidence and page context.\nSAME_OPERATION: the same application function, differing only in parameter, data object, or entry point.\nDIFFERENT_OPERATION: different application functions.\nINSUFFICIENT_EVIDENCE: the visible evidence is insufficient to judge reliably.\nThe same handler, class, resource ID, menu container, or switch is not sufficient evidence of operation equivalence. Judge application functions, not implementation form.\n\nIs candidate at `candidates.c4` the same application-function operation as executed action at `executed_actions.h6`? Interpret each action using its own source_page_id in pages.\n\nDecision standard:\nSAME_OPERATION means the candidate and the executed history are the same GUI operation pattern already represented; differences limited to data instances, entered values, or equivalent entry points are SAME.\nDIFFERENT_OPERATION means the candidate is a distinct command, feature entry, or interaction branch that the executed history does not represent and is reasonably worth one additional concrete-action attempt. Do not require proof of new method coverage, a new state, or successful completion.\nINSUFFICIENT_EVIDENCE means the supplied GUI and execution history do not support a reliable relation.\nTreat a visible menu-command label as evidence of the command. Do not equate a menu command with ordinary text entered into an EditText. Different Checklist rows with the same edit behavior are normally SAME. For a long-pressed EditText, do not infer a different block operation from the block name alone; it may be ordinary text selection. Similar class, resource ID, outer container, or ModelAction does not establish equivalence. Compare operation behavior, not wording alone."
},
"original_answer": {
"type": "choice",
"choice": "DIFFERENT_OPERATION",
"confidence": 0.734038233757019,
"probabilities": {
"SAME_OPERATION": 0.13179290294647217,
"DIFFERENT_OPERATION": 0.8226921558380127,
"INSUFFICIENT_EVIDENCE": 0.04551492631435394
}
},
"model_visible_history": {
"class": "android.widget.EditText",
"resource_id": "com.bijoysingh.quicknote:id/edit",
"text": "Add Heading…",
"content_desc": "",
"enabled": true,
"clickable": true,
"long_clickable": true,
"scrollable": false,
"checked": false,
"selected": false,
"action_type": "MODEL_CLICK",
"index": 1,
"concrete_identity": "MODEL_CLICK|/*[@class=\"android.widget.FrameLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.support.v7.widget.RecyclerView\"][@resource-id=\"com.bijoysingh.quicknote:id/advanced_note_recycler\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.LinearLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.EditText\"][@resource-id=\"com.bijoysingh.quicknote:id/edit\"][@text=\"Add Head\"][@content-desc=\"\"][@index=1][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='true'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='true'][@scrollable='false']",
"model_action_id": "g43a2055",
"source_state_id": "g43s152",
"bounds": [
74,
89,
1069,
274
],
"source_page_id": "page7",
"target_subtree": [
{
"class": "android.widget.EditText",
"resource_id": "com.bijoysingh.quicknote:id/edit",
"text": "Add Heading…",
"content_desc": "",
"enabled": true,
"clickable": true,
"long_clickable": true,
"scrollable": false,
"checked": false,
"selected": false,
"path": []
}
],
"subtree_truncated": false,
"parent": {
"class": "android.widget.LinearLayout",
"resource_id": "",
"text": "",
"content_desc": "",
"enabled": true,
"clickable": false,
"long_clickable": false,
"scrollable": false,
"checked": false,
"selected": false
},
"local_context": {
"parent": {
"class": "android.widget.LinearLayout",
"resource_id": ""
},
"labels": [],
"truncated": false
},
"text_source": "retained_gui_text",
"generated_image_text": false,
"snapshot_provenance": "retained source GUI node; no inferred or reconstructed labels"
},
"offline_only_provenance": {
"source_tree": 658,
"source_gui_timestamp": 554,
"current_state": "g43s152",
"current_model_action": "g43a2055",
"current_version": 43,
"input_confirmed": true,
"confirmation_basis": "live confirmedInputs before review; not function completion",
"attributes_recoverable": true
}
},
{
"pair_id": "p3",
"history_id": "h8",
"history_step": 591,
"history_input_id": "input-3440",
"choice": "DIFFERENT_OPERATION",
"confidence": 0.2878018021583557,
"probabilities": {
"SAME_OPERATION": 0.32214948534965515,
"DIFFERENT_OPERATION": 0.5252012014389038,
"INSUFFICIENT_EVIDENCE": 0.15264925360679626
},
"trusted": false,
"pair_cache_hit": false,
"original_question": {
"type": "choice",
"criteria": {
"SAME_OPERATION": "Same application-function operation; only parameter, data object, or entry point differs.",
"DIFFERENT_OPERATION": "Different application-function operations.",
"INSUFFICIENT_EVIDENCE": "The current visible GUI evidence is insufficient to determine the operation relation reliably."
},
"instructions": "Judge whether two concrete GUI actions represent the same application-function operation, using only the supplied GUI evidence and page context.\nSAME_OPERATION: the same application function, differing only in parameter, data object, or entry point.\nDIFFERENT_OPERATION: different application functions.\nINSUFFICIENT_EVIDENCE: the visible evidence is insufficient to judge reliably.\nThe same handler, class, resource ID, menu container, or switch is not sufficient evidence of operation equivalence. Judge application functions, not implementation form.\n\nIs candidate at `candidates.c4` the same application-function operation as executed action at `executed_actions.h8`? Interpret each action using its own source_page_id in pages.\n\nDecision standard:\nSAME_OPERATION means the candidate and the executed history are the same GUI operation pattern already represented; differences limited to data instances, entered values, or equivalent entry points are SAME.\nDIFFERENT_OPERATION means the candidate is a distinct command, feature entry, or interaction branch that the executed history does not represent and is reasonably worth one additional concrete-action attempt. Do not require proof of new method coverage, a new state, or successful completion.\nINSUFFICIENT_EVIDENCE means the supplied GUI and execution history do not support a reliable relation.\nTreat a visible menu-command label as evidence of the command. Do not equate a menu command with ordinary text entered into an EditText. Different Checklist rows with the same edit behavior are normally SAME. For a long-pressed EditText, do not infer a different block operation from the block name alone; it may be ordinary text selection. Similar class, resource ID, outer container, or ModelAction does not establish equivalence. Compare operation behavior, not wording alone."
},
"original_answer": {
"type": "choice",
"choice": "DIFFERENT_OPERATION",
"confidence": 0.2878018021583557,
"probabilities": {
"SAME_OPERATION": 0.32214948534965515,
"DIFFERENT_OPERATION": 0.5252012014389038,
"INSUFFICIENT_EVIDENCE": 0.15264925360679626
}
},
"model_visible_history": {
"class": "android.widget.EditText",
"resource_id": "com.bijoysingh.quicknote:id/edit",
"text": "11245851",
"content_desc": "",
"enabled": true,
"clickable": true,
"long_clickable": true,
"scrollable": false,
"checked": false,
"selected": false,
"action_type": "MODEL_CLICK",
"index": 1,
"concrete_identity": "MODEL_CLICK|/*[@class=\"android.widget.FrameLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.support.v7.widget.RecyclerView\"][@resource-id=\"com.bijoysingh.quicknote:id/advanced_note_recycler\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.LinearLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=4][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.EditText\"][@resource-id=\"com.bijoysingh.quicknote:id/edit\"][@text=\"11245851\"][@content-desc=\"\"][@index=1][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='true'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='true'][@scrollable='false']",
"model_action_id": "g43a2055",
"source_state_id": "g43s152",
"bounds": [
221,
637,
1038,
758
],
"source_page_id": "page9",
"target_subtree": [
{
"class": "android.widget.EditText",
"resource_id": "com.bijoysingh.quicknote:id/edit",
"text": "11245851",
"content_desc": "",
"enabled": true,
"clickable": true,
"long_clickable": true,
"scrollable": false,
"checked": false,
"selected": false,
"path": []
}
],
"subtree_truncated": false,
"parent": {
"class": "android.widget.LinearLayout",
"resource_id": "",
"text": "",
"content_desc": "",
"enabled": true,
"clickable": false,
"long_clickable": false,
"scrollable": false,
"checked": false,
"selected": false
},
"local_context": {
"parent": {
"class": "android.widget.LinearLayout",
"resource_id": ""
},
"labels": [],
"truncated": false
},
"text_source": "retained_gui_text",
"generated_image_text": false,
"snapshot_provenance": "retained source GUI node; no inferred or reconstructed labels"
},
"offline_only_provenance": {
"source_tree": 695,
"source_gui_timestamp": 591,
"current_state": "g43s152",
"current_model_action": "g43a2055",
"current_version": 43,
"input_confirmed": true,
"confirmation_basis": "live confirmedInputs before review; not function completion",
"attributes_recoverable": true
}
}
]二、此前APE实际做过什么
384已经点击Add Item清单行编辑框;604对已有No Notes文本行只取得焦点。模型确实给384 SAME,但confidence=.255低于Native可信阈值,另一个Heading DIFFERENT=.734触发PROMOTE。
等价历史是否送入Provider wire:YES;当前Pair直接比较过的等价历史step:[384]。这是wire可见性,服务端最终token渲染是否逐字段保留仍UNKNOWN。
| 此前step / UTC | 页面与控件 | 确认与目标 |
|---|---|---|
| 384 2026-11-06T18:50:04.973+00:00 | Add Item… com.maubis.scarlet.base.note.creation.activity.CreateListNoteActivity | Native确认=True com.maubis.scarlet.base.note.creation.activity.CreateListNoteActivity 保留目标GUI |
历史Witness执行后的截图(事后证据,未送模型)
三、Probe执行后发生什么
点击清单文本 No Notes,只出现编辑焦点/光标;仍为原清单,无新增方法。


Run内首次METHOD观察:完成后2秒=0,10秒=0,下一动作前B=0。仅时间关联;A2/A10可含后续动作。原方法完整名单及时间戳。
后续APE输入与生命周期原始事件
{
"following_actions": [
{
"input_id": "input-3537",
"step": 605,
"version": 43,
"elapsed_s": 931.225,
"wall_time_ms": 1793991338060,
"next_input_wall_ms": 1793991341895,
"input_completed_wall_ms": 1793991338977,
"input_confirmed": true,
"action": "MODEL_CLICK Add Quot",
"action_type": "MODEL_CLICK",
"text": "Add Quot",
"content_desc": "",
"resource_id": "com.bijoysingh.quicknote:id/edit",
"model_action_id": "g43a2055",
"concrete_identity": "MODEL_CLICK|/*[@class=\"android.widget.FrameLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.support.v7.widget.RecyclerView\"][@resource-id=\"com.bijoysingh.quicknote:id/advanced_note_recycler\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.LinearLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=3][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.EditText\"][@resource-id=\"com.bijoysingh.quicknote:id/edit\"][@text=\"Add Quot\"][@content-desc=\"\"][@index=1][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='true'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='true'][@scrollable='false']",
"state_id": "g43s152",
"source_gui_id": 709,
"activity": "com.maubis.scarlet.base.note.creation.activity.CreateListNoteActivity",
"activity_evidence": "GUI receipt",
"labels": [
"Add Heading…",
"No Notes",
"Add Item…",
"Add Quoted Text…",
"-775349830649867531420.7"
],
"probe": true,
"strategy": "PROBE",
"context": "exploration",
"native_branch": "Probe",
"executor_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_90be2cba06ed490eb48e0c51795875ef.zip!device-output/executor.log:59798",
"observed_methods_until_next": 0,
"category_counts": {},
"inventory_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_90be2cba06ed490eb48e0c51795875ef.zip!device-output/native/sata-com.bijoysingh.quicknote-ape-sata-running-minutes-60/jev-audit/inputs/generated-3539.json"
},
{
"input_id": "input-3546",
"step": 606,
"version": 43,
"elapsed_s": 935.06,
"wall_time_ms": 1793991341895,
"next_input_wall_ms": 1793991344733,
"input_completed_wall_ms": 1793991341977,
"input_confirmed": true,
"action": "MODEL_CLICK android.view.ViewGroup",
"action_type": "MODEL_CLICK",
"text": "",
"content_desc": "",
"resource_id": "",
"model_action_id": "g43a2053",
"concrete_identity": "MODEL_CLICK|/*[@class=\"android.widget.FrameLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.view.ViewGroup\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=7][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false']",
"state_id": "g43s152",
"source_gui_id": 710,
"activity": "com.maubis.scarlet.base.note.creation.activity.CreateListNoteActivity",
"activity_evidence": "GUI receipt",
"labels": [
"Add Heading…",
"No Notes",
"Add Item…",
"+8.\n",
"-775349830649867531420.7",
"Add Quoted Text…"
],
"probe": false,
"strategy": "EARLY_STAGE",
"context": "navigation",
"native_branch": "Remote Greedy",
"executor_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_90be2cba06ed490eb48e0c51795875ef.zip!device-output/executor.log:59878",
"observed_methods_until_next": 0,
"category_counts": {},
"inventory_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_90be2cba06ed490eb48e0c51795875ef.zip!device-output/native/sata-com.bijoysingh.quicknote-ape-sata-running-minutes-60/jev-audit/inputs/generated-3548.json"
},
{
"input_id": "input-3555",
"step": 607,
"version": 43,
"elapsed_s": 937.898,
"wall_time_ms": 1793991344733,
"next_input_wall_ms": 1793991347840,
"input_completed_wall_ms": 1793991344810,
"input_confirmed": true,
"action": "MODEL_CLICK android.view.ViewGroup",
"action_type": "MODEL_CLICK",
"text": "",
"content_desc": "",
"resource_id": "",
"model_action_id": "g43a2053",
"concrete_identity": "MODEL_CLICK|/*[@class=\"android.widget.FrameLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.view.ViewGroup\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=5][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false']",
"state_id": "g43s152",
"source_gui_id": 711,
"activity": "com.maubis.scarlet.base.note.creation.activity.CreateListNoteActivity",
"activity_evidence": "GUI receipt",
"labels": [
"Add Heading…",
"No Notes",
"Add Item…",
"+8.\n",
"-775349830649867531420.7",
"Add Quoted Text…"
],
"probe": false,
"strategy": "EARLY_STAGE",
"context": "navigation",
"native_branch": "Remote Greedy",
"executor_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_90be2cba06ed490eb48e0c51795875ef.zip!device-output/executor.log:59953",
"observed_methods_until_next": 0,
"category_counts": {},
"inventory_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_90be2cba06ed490eb48e0c51795875ef.zip!device-output/native/sata-com.bijoysingh.quicknote-ape-sata-running-minutes-60/jev-audit/inputs/generated-3557.json"
},
{
"input_id": "input-3569",
"step": 608,
"version": 43,
"elapsed_s": 941.005,
"wall_time_ms": 1793991347840,
"next_input_wall_ms": 1793991351571,
"input_completed_wall_ms": 1793991348913,
"input_confirmed": true,
"action": "MODEL_LONG_CLICK No Notes",
"action_type": "MODEL_LONG_CLICK",
"text": "No Notes",
"content_desc": "",
"resource_id": "com.bijoysingh.quicknote:id/edit",
"model_action_id": "g43a2056",
"concrete_identity": "MODEL_LONG_CLICK|/*[@class=\"android.widget.FrameLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.support.v7.widget.RecyclerView\"][@resource-id=\"com.bijoysingh.quicknote:id/advanced_note_recycler\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.LinearLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=1][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.EditText\"][@resource-id=\"com.bijoysingh.quicknote:id/edit\"][@text=\"No Notes\"][@content-desc=\"\"][@index=1][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='true'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='true'][@scrollable='false']",
"state_id": "g43s152",
"source_gui_id": 712,
"activity": "com.maubis.scarlet.base.note.creation.activity.CreateListNoteActivity",
"activity_evidence": "GUI receipt",
"labels": [
"Add Heading…",
"No Notes",
"Add Item…",
"+8.\n",
"-775349830649867531420.7",
"Add Quoted Text…"
],
"probe": true,
"strategy": "PROBE",
"context": "exploration",
"native_branch": "Probe",
"executor_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_90be2cba06ed490eb48e0c51795875ef.zip!device-output/executor.log:60045",
"observed_methods_until_next": 0,
"category_counts": {},
"inventory_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_90be2cba06ed490eb48e0c51795875ef.zip!device-output/native/sata-com.bijoysingh.quicknote-ape-sata-running-minutes-60/jev-audit/inputs/generated-3570.json"
},
{
"input_id": "input-3577",
"step": 609,
"version": 43,
"elapsed_s": 944.736,
"wall_time_ms": 1793991351571,
"next_input_wall_ms": 1793991354446,
"input_completed_wall_ms": 1793991351595,
"input_confirmed": true,
"action": "MODEL_CLICK android.view.ViewGroup",
"action_type": "MODEL_CLICK",
"text": "",
"content_desc": "",
"resource_id": "",
"model_action_id": "g43a2053",
"concrete_identity": "MODEL_CLICK|/*[@class=\"android.widget.FrameLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.view.ViewGroup\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=7][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false']",
"state_id": "g43s152",
"source_gui_id": 713,
"activity": "com.maubis.scarlet.base.note.creation.activity.CreateListNoteActivity",
"activity_evidence": "GUI receipt",
"labels": [
"Add Heading…",
"No Notes",
"Add Item…",
"+8.\n",
"-775349830649867531420.7",
"Add Quoted Text…"
],
"probe": false,
"strategy": "EARLY_STAGE",
"context": "navigation",
"native_branch": "Remote Greedy",
"executor_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_90be2cba06ed490eb48e0c51795875ef.zip!device-output/executor.log:60135",
"observed_methods_until_next": 0,
"category_counts": {},
"inventory_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_90be2cba06ed490eb48e0c51795875ef.zip!device-output/native/sata-com.bijoysingh.quicknote-ape-sata-running-minutes-60/jev-audit/inputs/generated-3578.json"
}
],
"lifecycle": {
"DECISION_PROBE": {
"event": "DECISION_PROBE",
"step": 604,
"monotonic_ns": 1880384430160898,
"wall_time_ms": 1793991336876,
"abstraction_version": 43,
"state_id": "g43s152",
"model_action_id": "g43a2055",
"entry_id": "semantic-27-c4",
"request_id": "semantic-27",
"candidate_id": "c4",
"confidence": 0.734038233757019,
"choice": "PROMOTE",
"parsed_outcome": "PROBE",
"ledger_status": "STAGED",
"decision_role": "candidate_decision",
"input_signature": "ce4d044cd9c9265bec3a7f31d3b121c3eaa5d38ac760308ed6c333f2aa755ae1",
"concrete_identity": "25fd56865964c4a0582998259cd23c51476e5a881501763867ec968991a017d1",
"decision_scope": "0a645ed5ae030a2538119f89669257f90e4b3697a49ab865cc4a2b8539283109",
"representative_model_action_id": "PROMOTE",
"decision_request_id": "semantic-27",
"aggregation_policy": "exploratory-top3-v1",
"total_history": 9,
"history_complete": true,
"unknown_mapping_count": 0,
"recoverable_history_count": 9,
"selected_history": 3,
"comparison_count": 3,
"same_count": 1,
"different_count": 2,
"insufficient_count": 0,
"trusted_same_count": 0,
"trusted_different_count": 1,
"low_confidence_count": 2,
"full_history_compared": false,
"exploratory": true,
"_line": 2084
},
"SEMANTIC_DECISION_STORED": {
"event": "SEMANTIC_DECISION_STORED",
"step": 604,
"monotonic_ns": 1880384430536291,
"wall_time_ms": 1793991336877,
"abstraction_version": 43,
"state_id": "g43s152",
"model_action_id": "g43a2055",
"entry_id": "semantic-27-c4",
"request_id": "semantic-27",
"candidate_id": "c4",
"decision_role": "candidate_decision",
"ledger_status": "PROBE",
"input_signature": "ce4d044cd9c9265bec3a7f31d3b121c3eaa5d38ac760308ed6c333f2aa755ae1",
"input_fingerprint": "e487c3cd062315a8dfc7cead7ce9e1c361e2136a68f55a72872c492e7f8fa369",
"concrete_identity": "25fd56865964c4a0582998259cd23c51476e5a881501763867ec968991a017d1",
"decision_scope": "0a645ed5ae030a2538119f89669257f90e4b3697a49ab865cc4a2b8539283109",
"_line": 2086
},
"PROBE_BOUND": {
"event": "PROBE_BOUND",
"step": 604,
"monotonic_ns": 1880384469510105,
"wall_time_ms": 1793991336916,
"abstraction_version": 43,
"state_id": "g43s152",
"model_action_id": "g43a2055",
"entry_id": "semantic-27-c4",
"request_id": "semantic-27",
"candidate_id": "c4",
"confidence": 0.734038233757019,
"choice": "PROMOTE",
"source": "semantic_sync",
"input_signature": "ce4d044cd9c9265bec3a7f31d3b121c3eaa5d38ac760308ed6c333f2aa755ae1",
"decision_scope": "0a645ed5ae030a2538119f89669257f90e4b3697a49ab865cc4a2b8539283109",
"concrete_identity": "25fd56865964c4a0582998259cd23c51476e5a881501763867ec968991a017d1",
"_line": 2088
},
"PROBE_SELECTED": {
"event": "PROBE_SELECTED",
"step": 604,
"monotonic_ns": 1880384469548608,
"wall_time_ms": 1793991336916,
"abstraction_version": 43,
"state_id": "g43s152",
"model_action_id": "g43a2055",
"entry_id": "semantic-27-c4",
"request_id": "semantic-27",
"candidate_id": "c4",
"confidence": 0.734038233757019,
"choice": "PROMOTE",
"source": "semantic_sync",
"_line": 2089
},
"PROBE_INPUT_GENERATED": {
"event": "PROBE_INPUT_GENERATED",
"step": 604,
"monotonic_ns": 1880384513064839,
"wall_time_ms": 1793991336959,
"abstraction_version": 43,
"state_id": null,
"model_action_id": null,
"entry_id": "semantic-27-c4",
"request_id": "semantic-27",
"candidate_id": "c4",
"event_count": 2,
"_line": 2092
},
"PROBE_INPUT_COMPLETED": {
"event": "PROBE_INPUT_COMPLETED",
"step": 604,
"monotonic_ns": 1880384548323453,
"wall_time_ms": 1793991336994,
"abstraction_version": 43,
"state_id": null,
"model_action_id": null,
"input_phase": "input_injected",
"event_count": 2,
"injected_success": 2,
"injected_failed": 0,
"discarded": 0,
"unreported": 0,
"entry_id": "semantic-27-c4",
"request_id": "semantic-27",
"candidate_id": "c4",
"_line": 2093
},
"PROBE_EXECUTED": {
"event": "PROBE_EXECUTED",
"step": 605,
"monotonic_ns": 1880385284348367,
"wall_time_ms": 1793991337730,
"abstraction_version": 43,
"state_id": "g43s152",
"model_action_id": "g43a2055",
"entry_id": "semantic-27-c4",
"request_id": "semantic-27",
"candidate_id": "c4",
"confidence": 0.734038233757019,
"choice": "PROMOTE",
"transition_id": "g43e271:598",
"target_state": "g43s152",
"input_confirmed": true,
"_line": 2095
}
},
"selection_at_execution": {
"event": "SELECTION_DECISION",
"step": 604,
"monotonic_ns": 1880384469809102,
"wall_time_ms": 1793991336916,
"abstraction_version": 43,
"state_id": "g43s152",
"model_action_id": "g43a2055",
"snapshot_reason": "selection",
"state_visits": 100,
"state_first_seen": 163,
"state_last_seen": 604,
"state_saturated": true,
"state_saturation": 1,
"native_state_saturated": true,
"native_unsaturated_model_action_count": 0,
"model_action_count": 5,
"enabled_valid_action_count": 5,
"unsaturated_model_action_count": 0,
"unvisited_model_action_count": 0,
"effective_unvisited_model_action_count": 0,
"effective_state_saturated": true,
"local_probe_action_count": 0,
"navigation_action_count": 0,
"enabled_valid_unvisited_action_count": 0,
"unvisited_model_action_ids": "",
"selection_strategy": "PROBE",
"selection_context": "exploration",
"selection_buffer_size_after": 0,
"selected_model_action_type": "MODEL_CLICK",
"selected_model_action_saturated": true,
"selected_model_action_unvisited": false,
"selected_effective_unvisited": false,
"selected_navigation_target": false,
"selected_model_action_visits": 8,
"selected_action_fingerprint": "type=MODEL_CLICK|activity=com.maubis.scarlet.base.note.creation.activity.CreateListNoteActivity|class=android.widget.EditText|text=No Notes|resource_id=com.bijoysingh.quicknote:id/edit|bounds=221,274,1038,395",
"selected_resolved_node_count": 16,
"_line": 2091
}
}四、是否值得PROMOTE
完整已保存历史支持此前已尝试等价功能;不能自动归为模型错误。
疑似主要环节:CANDIDATE_AGGREGATION_POLICY;wire关系审查:SAME_WITNESS_PRESENT_LOW_CONFIDENCE。
冻结实现:Registry历史范围(315–342) · Top3(210–230)及聚合(146–178) · Ledger pending与确认(235–285) · Probe调度机会(415–468)。源码行号是原文件行号,GUI历史与源码解释分别有边界。
即便新功能也只证明此次Probe填补了该Run当时的遗漏;正常APE仍可经后续Epsilon等策略选到,不能推出Pure永远不会执行。全部事实与原始位置 · 本Run完整保留输入历史

