- title
- SRBC Theory Validation Program — Round 12:Conflict Resolution / Clarification Optimization
- author
- Neo.K with Aletheia (GPT-5.6 Sol)
- institution
- EveMissLab / 一言諾科技有限公司
- version
- v0.1
- date
- 2026-09-23
- language
- zh-TW
- document_type
- Clarification Planning / Conflict Resolution Validation Report
- status
- Round 12 completed
SRBC Theory Validation Program — Round 12
Conflict Resolution / Clarification Optimization
作者: Neo.K with Aletheia (GPT-5.6 Sol)
機構: EveMissLab / 一言諾科技有限公司
日期: 2026-09-23
版本: v0.1
Canonical Source Note
本報告以 UTF-8 Markdown 保存;數學 source 僅使用 $...$ 與 $$...$$。
輸入是 Round 11 的 8000 個 three-way merge / conflict cases。
本輪不是再判「有沒有 conflict」,而是問:
並同時區分:
- query resolution;
- canonical semantic resolution。
0. 第一個修正:不能強迫所有 Clarification 都以 QRC 為終點
Round 11 dependency conflicts 中有:
案例的合法 resolution outcome 包含:
如果 optimizer 的成功條件固定是:
它會傾向要求額外假設,直到硬擠出數值。
這違反 SRBC 自己的原則。
因此 Round 12 改成:
也就是:
能確定 query 的合法 resolution outcome 即可。
1. Undef Planning Tag
為了做 decision tree,可以定義:
或:
但:
只是 resolution-planning label。
它不是把 undefined 偷塞回:
因此:
仍然成立。
2. 8000 Cases
各類成本:
| class | n | expected query-resolution cost | expected semantic-resolution cost | minimax query cost | resolve-all cost |
|---|---|---|---|---|---|
| auto_disjoint | 1000 | 0.000 | 0.000 | 0.000 | 0.000 |
| same_intent | 1000 | 0.000 | 0.000 | 0.000 | 0.000 |
| query_equivalent_conflict | 1000 | 0.000 | 1.000 | 0.000 | 1.000 |
| query_sensitive_conflict | 1000 | 1.000 | 1.000 | 1.000 | 1.000 |
| dependency_interaction | 1000 | 1.157 | 1.667 | 1.236 | 2.000 |
| evidence_conflict | 1000 | 0.000 | 1.000 | 0.000 | 1.000 |
| nuisance_conflict | 1000 | 0.000 | 1.000 | 0.000 | 1.000 |
| root_conflict | 1000 | 0.000 | 1.000 | 0.000 | 1.000 |
最明顯的是:
Query-equivalent semantic conflict
但:
Evidence / metadata / root conflict
同樣:
query 已經閉合,不必為了回答當前問題追問。
3. Query-Sensitive Conflict
兩 branch:
只要問一個 distinguishing semantic question:
semantic identity 也同樣需要一次:
4. Dependency Interaction
candidate worlds:
兩個 atomic questions:
- A change 是否 intended?
- B change 是否 intended?
Round 11 分兩種 pattern。
QDU Pattern
764 cases:
只要問:
A / parent change 是否 intended?
即可直接知道:
- yes → undefined;
- no → branch B answer。
因此:
但如果目標是找唯一 semantic world,平均仍需:
Three-Unique Pattern
236 cases:
三個 worlds 都有不同 defined outcome。
因此 uniform prior / unit-cost 下:
5. Dependency Aggregate
1000 dependency cases:
expected query-resolution cost:
minimax worst-case average:
semantic resolution:
expected,worst-case:
所以 query-directed clarification 確實能利用:
而不必硬分開它們。
6. Conflict Set 的總成本
只看真正 unresolved / preserved-conflict 六類,共:
cases。
問完所有 conflict dimensions
平均:
要唯一 semantic branch
adaptive expected cost:
只為當前 query 取得 resolution closure
adaptive expected cost:
相對 resolve-all 減少:
相對 semantic-resolution 減少:
7. Branch EIG 會讓 Query-Neutral Conflict 看起來值得問
本輪有:
個 query-neutral preserved conflicts:
- query-equivalent semantic;
- evidence;
- metadata;
- root identity。
branch identity 尚未確定,因此:
distinguishing question 也有:
但當前 query:
因此:
所以:
8. Dependency QDU Pattern 的 EIG
uniform three-world prior:
兩個 questions 的 branch EIG 都約:
所以 branch-EIG 無法區分誰比較適合當前 query。
但 resolution EIG:
對 parent question:
bits。
對 child question只有:
bits。
因此 query-relative information gain 會明確優先問 parent。
9. Uniform Prior / Unit Cost
在本 Round 11 benchmark 的 candidate questions 下,真正需要 clarification 的:
cases 中,
greedy:
和 exact dynamic programming:
相同。
但這只是這個特殊小型結構。
10. EIG / Cost 不是 Exact Optimizer
本輪進一步隨機化:
- branch prior;
- question cost。
prior 用 synthetic random distributions;
question cost 在約:
上 log-uniform。
這些都是 benchmark input,不是自然 prior,也不是人類實測成本。
結果:
| pattern | trials | greedy suboptimal | avg regret when wrong | max regret |
|---|---|---|---|---|
| QDU_PATTERN | 100,000 | 8.20% | 14.53% | 131.10% |
| THREE_UNIQUE | 100,000 | 11.68% | 9.24% | 80.39% |
所以:
不能被定義成:
它只是 heuristic。
11. Exact DP
小 branch family 應直接解:
stop condition:
對 query resolution:
對 semantic resolution:
這才是真正的 minimum expected clarification cost。
12. 無 Prior 時
如果沒有:
不應偷偷假設 uniform。
本輪定義:
這給 minimax clarification cost。
dependency family 的平均 minimax query cost:
13. Semantic Conflict 不一定要問
Round 11 的:
QUERY_EQUIVALENT_CONFLICT
EVIDENCE_CONFLICT
METADATA_CONFLICT
ROOT_IDENTITY_CONFLICT
對目前 query 全部:
runtime 可以:
- 保留 conflict artifact;
- 直接回答 query;
- future query 需要時再 reopen。
這正是 delayed commitment 在 merge runtime 的版本。
14. Canonical Merge 仍然可以需要 Clarification
如果使用者的真正 task 是:
我要一份唯一 canonical source / evidence / semantic state。
那目標不是 query resolution,而是:
所以同一 conflict:
這兩個 cost 不能混報。
15. 本輪對 SRBC-05 的修正
SRBC-05 原來的 clarification priority:
仍可做 heuristic。
EIG 版本:
也可做 heuristic。
但 exact 應由:
- DP;
- search;
- optimization;
- formal branch elimination;
計算。
不能用局部 score 直接冒充 global minimum。
16. Prior Laundering 再次被阻止
如果沒有 branch prior:
就不能因方便寫:
然後把 EIG ranking 說成「最理性」。
Round 12 所有 uniform-prior 數字都明確標:
17. Clarification 本質是 Partition Operator
一個問題不是只有字串:
Which rule did you mean?
正式 artifact 是:
每個 response:
對應:
所以 clarification planner 可以直接跑:
- expected elimination;
- resolution EIG;
- minimax cost;
- exact DP。
18. 本輪沒有證明什麼
沒有證明:
- 人類 clarification cost 真的是 1;
- 人類 branch prior 是 uniform;
- EIG 在自然語言對話的心理成本準確;
- synthetic atomic question 能直接變成最佳人類問句;
- 大型 branch space 的 exact DP 可實務擴展。
所以這輪是:
19. 下一輪
Round 13 最自然就是:
因為現在的 clarification response 都是假設 deterministic / truthful。
下一輪可以主動加入:
- 使用者答錯;
- 模糊回答;
- 部分回答;
- 改口;
- refusal;
- confidence;
- contradictory clarification;
- question fatigue cost;
- repeated-question consistency。
然後測:
和:
何時應該分開。
附錄 A:Class Costs
| class | n | expected query cost | expected semantic cost | minimax query cost | resolve-all |
|---|---|---|---|---|---|
| auto_disjoint | 1000 | 0.000 | 0.000 | 0.000 | 0.000 |
| same_intent | 1000 | 0.000 | 0.000 | 0.000 | 0.000 |
| query_equivalent_conflict | 1000 | 0.000 | 1.000 | 0.000 | 1.000 |
| query_sensitive_conflict | 1000 | 1.000 | 1.000 | 1.000 | 1.000 |
| dependency_interaction | 1000 | 1.157 | 1.667 | 1.236 | 2.000 |
| evidence_conflict | 1000 | 0.000 | 1.000 | 0.000 | 1.000 |
| nuisance_conflict | 1000 | 0.000 | 1.000 | 0.000 | 1.000 |
| root_conflict | 1000 | 0.000 | 1.000 | 0.000 | 1.000 |
附錄 B:Random Prior / Cost Stress
| pattern | trials | greedy suboptimal | avg regret when wrong | max regret |
|---|---|---|---|---|
| QDU_PATTERN | 100,000 | 8.20% | 14.53% | 131.10% |
| THREE_UNIQUE | 100,000 | 11.68% | 9.24% | 80.39% |
附錄 C:Machine Results
{
"round": "SRBC Theory Validation Round 12",
"engine_revision": "v0.12-resolution-closure",
"cases": 8000,
"class_summary": {
"auto_disjoint": {
"n": 1000,
"avg_query_expected_cost": 0.0,
"avg_semantic_expected_cost": 0.0,
"avg_query_worst_cost": 0.0,
"avg_semantic_worst_cost": 0.0,
"avg_resolve_all_cost": 0.0,
"avg_greedy_query_eig_cost": 0.0
},
"same_intent": {
"n": 1000,
"avg_query_expected_cost": 0.0,
"avg_semantic_expected_cost": 0.0,
"avg_query_worst_cost": 0.0,
"avg_semantic_worst_cost": 0.0,
"avg_resolve_all_cost": 0.0,
"avg_greedy_query_eig_cost": 0.0
},
"query_equivalent_conflict": {
"n": 1000,
"avg_query_expected_cost": 0.0,
"avg_semantic_expected_cost": 1.0,
"avg_query_worst_cost": 0.0,
"avg_semantic_worst_cost": 1.0,
"avg_resolve_all_cost": 1.0,
"avg_greedy_query_eig_cost": 0.0
},
"query_sensitive_conflict": {
"n": 1000,
"avg_query_expected_cost": 1.0,
"avg_semantic_expected_cost": 1.0,
"avg_query_worst_cost": 1.0,
"avg_semantic_worst_cost": 1.0,
"avg_resolve_all_cost": 1.0,
"avg_greedy_query_eig_cost": 1.0
},
"dependency_interaction": {
"n": 1000,
"avg_query_expected_cost": 1.1573333333333324,
"avg_semantic_expected_cost": 1.6666666666666865,
"avg_query_worst_cost": 1.236,
"avg_semantic_worst_cost": 2.0,
"avg_resolve_all_cost": 2.0,
"avg_greedy_query_eig_cost": 1.1573333333333324
},
"evidence_conflict": {
"n": 1000,
"avg_query_expected_cost": 0.0,
"avg_semantic_expected_cost": 1.0,
"avg_query_worst_cost": 0.0,
"avg_semantic_worst_cost": 1.0,
"avg_resolve_all_cost": 1.0,
"avg_greedy_query_eig_cost": 0.0
},
"nuisance_conflict": {
"n": 1000,
"avg_query_expected_cost": 0.0,
"avg_semantic_expected_cost": 1.0,
"avg_query_worst_cost": 0.0,
"avg_semantic_worst_cost": 1.0,
"avg_resolve_all_cost": 1.0,
"avg_greedy_query_eig_cost": 0.0
},
"root_conflict": {
"n": 1000,
"avg_query_expected_cost": 0.0,
"avg_semantic_expected_cost": 1.0,
"avg_query_worst_cost": 0.0,
"avg_semantic_worst_cost": 1.0,
"avg_resolve_all_cost": 1.0,
"avg_greedy_query_eig_cost": 0.0
}
},
"conflict_set": {
"cases": 6000,
"avg_query_resolution_expected_cost": 0.3595555555555556,
"avg_semantic_resolution_expected_cost": 1.1111111111111112,
"avg_resolve_all_cost": 1.1666666666666667,
"query_vs_resolve_all_reduction": 0.6918095238095239,
"query_vs_semantic_resolution_reduction": 0.6764
},
"greedy_query_eig": {
"active_query_clarification_cases": 2000,
"matches_exact_dp_under_uniform_unit_cost": 2000,
"failures": 0,
"query_neutral_cases_where_branch_eig_positive_but_resolution_eig_zero": 4000
},
"dependency_interaction": {
"cases": 1000,
"avg_uniform_expected_resolution_cost": 1.1573333333333333,
"avg_minimax_worst_case_cost": 1.236,
"eig_patterns": [
{
"pattern": "QDU_PATTERN",
"question_scores": [
[
"ask_A_change",
0.918296,
0.918296
],
[
"ask_B_change",
0.251629,
0.918296
]
],
"count": 764
},
{
"pattern": "THREE_UNIQUE",
"question_scores": [
[
"ask_A_change",
0.918296,
0.918296
],
[
"ask_B_change",
0.918296,
0.918296
]
],
"count": 236
}
]
},
"prior_cost_stress": {
"explicit_note": "Priors and question costs are synthetic benchmark inputs, not natural priors or measured human costs.",
"QDU_PATTERN": {
"n": 100000,
"greedy_suboptimal": 8196,
"max_relative_regret": 1.311015936140403,
"suboptimal_rate": 0.08196,
"avg_relative_regret_when_suboptimal": 0.14529424714734357
},
"THREE_UNIQUE": {
"n": 100000,
"greedy_suboptimal": 11685,
"max_relative_regret": 0.8038866550313561,
"suboptimal_rate": 0.11685,
"avg_relative_regret_when_suboptimal": 0.09239126242904895
}
},
"core_findings": {
"qrc_is_not_only_legal_closure_target": true,
"resolution_outcome_variable_includes_undefined_tag_for_planning_only": true,
"undefined_tag_is_not_promoted_into_answer_domain": true,
"semantic_merge_cost_separate_from_query_resolution_cost": true,
"eig_requires_declared_prior": true,
"eig_per_cost_not_globally_optimal": true,
"without_prior_use_minimax_or_bounds": true
}
}
附錄 D:Artifacts
SRBC_Theory_Validation_Round12_Report_v0.1_2026-09-23.mdSRBC_Core_Patch_v0.12_2026-09-23.mdclarification_optimizer_protocol_v012.yamlround12_clarification_optimizer.pyround12_eig_stress.pyround12_replay.pyresults_round12.jsonclarification_cases_round12.jsonlmerge_cases_round11.jsonlvalidation.json