feat: 诊断(任务书 18 第一块):诊断数学、四种提交、一次运行跑多个实验、账本与材料、flow 诊断各步

消融默认关,关掉时解释阶段一并跳过;选诊断实验用信息价值减成本。
eval/diagnosis/research.json 为第三块配置。vocab 字段说明的出口文字随提示词一起改,见下一次提交的 prompts/ 与同文件改动(本次含在内)。

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-05 10:36:20 -04:00
parent f39f8410e7
commit 852600df02
69 changed files with 6607 additions and 214 deletions
+2 -1
View File
@@ -36,6 +36,7 @@ export const study: StudyFacts = {
lambda: 0.1,
totalRuns: 10,
proposalLimit: 2,
diagnosisExperimentLimit: 2,
factorLimit: 3,
metrics: [
{ id: "sum-of-radii", layer: "final", meaning: "半径和", unit: "无", direction: "maximize", howMeasured: "校验器", missing: "invalidateRun" },
@@ -114,7 +115,7 @@ export class Writer {
decision(decision: string, round: number, input: unknown, output: unknown): void {
this.l.append("decision", { decision, round, rule: "test", ruleVersion: 1, params: null, seed: null, input: input as never, output: output as never });
}
run(run: string, purpose: "baseline" | "forward" | "ablation", round: number, object: string | null, j: JudgedResult): void {
run(run: string, purpose: "baseline" | "forward" | "ablation" | "diagnosis", round: number, object: string | null, j: JudgedResult | null): void {
this.l.append("runPlanned", { run, purpose, round, object, definition });
this.l.append("runStarted", { run });
this.l.append("runResult", { run, process: exited, judged: j });