wikipedia STARTLUX step1698 View user page
run_d04ae609a94042e28f3ab00ddb284ca9 · 第45.83分钟 · 请求step1698 / 决策step1698 / 执行step1698 · UNKNOWN · 证据INSUFFICIENT_FOR_GLOBAL_NOVELTY · 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（p2 对step1153=0.709111），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 g50s319 / g50a3563；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 / 1149 | View user contributions | DIFFERENT_OPERATION | 0.43260407 | False |
| p2 / 1153 | View user contributions | DIFFERENT_OPERATION | 0.70911059 | 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": 1149,
"history_input_id": "input-6074",
"choice": "DIFFERENT_OPERATION",
"confidence": 0.4326040744781494,
"probabilities": {
"SAME_OPERATION": 0.33322736620903015,
"DIFFERENT_OPERATION": 0.6217360496520996,
"INSUFFICIENT_EVIDENCE": 0.04503656178712845
},
"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.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": 0.4326040744781494,
"probabilities": {
"SAME_OPERATION": 0.33322736620903015,
"DIFFERENT_OPERATION": 0.6217360496520996,
"INSUFFICIENT_EVIDENCE": 0.04503656178712845
}
},
"model_visible_history": {
"class": "android.widget.TextView",
"resource_id": "org.wikipedia:id/title",
"text": "View user contributions",
"content_desc": "",
"enabled": true,
"clickable": true,
"long_clickable": false,
"scrollable": false,
"checked": false,
"selected": false,
"action_type": "MODEL_CLICK",
"index": 2,
"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.ListView\"][@resource-id=\"\"][@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.TextView\"][@resource-id=\"org.wikipedia:id/title\"][@text=\"View use\"][@content-desc=\"\"][@index=2][@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": "g50a3563",
"source_state_id": "g50s319",
"bounds": [
189,
2224,
657,
2281
],
"source_page_id": "page2",
"target_subtree": [
{
"class": "android.widget.TextView",
"resource_id": "org.wikipedia:id/title",
"text": "View user contributions",
"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": "",
"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": 1402,
"source_gui_timestamp": 1149,
"current_state": "g50s319",
"current_model_action": "g50a3563",
"current_version": 74,
"input_confirmed": true,
"confirmation_basis": "live confirmedInputs before review; not function completion",
"attributes_recoverable": true
}
},
{
"pair_id": "p2",
"history_id": "h2",
"history_step": 1153,
"history_input_id": "input-6098",
"choice": "DIFFERENT_OPERATION",
"confidence": 0.7091105878353119,
"probabilities": {
"SAME_OPERATION": 0.1345343440771103,
"DIFFERENT_OPERATION": 0.8060737252235413,
"INSUFFICIENT_EVIDENCE": 0.059391919523477554
},
"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": 0.7091105878353119,
"probabilities": {
"SAME_OPERATION": 0.1345343440771103,
"DIFFERENT_OPERATION": 0.8060737252235413,
"INSUFFICIENT_EVIDENCE": 0.059391919523477554
}
},
"model_visible_history": {
"class": "android.widget.TextView",
"resource_id": "org.wikipedia:id/title",
"text": "View user contributions",
"content_desc": "",
"enabled": true,
"clickable": true,
"long_clickable": false,
"scrollable": false,
"checked": false,
"selected": false,
"action_type": "MODEL_CLICK",
"index": 2,
"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.ListView\"][@resource-id=\"\"][@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.TextView\"][@resource-id=\"org.wikipedia:id/title\"][@text=\"View use\"][@content-desc=\"\"][@index=2][@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": "g50a3563",
"source_state_id": "g50s319",
"bounds": [
189,
2224,
657,
2281
],
"source_page_id": "page3",
"target_subtree": [
{
"class": "android.widget.TextView",
"resource_id": "org.wikipedia:id/title",
"text": "View user contributions",
"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": "",
"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": 1407,
"source_gui_timestamp": 1153,
"current_state": "g50s319",
"current_model_action": "g50a3563",
"current_version": 74,
"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
View user page与View user contributions是不同入口；实际为Secretagentgex不存在的用户页404，44个B首次方法是错误处理观测，不能当作用户页加载成功或首次用户页功能的证明。
等价历史是否送入Provider wire：UNKNOWN；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。
NA：没有足以可靠裁定全局首次或重复的已核实等价历史。不能把未检索到当成未执行。
三、Probe执行后发生什么
View user page 打开Secretagentgex的404错误页面，B窗口44首次方法；是错误处理，不是用户页加载成功。
Run内首次METHOD观察：完成后2秒=44，10秒=44，下一动作前B=44。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-9119",
"step": 1699,
"version": 75,
"elapsed_s": 2755.385,
"wall_time_ms": 1793993244431,
"next_input_wall_ms": 1793993245349,
"input_completed_wall_ms": 1793993244468,
"input_confirmed": true,
"action": "MODEL_CLICK Save",
"action_type": "MODEL_CLICK",
"text": "Save",
"content_desc": "Save",
"resource_id": "org.wikipedia:id/page_save",
"model_action_id": "g74a5088",
"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.drawerlayout.widget.DrawerLayout\"][@resource-id=\"org.wikipedia:id/navigation_drawer\"][@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/container_with_nav_trigger\"][@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/page_contents_container\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.TextView\"][@resource-id=\"org.wikipedia:id/page_save\"][@text=\"Save\"][@content-desc=\"Save\"][@index=3][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false']",
"state_id": "g74s448",
"source_gui_id": 2061,
"activity": "org.wikipedia.page.PageActivity",
"activity_evidence": "GUI receipt",
"labels": [
"#f1409233",
"Search Wikipedia",
"Show tabs",
"More options",
"Save",
"Language",
"Find in article",
"Theme",
"Contents",
"2",
"Wikipedia does not have a user page with this exact name. In general, this page should be created and edited by User:Secretagentgex. If in doubt, please verify that \"Secretagentgex\" exists.",
"Go back",
"Code: 404, URL: https://en.wikipedia.org/api/rest_v1/page/summary/User%3ASecretagentgex, title: , detail: "
],
"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:164952",
"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-9120.json"
},
{
"input_id": "input-9124",
"step": 1700,
"version": 75,
"elapsed_s": 2756.303,
"wall_time_ms": 1793993245349,
"next_input_wall_ms": 1793993246274,
"input_completed_wall_ms": 1793993245384,
"input_confirmed": true,
"action": "MODEL_CLICK #f1409233",
"action_type": "MODEL_CLICK",
"text": "#f1409233",
"content_desc": "Navigate up",
"resource_id": "",
"model_action_id": "g74a5085",
"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.drawerlayout.widget.DrawerLayout\"][@resource-id=\"org.wikipedia:id/navigation_drawer\"][@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/container_with_nav_trigger\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.ImageButton\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"Navigate up\"][@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": "g74s448",
"source_gui_id": 2062,
"activity": "org.wikipedia.page.PageActivity",
"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:165110",
"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-9125.json"
},
{
"input_id": "input-9129",
"step": 1701,
"version": 75,
"elapsed_s": 2757.228,
"wall_time_ms": 1793993246274,
"next_input_wall_ms": 1793993247187,
"input_completed_wall_ms": 1793993246301,
"input_confirmed": true,
"action": "MODEL_CLICK User:",
"action_type": "MODEL_CLICK",
"text": "User:",
"content_desc": "",
"resource_id": "org.wikipedia:id/search_src_text",
"model_action_id": "g64a4664",
"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.LinearLayout\"][@resource-id=\"org.wikipedia:id/search_container\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"androidx.appcompat.widget.LinearLayoutCompat\"][@resource-id=\"org.wikipedia:id/search_cab_view\"][@text=\"\"][@content-desc=\"\"][@index=1][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.AutoCompleteTextView\"][@resource-id=\"org.wikipedia:id/search_src_text\"][@text=\"User:\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='true'][@scrollable='false'][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='true'][@scrollable='false']",
"state_id": "g64s420",
"source_gui_id": 2063,
"activity": "org.wikipedia.search.SearchActivity",
"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:165224",
"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-9130.json"
},
{
"input_id": "input-9134",
"step": 1702,
"version": 75,
"elapsed_s": 2758.141,
"wall_time_ms": 1793993247187,
"next_input_wall_ms": 1793993248636,
"input_completed_wall_ms": 1793993247285,
"input_confirmed": true,
"action": "MODEL_CLICK android.view.ViewGroup",
"action_type": "MODEL_CLICK",
"text": "",
"content_desc": "",
"resource_id": "",
"model_action_id": "g64a4671",
"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.LinearLayout\"][@resource-id=\"org.wikipedia:id/search_container\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='true'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"androidx.recyclerview.widget.RecyclerView\"][@resource-id=\"org.wikipedia:id/search_results_list\"][@text=\"\"][@content-desc=\"\"][@index=5][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='true']/*[@class=\"android.view.ViewGroup\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"\"][@index=6][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='true'][@scrollable='false'][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='true'][@scrollable='false']",
"state_id": "g64s420",
"source_gui_id": 2064,
"activity": "org.wikipedia.search.SearchActivity",
"activity_evidence": "GUI receipt",
"labels": [
"#84c0168c",
"more",
"User:",
"Clear query",
"ENGLISH",
"RUSSIAN",
"ARABIC",
"User:Everedux",
"User:Bkissin",
"User:Johnuniq",
"User:Coolabahapple",
"User:Paul Erik",
"Wikipedia editor",
"User:Isabelle Belato",
"User:StuRat",
"User:NJA",
"User:Taggy McTaggerstein",
"User:Sjakkalle",
"User:NuclearWarfare",
"EN",
"RU",
"AR"
],
"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:165341",
"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-9137.json"
},
{
"input_id": "input-9143",
"step": 1703,
"version": 75,
"elapsed_s": 2759.59,
"wall_time_ms": 1793993248636,
"next_input_wall_ms": 1793993249959,
"input_completed_wall_ms": 1793993248667,
"input_confirmed": true,
"action": "MODEL_CLICK #f1409233",
"action_type": "MODEL_CLICK",
"text": "#f1409233",
"content_desc": "Navigate up",
"resource_id": "",
"model_action_id": "g7a746",
"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.drawerlayout.widget.DrawerLayout\"][@resource-id=\"org.wikipedia:id/navigation_drawer\"][@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/container_with_nav_trigger\"][@text=\"\"][@content-desc=\"\"][@index=0][@enabled='true'][@clickable='false'][@checkable='false'][@long-clickable='false'][@scrollable='false']/*[@class=\"android.widget.ImageButton\"][@resource-id=\"\"][@text=\"\"][@content-desc=\"Navigate up\"][@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": "g7s67",
"source_gui_id": 2065,
"activity": "org.wikipedia.page.PageActivity",
"activity_evidence": "GUI receipt",
"labels": [
"#f1409233",
"Search Wikipedia",
"Show tabs",
"More options",
"Save",
"Language",
"Find in article",
"Theme",
"Contents",
"1"
],
"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_d04ae609a94042e28f3ab00ddb284ca9.zip!device-output/executor.log:165459",
"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-9144.json"
}
],
"lifecycle": {
"DECISION_PROBE": {
"event": "DECISION_PROBE",
"step": 1698,
"monotonic_ns": 1882285863048179,
"wall_time_ms": 1793993238959,
"abstraction_version": 74,
"state_id": "g50s319",
"model_action_id": "g50a3563",
"entry_id": "semantic-32-c1",
"request_id": "semantic-32",
"candidate_id": "c1",
"confidence": 0.7091105878353119,
"choice": "PROMOTE",
"parsed_outcome": "PROBE",
"ledger_status": "STAGED",
"decision_role": "candidate_decision",
"input_signature": "fefbf3e06c98e76131fb7277113d0c717fc41942e482121d9f0c95e2c638dda9",
"concrete_identity": "8253fb59a3fe7f18e34bc4180d460565b1010f558cd5060b35042f6420361d59",
"decision_scope": "34072367442a8d9b9823768d6ee8f08afcd6432557029017b08f722b20b8a8b4",
"representative_model_action_id": "PROMOTE",
"decision_request_id": "semantic-32",
"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": 1,
"low_confidence_count": 1,
"full_history_compared": true,
"exploratory": false,
"_line": 4932
},
"SEMANTIC_DECISION_STORED": {
"event": "SEMANTIC_DECISION_STORED",
"step": 1698,
"monotonic_ns": 1882285863729612,
"wall_time_ms": 1793993238960,
"abstraction_version": 74,
"state_id": "g50s319",
"model_action_id": "g50a3563",
"entry_id": "semantic-32-c1",
"request_id": "semantic-32",
"candidate_id": "c1",
"decision_role": "candidate_decision",
"ledger_status": "PROBE",
"input_signature": "fefbf3e06c98e76131fb7277113d0c717fc41942e482121d9f0c95e2c638dda9",
"input_fingerprint": "ece13736572cfb1fc112287b18d256d3afb94cc1b391d5f56842736dc913106f",
"concrete_identity": "8253fb59a3fe7f18e34bc4180d460565b1010f558cd5060b35042f6420361d59",
"decision_scope": "34072367442a8d9b9823768d6ee8f08afcd6432557029017b08f722b20b8a8b4",
"_line": 4934
},
"PROBE_BOUND": {
"event": "PROBE_BOUND",
"step": 1698,
"monotonic_ns": 1882285871013666,
"wall_time_ms": 1793993238967,
"abstraction_version": 74,
"state_id": "g50s319",
"model_action_id": "g50a3563",
"entry_id": "semantic-32-c1",
"request_id": "semantic-32",
"candidate_id": "c1",
"confidence": 0.7091105878353119,
"choice": "PROMOTE",
"source": "semantic_sync",
"input_signature": "fefbf3e06c98e76131fb7277113d0c717fc41942e482121d9f0c95e2c638dda9",
"decision_scope": "34072367442a8d9b9823768d6ee8f08afcd6432557029017b08f722b20b8a8b4",
"concrete_identity": "8253fb59a3fe7f18e34bc4180d460565b1010f558cd5060b35042f6420361d59",
"_line": 4936
},
"PROBE_SELECTED": {
"event": "PROBE_SELECTED",
"step": 1698,
"monotonic_ns": 1882285871067883,
"wall_time_ms": 1793993238967,
"abstraction_version": 74,
"state_id": "g50s319",
"model_action_id": "g50a3563",
"entry_id": "semantic-32-c1",
"request_id": "semantic-32",
"candidate_id": "c1",
"confidence": 0.7091105878353119,
"choice": "PROMOTE",
"source": "semantic_sync",
"_line": 4937
},
"PROBE_INPUT_GENERATED": {
"event": "PROBE_INPUT_GENERATED",
"step": 1698,
"monotonic_ns": 1882285925001807,
"wall_time_ms": 1793993239021,
"abstraction_version": 74,
"state_id": null,
"model_action_id": null,
"entry_id": "semantic-32-c1",
"request_id": "semantic-32",
"candidate_id": "c1",
"event_count": 2,
"_line": 4940
},
"PROBE_INPUT_COMPLETED": {
"event": "PROBE_INPUT_COMPLETED",
"step": 1698,
"monotonic_ns": 1882285954870535,
"wall_time_ms": 1793993239051,
"abstraction_version": 74,
"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-32-c1",
"request_id": "semantic-32",
"candidate_id": "c1",
"_line": 4941
},
"PROBE_EXECUTED": {
"event": "PROBE_EXECUTED",
"step": 1699,
"monotonic_ns": 1882287201805043,
"wall_time_ms": 1793993240298,
"abstraction_version": 74,
"state_id": "g50s319",
"model_action_id": "g50a3563",
"entry_id": "semantic-32-c1",
"request_id": "semantic-32",
"candidate_id": "c1",
"confidence": 0.7091105878353119,
"choice": "PROMOTE",
"transition_id": "g74e1368:1685",
"target_state": "g74s448",
"input_confirmed": true,
"_line": 4943
}
},
"selection_at_execution": {
"event": "SELECTION_DECISION",
"step": 1698,
"monotonic_ns": 1882285871539311,
"wall_time_ms": 1793993238968,
"abstraction_version": 74,
"state_id": "g50s319",
"model_action_id": "g50a3563",
"snapshot_reason": "selection",
"state_visits": 3,
"state_first_seen": 1149,
"state_last_seen": 1698,
"state_saturated": false,
"state_saturation": 0.5,
"native_state_saturated": false,
"native_unsaturated_model_action_count": 1,
"model_action_count": 2,
"enabled_valid_action_count": 2,
"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": "g50a3564",
"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.page.edithistory.EditHistoryListActivity|class=android.widget.TextView|text=View use|resource_id=org.wikipedia:id/title|bounds=189,1834,657,1891",
"selected_resolved_node_count": 3,
"_line": 4939
}
}四、是否值得PROMOTE
无法可靠裁定相对整个Run决策前历史的功能新颖性。
疑似主要环节：PROBE_EXECUTION_OR_RESULT_EVIDENCE；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