wikipedia STARTLUX step615 Settings
run_d04ae609a94042e28f3ab00ddb284ca9 · 第16.51分钟 · 请求step615 / 决策step615 / 执行step615 · NEW_SUPPORTED · 证据HIGH · 结构化审查
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(p1 对step312=0.933366;p2 对step455=0.929857),因此PROMOTE。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 g8s93 / g8a974;合法历史2条,比较2条。Pair缓存命中:False。
| Pair / 历史step | 原Evidence控件 | 原回答 | confidence | 可信阈值 |
|---|---|---|---|---|
| p1 / 312 | Places | DIFFERENT_OPERATION | 0.93336642 | True |
| p2 / 455 | Places | DIFFERENT_OPERATION | 0.92985657 | True |
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": 312,
"history_input_id": "input-1649",
"choice": "DIFFERENT_OPERATION",
"confidence": 0.9333664178848267,
"probabilities": {
"SAME_OPERATION": 0.017833616584539413,
"DIFFERENT_OPERATION": 0.9555776119232178,
"INSUFFICIENT_EVIDENCE": 0.026588691398501396
},
"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.c1` 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": "DIFFERENT_OPERATION",
"confidence": 0.9333664178848267,
"probabilities": {
"SAME_OPERATION": 0.017833616584539413,
"DIFFERENT_OPERATION": 0.9555776119232178,
"INSUFFICIENT_EVIDENCE": 0.026588691398501396
}
},
"model_visible_history": {
"class": "android.widget.TextView",
"resource_id": "",
"text": "Places",
"content_desc": "",
"enabled": true,
"clickable": true,
"long_clickable": false,
"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.view.ViewGroup\"][@resource-id=\"org.wikipedia:id/coordinator\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.FrameLayout\"][@resource-id=\"org.wikipedia:id/design_bottom_sheet\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.ScrollView\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.LinearLayout\"][@resource-id=\"org.wikipedia:id/main_drawer_places_container\"][@text=\"\"][@content-desc=\"\"][@index=1][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.TextView\"][@resource-id=\"\"][@text=\"Places\"][@content-desc=\"\"][@index=1][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false']",
"model_action_id": "g8a974",
"source_state_id": "g8s93",
"bounds": [
168,
1993,
1038,
2050
],
"source_page_id": "page2",
"target_subtree": [
{
"class": "android.widget.TextView",
"resource_id": "",
"text": "Places",
"content_desc": "",
"enabled": true,
"clickable": true,
"long_clickable": false,
"scrollable": false,
"checked": false,
"selected": false,
"path": []
}
],
"subtree_truncated": false,
"parent": {
"class": "android.widget.LinearLayout",
"resource_id": "org.wikipedia:id/main_drawer_places_container",
"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": "org.wikipedia:id/main_drawer_places_container"
},
"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": 410,
"source_gui_timestamp": 312,
"current_state": "g8s93",
"current_model_action": "g8a974",
"current_version": 33,
"input_confirmed": true,
"confirmation_basis": "live confirmedInputs before review; not function completion",
"attributes_recoverable": true
}
},
{
"pair_id": "p2",
"history_id": "h2",
"history_step": 455,
"history_input_id": "input-2397",
"choice": "DIFFERENT_OPERATION",
"confidence": 0.9298565685749054,
"probabilities": {
"SAME_OPERATION": 0.017938027158379555,
"DIFFERENT_OPERATION": 0.9532377123832703,
"INSUFFICIENT_EVIDENCE": 0.028824210166931152
},
"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.c1` the same application-function operation as executed action at `executed_actions.h2`? 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": 0.9298565685749054,
"probabilities": {
"SAME_OPERATION": 0.017938027158379555,
"DIFFERENT_OPERATION": 0.9532377123832703,
"INSUFFICIENT_EVIDENCE": 0.028824210166931152
}
},
"model_visible_history": {
"class": "android.widget.TextView",
"resource_id": "",
"text": "Places",
"content_desc": "",
"enabled": true,
"clickable": true,
"long_clickable": false,
"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.view.ViewGroup\"][@resource-id=\"org.wikipedia:id/coordinator\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.FrameLayout\"][@resource-id=\"org.wikipedia:id/design_bottom_sheet\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.ScrollView\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.LinearLayout\"][@resource-id=\"org.wikipedia:id/main_drawer_places_container\"][@text=\"\"][@content-desc=\"\"][@index=1][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.TextView\"][@resource-id=\"\"][@text=\"Places\"][@content-desc=\"\"][@index=1][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false']",
"model_action_id": "g8a974",
"source_state_id": "g8s93",
"bounds": [
168,
1993,
1038,
2050
],
"source_page_id": "page3",
"target_subtree": [
{
"class": "android.widget.TextView",
"resource_id": "",
"text": "Places",
"content_desc": "",
"enabled": true,
"clickable": true,
"long_clickable": false,
"scrollable": false,
"checked": false,
"selected": false,
"path": []
}
],
"subtree_truncated": false,
"parent": {
"class": "android.widget.LinearLayout",
"resource_id": "org.wikipedia:id/main_drawer_places_container",
"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": "org.wikipedia:id/main_drawer_places_container"
},
"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": 601,
"source_gui_timestamp": 455,
"current_state": "g8s93",
"current_model_action": "g8a974",
"current_version": 33,
"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
输入冻结前无SettingsActivity记录或Settings导航输入;两条Witness均是Places。615打开General/语言/Feed/主题设置,是独立功能。
等价历史是否送入Provider wire:NO_EQUIVALENT_PRIOR_SUPPORTED;当前Pair直接比较过的等价历史step:[]。这是wire可见性,服务端最终token渲染是否逐字段保留仍UNKNOWN。
未发现对应功能Activity或导航输入的先前记录;检索范围和阴性结果见六条首次功能的完整检索清单。结论受已保存Native历史边界约束。
三、Probe执行后发生什么
Settings 打开语言/Feed/主题/同步设置页;B窗口155首次方法。


Run内首次METHOD观察:完成后2秒=155,10秒=178,下一动作前B=155。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-3278",
"step": 616,
"version": 35,
"elapsed_s": 995.673,
"wall_time_ms": 1793991484719,
"next_input_wall_ms": 1793991485980,
"input_completed_wall_ms": 1793991485085,
"input_confirmed": true,
"action": "MODEL_SCROLL_TOP_DOWN org.wikipedia:id/recycler_view",
"action_type": "MODEL_SCROLL_TOP_DOWN",
"text": "",
"content_desc": "",
"resource_id": "org.wikipedia:id/recycler_view",
"model_action_id": "g35a2322",
"concrete_identity": "MODEL_SCROLL_TOP_DOWN|/*[@class=\"android.widget.FrameLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"androidx.recyclerview.widget.RecyclerView\"][@resource-id=\"org.wikipedia:id/recycler_view\"][@text=\"\"][@content-desc=\"\"][@index=2][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='true'][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='true']",
"state_id": "g35s205",
"source_gui_id": 773,
"activity": "org.wikipedia.settings.SettingsActivity",
"activity_evidence": "GUI receipt",
"labels": [
"#f1409233",
"Settings",
"General",
"Wikipedia languages",
"italiano, 中文(中国大陆), français, English",
"Explore Feed",
"Customize the Explore feed",
"Show link previews",
"Show a quick preview of articles when tapping on links.",
"Collapse tables",
"Automatically collapse tables in articles, such as infoboxes, references, and notes.",
"App theme",
"Light",
"Syncing",
"Reading list syncing",
"Sync reading lists across different devices by saving them to your Wikipedia account",
"Download reading list articles",
"Data usage",
"Download only over Wi-Fi"
],
"probe": false,
"strategy": "EARLY_STAGE",
"context": "exploration",
"native_branch": "Local Greedy",
"executor_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_d04ae609a94042e28f3ab00ddb284ca9.zip!device-output/executor.log:53781",
"observed_methods_until_next": 0,
"category_counts": {},
"inventory_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_d04ae609a94042e28f3ab00ddb284ca9.zip!device-output/native/sata-org.wikipedia-ape-sata-running-minutes-60/jev-audit/inputs/generated-3279.json"
},
{
"input_id": "input-3283",
"step": 617,
"version": 35,
"elapsed_s": 996.934,
"wall_time_ms": 1793991485980,
"next_input_wall_ms": 1793991486902,
"input_completed_wall_ms": 1793991486018,
"input_confirmed": true,
"action": "MODEL_CLICK android.widget.LinearLayout",
"action_type": "MODEL_CLICK",
"text": "",
"content_desc": "",
"resource_id": "",
"model_action_id": "g35a2320",
"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=\"androidx.recyclerview.widget.RecyclerView\"][@resource-id=\"org.wikipedia:id/recycler_view\"][@text=\"\"][@content-desc=\"\"][@index=2][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='true']/*[@class=\"android.widget.LinearLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=11][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false']",
"state_id": "g35s205",
"source_gui_id": 774,
"activity": "org.wikipedia.settings.SettingsActivity",
"activity_evidence": "exact source_gui_id transition receipt",
"labels": null,
"probe": false,
"strategy": "EARLY_STAGE",
"context": "exploration",
"native_branch": "Local Greedy",
"executor_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_d04ae609a94042e28f3ab00ddb284ca9.zip!device-output/executor.log:54003",
"observed_methods_until_next": 17,
"category_counts": {
"third_party": 15,
"app_domain": 2
},
"inventory_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_d04ae609a94042e28f3ab00ddb284ca9.zip!device-output/native/sata-org.wikipedia-ape-sata-running-minutes-60/jev-audit/inputs/generated-3284.json"
},
{
"input_id": "input-3288",
"step": 618,
"version": 35,
"elapsed_s": 997.856,
"wall_time_ms": 1793991486902,
"next_input_wall_ms": 1793991487952,
"input_completed_wall_ms": 1793991486987,
"input_confirmed": true,
"action": "MODEL_CLICK org.wikipedia:id/switchWidget",
"action_type": "MODEL_CLICK",
"text": "",
"content_desc": "",
"resource_id": "org.wikipedia:id/switchWidget",
"model_action_id": "g35a2325",
"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=\"androidx.recyclerview.widget.RecyclerView\"][@resource-id=\"org.wikipedia:id/recycler_view\"][@text=\"\"][@content-desc=\"\"][@index=2][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='true']/*[@class=\"android.widget.LinearLayout\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=3][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.Switch\"][@resource-id=\"org.wikipedia:id/switchWidget\"][@text=\"\"][@content-desc=\"\"][@index=2][@enabled='true'][@clickable='true'][@checkable='true'][@long-clickable='false'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='true'][@long-clickable='false'][@scrollable='false']",
"state_id": "g35s205",
"source_gui_id": 775,
"activity": "org.wikipedia.settings.SettingsActivity",
"activity_evidence": "GUI receipt",
"labels": [
"#f1409233",
"Settings",
"General",
"Wikipedia languages",
"italiano, 中文(中国大陆), français, English",
"Explore Feed",
"Customize the Explore feed",
"Show link previews",
"Show a quick preview of articles when tapping on links.",
"Collapse tables",
"Automatically collapse tables in articles, such as infoboxes, references, and notes.",
"App theme",
"Light",
"Syncing",
"Reading list syncing",
"Sync reading lists across different devices by saving them to your Wikipedia account",
"Download reading list articles",
"Data usage",
"Download only over Wi-Fi"
],
"probe": false,
"strategy": "EARLY_STAGE",
"context": "exploration",
"native_branch": "Local Greedy",
"executor_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_d04ae609a94042e28f3ab00ddb284ca9.zip!device-output/executor.log:54103",
"observed_methods_until_next": 1,
"category_counts": {
"third_party": 1
},
"inventory_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_d04ae609a94042e28f3ab00ddb284ca9.zip!device-output/native/sata-org.wikipedia-ape-sata-running-minutes-60/jev-audit/inputs/generated-3291.json"
},
{
"input_id": "input-3297",
"step": 619,
"version": 35,
"elapsed_s": 998.906,
"wall_time_ms": 1793991487952,
"next_input_wall_ms": 1793991489329,
"input_completed_wall_ms": 1793991487987,
"input_confirmed": true,
"action": "MODEL_CLICK android.widget.LinearLayout",
"action_type": "MODEL_CLICK",
"text": "",
"content_desc": "",
"resource_id": "",
"model_action_id": "g35a2317",
"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=\"androidx.recyclerview.widget.RecyclerView\"][@resource-id=\"org.wikipedia:id/recycler_view\"][@text=\"\"][@content-desc=\"\"][@index=2][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='true']/*[@class=\"android.widget.LinearLayout\"][@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": "g35s205",
"source_gui_id": 776,
"activity": "org.wikipedia.settings.SettingsActivity",
"activity_evidence": "GUI receipt",
"labels": [
"#f1409233",
"Settings",
"General",
"Wikipedia languages",
"italiano, 中文(中国大陆), français, English",
"Explore Feed",
"Customize the Explore feed",
"Show link previews",
"Show a quick preview of articles when tapping on links.",
"Collapse tables",
"Automatically collapse tables in articles, such as infoboxes, references, and notes.",
"App theme",
"Light",
"Syncing",
"Reading list syncing",
"Sync reading lists across different devices by saving them to your Wikipedia account",
"Download reading list articles",
"Data usage",
"Download only over Wi-Fi"
],
"probe": false,
"strategy": "EARLY_STAGE",
"context": "exploration",
"native_branch": "Local Greedy",
"executor_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_d04ae609a94042e28f3ab00ddb284ca9.zip!device-output/executor.log:54203",
"observed_methods_until_next": 2,
"category_counts": {
"app_domain": 2
},
"inventory_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_d04ae609a94042e28f3ab00ddb284ca9.zip!device-output/native/sata-org.wikipedia-ape-sata-running-minutes-60/jev-audit/inputs/generated-3298.json"
},
{
"input_id": "input-3302",
"step": 620,
"version": 35,
"elapsed_s": 1000.283,
"wall_time_ms": 1793991489329,
"next_input_wall_ms": 1793991490253,
"input_completed_wall_ms": 1793991489351,
"input_confirmed": true,
"action": "MODEL_CLICK Log in",
"action_type": "MODEL_CLICK",
"text": "Log in",
"content_desc": "",
"resource_id": "android:id/button1",
"model_action_id": "g35a2329",
"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.widget.ScrollView\"][@resource-id=\"org.wikipedia:id/buttonPanel\"][@text=\"\"][@content-desc=\"\"][@index=2][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.Button\"][@resource-id=\"android:id/button1\"][@text=\"Log in\"][@content-desc=\"\"][@index=1][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false']",
"state_id": "g35s206",
"source_gui_id": 780,
"activity": "org.wikipedia.settings.SettingsActivity",
"activity_evidence": "exact source_gui_id transition receipt",
"labels": null,
"probe": false,
"strategy": "EARLY_STAGE",
"context": "exploration",
"native_branch": "Local Greedy",
"executor_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_d04ae609a94042e28f3ab00ddb284ca9.zip!device-output/executor.log:54303",
"observed_methods_until_next": 18,
"category_counts": {
"app_domain": 3,
"third_party": 15
},
"inventory_ref": "[WORKSPACE]/experiments/guitaboo-5app-1rep-baseline-comparison-20261107/analysis/evidence-zips/run_d04ae609a94042e28f3ab00ddb284ca9.zip!device-output/native/sata-org.wikipedia-ape-sata-running-minutes-60/jev-audit/inputs/generated-3303.json"
}
],
"lifecycle": {
"DECISION_PROBE": {
"event": "DECISION_PROBE",
"step": 615,
"monotonic_ns": 1880526701383554,
"wall_time_ms": 1793991479798,
"abstraction_version": 33,
"state_id": "g8s93",
"model_action_id": "g8a974",
"entry_id": "semantic-6-c1",
"request_id": "semantic-6",
"candidate_id": "c1",
"confidence": 0.9333664178848267,
"choice": "PROMOTE",
"parsed_outcome": "PROBE",
"ledger_status": "STAGED",
"decision_role": "candidate_decision",
"input_signature": "064c67207beafddfb913a427a84fd5bd83310e0777d8354fe1f33c0d4778bc9d",
"concrete_identity": "f08fca80599c16eb18b0a6ce843b6b4f93e76f1823f33b31edf06defb0360e0e",
"decision_scope": "3d3926431bc93bde8cbf490a5c09a2a9ac33f948d32beb3e48d7ed726162c382",
"representative_model_action_id": "PROMOTE",
"decision_request_id": "semantic-6",
"aggregation_policy": "exploratory-top3-v1",
"total_history": 2,
"history_complete": true,
"unknown_mapping_count": 0,
"recoverable_history_count": 2,
"selected_history": 2,
"comparison_count": 2,
"same_count": 0,
"different_count": 2,
"insufficient_count": 0,
"trusted_same_count": 0,
"trusted_different_count": 2,
"low_confidence_count": 0,
"full_history_compared": true,
"exploratory": false,
"_line": 1533
},
"SEMANTIC_DECISION_STORED": {
"event": "SEMANTIC_DECISION_STORED",
"step": 615,
"monotonic_ns": 1880526702107285,
"wall_time_ms": 1793991479798,
"abstraction_version": 33,
"state_id": "g8s93",
"model_action_id": "g8a974",
"entry_id": "semantic-6-c1",
"request_id": "semantic-6",
"candidate_id": "c1",
"decision_role": "candidate_decision",
"ledger_status": "PROBE",
"input_signature": "064c67207beafddfb913a427a84fd5bd83310e0777d8354fe1f33c0d4778bc9d",
"input_fingerprint": "c7af288ea63ab3c21e8c1fc600d85d75ccdafcc9bebd085e0fe7a266e585dedb",
"concrete_identity": "f08fca80599c16eb18b0a6ce843b6b4f93e76f1823f33b31edf06defb0360e0e",
"decision_scope": "3d3926431bc93bde8cbf490a5c09a2a9ac33f948d32beb3e48d7ed726162c382",
"_line": 1535
},
"PROBE_BOUND": {
"event": "PROBE_BOUND",
"step": 615,
"monotonic_ns": 1880526710431789,
"wall_time_ms": 1793991479807,
"abstraction_version": 33,
"state_id": "g8s93",
"model_action_id": "g8a974",
"entry_id": "semantic-6-c1",
"request_id": "semantic-6",
"candidate_id": "c1",
"confidence": 0.9333664178848267,
"choice": "PROMOTE",
"source": "semantic_sync",
"input_signature": "064c67207beafddfb913a427a84fd5bd83310e0777d8354fe1f33c0d4778bc9d",
"decision_scope": "3d3926431bc93bde8cbf490a5c09a2a9ac33f948d32beb3e48d7ed726162c382",
"concrete_identity": "f08fca80599c16eb18b0a6ce843b6b4f93e76f1823f33b31edf06defb0360e0e",
"_line": 1537
},
"PROBE_SELECTED": {
"event": "PROBE_SELECTED",
"step": 615,
"monotonic_ns": 1880526710481283,
"wall_time_ms": 1793991479807,
"abstraction_version": 33,
"state_id": "g8s93",
"model_action_id": "g8a974",
"entry_id": "semantic-6-c1",
"request_id": "semantic-6",
"candidate_id": "c1",
"confidence": 0.9333664178848267,
"choice": "PROMOTE",
"source": "semantic_sync",
"_line": 1538
},
"PROBE_INPUT_GENERATED": {
"event": "PROBE_INPUT_GENERATED",
"step": 615,
"monotonic_ns": 1880526765817002,
"wall_time_ms": 1793991479862,
"abstraction_version": 33,
"state_id": null,
"model_action_id": null,
"entry_id": "semantic-6-c1",
"request_id": "semantic-6",
"candidate_id": "c1",
"event_count": 2,
"_line": 1541
},
"PROBE_INPUT_COMPLETED": {
"event": "PROBE_INPUT_COMPLETED",
"step": 615,
"monotonic_ns": 1880526788409326,
"wall_time_ms": 1793991479885,
"abstraction_version": 33,
"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-6-c1",
"request_id": "semantic-6",
"candidate_id": "c1",
"_line": 1542
},
"PROBE_EXECUTED": {
"event": "PROBE_EXECUTED",
"step": 616,
"monotonic_ns": 1880531568462245,
"wall_time_ms": 1793991484665,
"abstraction_version": 35,
"state_id": "g8s93",
"model_action_id": "g8a974",
"entry_id": "semantic-6-c1",
"request_id": "semantic-6",
"candidate_id": "c1",
"confidence": 0.9333664178848267,
"choice": "PROMOTE",
"transition_id": "g35e519:610",
"target_state": "g35s205",
"input_confirmed": true,
"_line": 1546
}
},
"selection_at_execution": {
"event": "SELECTION_DECISION",
"step": 615,
"monotonic_ns": 1880526710882426,
"wall_time_ms": 1793991479807,
"abstraction_version": 33,
"state_id": "g8s93",
"model_action_id": "g8a974",
"snapshot_reason": "selection",
"state_visits": 5,
"state_first_seen": 288,
"state_last_seen": 615,
"state_saturated": false,
"state_saturation": 0.6666667,
"native_state_saturated": false,
"native_unsaturated_model_action_count": 1,
"model_action_count": 3,
"enabled_valid_action_count": 3,
"unsaturated_model_action_count": 1,
"unvisited_model_action_count": 1,
"effective_unvisited_model_action_count": 1,
"effective_state_saturated": false,
"local_probe_action_count": 0,
"navigation_action_count": 1,
"enabled_valid_unvisited_action_count": 1,
"unvisited_model_action_ids": "g8a976",
"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": 2,
"selected_action_fingerprint": "type=MODEL_CLICK|activity=org.wikipedia.main.MainActivity|class=android.widget.TextView|text=Settings|resource_id=|bounds=168,2119,1038,2176",
"selected_resolved_node_count": 3,
"_line": 1540
}
}四、是否值得PROMOTE
保留Native输入/Activity历史与本步GUI共同支持此前未尝试的独立功能入口;是可证明的收益下界。
疑似主要环节:NONE_IDENTIFIED;wire关系审查:DISTINCT_COMPARATORS_VALID。
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