feat: 研究规则 rules 模块（任务书 02）
rules 是纯计算，src/rules 共 1761 行：方法.md 第六部分的全部公式、第七部分的余额与扣次、4.2 的入口分配，以及种子与规则登记表。 预期值有三个来源：方法.md 的手算例；tests/fixtures/rules/ 下不看实现写的 Python 脚本；参考项目 calc15、calc14b 里与现行方法一致的部分。审阅做了两轮，每轮都换一个全新上下文的子 Agent，提出的问题都已修复或写明不修的理由。 用户确认的约定（原话"1–8 都同意"）：入池、采纳、消融中发现都用严格不等号；成本用 max(0, ĝ₀)；没测的格附"含它的最好组合"的净值；战绩在分数原值上判。三个数改为严格递增后，删掉了尖峰的全部专门处理（bfb96ba）。vocab 里 Range 的说明同步改为严格递增。 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,278 @@
|
||||
import assert from "node:assert/strict";
|
||||
import { createHash } from "node:crypto";
|
||||
import { test } from "node:test";
|
||||
import {
|
||||
ablationCellLimit,
|
||||
ablationCellMixture,
|
||||
assignEntries,
|
||||
authorShares,
|
||||
authorVsMerged,
|
||||
bitWidth,
|
||||
cellIndex,
|
||||
coverage,
|
||||
decisionSeed,
|
||||
disagreement,
|
||||
forwardBatchSize,
|
||||
forwardMixtures,
|
||||
personKnots,
|
||||
placement,
|
||||
runBalance,
|
||||
seededRandom,
|
||||
seededSample,
|
||||
surprise,
|
||||
trackRecord,
|
||||
worldBits,
|
||||
type Mixture,
|
||||
type Placement,
|
||||
type RunState,
|
||||
} from "../src/rules/index.ts";
|
||||
import { canonical } from "../src/vocab/index.ts";
|
||||
import { close, closeArray, loadFixture, range, scenarioPicker } from "./rules-fixtures-helpers.ts";
|
||||
|
||||
// info.json（方法.md 6.9、6.10 第 4 条，约定 31–34、37）与 misc.json（4.2、第七部分、约定 35–40），
|
||||
// 对照独立 Python 参考实现算出的预期值。
|
||||
|
||||
const info = loadFixture("info.json");
|
||||
const misc = loadFixture("misc.json");
|
||||
const pickInfo = scenarioPicker(info);
|
||||
const pickMisc = scenarioPicker(misc);
|
||||
/** 世界比特、分歧量：info.json tolerance.bits（理由见 tolerance.note）。 */
|
||||
const BITS_TOL: number = info.tolerance.bits;
|
||||
/** 事前把握、覆盖率等普通数值：info.json tolerance.abs。惊讶另按 tolerance.surprise 的公式（见 checkSurprise）。 */
|
||||
const TOL: number = info.tolerance.abs;
|
||||
|
||||
/** Python 用的落点、状态名 → rules 的代号。 */
|
||||
/** 正向一个候选的各人范围：[{researcher, range}]。 */
|
||||
const rangesOf = (rs: any[]) => rs.map((r) => ({ researcher: r.researcher as string, range: range(r.range) }));
|
||||
|
||||
const PLACEMENT: Record<string, Placement> = {
|
||||
below10: "belowQ1",
|
||||
from10to50: "q1ToQ5",
|
||||
from50to90: "q5ToQ9",
|
||||
above90: "aboveQ9",
|
||||
};
|
||||
|
||||
function checkSurprise(m: Mixture, b: number, width: number, v: number, e: any, what: string): void {
|
||||
const got = surprise(m, b, width, v);
|
||||
assert.equal(got.cell, e.bin, `${what}：格号`);
|
||||
close(got.prior, e.p, TOL, `${what}：事前把握`);
|
||||
if (e.status === "ok") {
|
||||
assert.equal(got.bits.status, "measured", `${what}：状态`);
|
||||
// 惊讶 = −log₂p；p 是两个浮点 F 值之差，带几个 2⁻⁵³ 的绝对误差，除以 p 后放大（info.json tolerance.surprise）。
|
||||
close((got.bits as { value: number }).value, e.surprise, TOL + 2 ** -50 / (e.p * Math.LN2), `${what}：惊讶`);
|
||||
} else {
|
||||
assert.equal(e.status, "priorZero");
|
||||
assert.equal(got.bits.status, "unmeasured", `${what}：事前把握为 0 时是明确状态`);
|
||||
}
|
||||
}
|
||||
|
||||
test("info.json bits_forward_r1_real", () => {
|
||||
const s = pickInfo.get("bits_forward_r1_real");
|
||||
const width = bitWidth(s.params.eps);
|
||||
close(width, s.params.delta, 0, "格宽 Δ");
|
||||
const ids = Object.keys(s.input.candidates);
|
||||
const raws = forwardMixtures(
|
||||
ids.map((id) => ({ ranges: rangesOf(s.input.candidates[id]) })),
|
||||
s.params.lambda,
|
||||
);
|
||||
ids.forEach((id, i) => close(worldBits(raws[i]!, s.input.b, width), s.expected.candidates[id].worldBits, BITS_TOL, `${id} 世界比特`));
|
||||
const c3 = ids.indexOf("r1-v1-c3");
|
||||
checkSurprise(raws[c3]!, s.input.b, width, s.input.actual["r1-v1-c3"], s.expected.candidates["r1-v1-c3"].surprise, "c3 惊讶");
|
||||
checkSurprise(raws[c3]!, s.input.b, width, s.input.farValue, s.expected.surpriseFarValue, "预留之外的实测");
|
||||
// 分歧量：正向一人一份范围，作者各不相同。
|
||||
const people = rangesOf(s.input.candidates["r1-v1-c3"]);
|
||||
const ranges = people.map((p) => p.range);
|
||||
const entries = people.map((p) => ({ id: p.researcher, author: p.researcher, range: p.range }));
|
||||
const e = s.expected.disagreementC3;
|
||||
close(disagreement(entries, s.input.b, width), e.disagreement, BITS_TOL, "c3 分歧量");
|
||||
// 分歧量的两项：等权平均后的比特、各人的比特（用 worldBits 在不掺预留的混合上算）。
|
||||
const avg: Mixture = ranges.map((r: any) => ({ weight: 1 / ranges.length, knots: personKnots(r) }));
|
||||
close(worldBits(avg, s.input.b, width), e.avgBits, BITS_TOL, "c3 平均后的比特");
|
||||
ranges.forEach((r: any, i: number) =>
|
||||
close(worldBits([{ weight: 1, knots: personKnots(r) }], s.input.b, width), e.eachBits[i], BITS_TOL, `c3 第 ${i} 人比特`),
|
||||
);
|
||||
});
|
||||
|
||||
test("info.json bits_ablation_cell_r1_p1", () => {
|
||||
const s = pickInfo.get("bits_ablation_cell_r1_p1");
|
||||
const width = bitWidth(s.params.eps);
|
||||
const entries = s.input.explanations.map((e: any) => ({ id: e.id as string, author: e.author as string, range: range(e.range) }));
|
||||
const m = ablationCellMixture(entries, s.params.lambda);
|
||||
close(worldBits(m, s.input.b, width), s.expected.worldBits, BITS_TOL, "世界比特");
|
||||
checkSurprise(m, s.input.b, width, s.input.actual, s.expected.surprise, "惊讶");
|
||||
// 平均后的比特：研究者等权、同人几条平分，不掺预留（两边读法相同）。
|
||||
const shares = authorShares(entries.map((e: any) => e.author));
|
||||
const avg: Mixture = entries.map((e: any, i: number) => ({ weight: shares[i]!, knots: personKnots(e.range) }));
|
||||
close(worldBits(avg, s.input.b, width), s.expected.avgBits, BITS_TOL, "平均后的比特");
|
||||
// 各人的比特：每人几条解释等权平均成"这个人的折线"（6.9，只量人与人之间的差别）。
|
||||
const authors = [...new Set(entries.map((e: any) => e.author as string))];
|
||||
authors.forEach((a, i) => {
|
||||
const own = entries.filter((e: any) => e.author === a);
|
||||
const person: Mixture = own.map((e: any) => ({ weight: 1 / own.length, knots: personKnots(e.range) }));
|
||||
close(worldBits(person, s.input.b, width), s.expected.eachPersonBits[i], BITS_TOL, `${a} 的比特`);
|
||||
});
|
||||
close(disagreement(entries, s.input.b, width), s.expected.disagreement, BITS_TOL, "分歧量");
|
||||
});
|
||||
|
||||
test("info.json bits_minimize_bin_edges", () => {
|
||||
const s = pickInfo.get("bits_minimize_bin_edges");
|
||||
const width = bitWidth(s.params.eps);
|
||||
const ids = Object.keys(s.input.candidates);
|
||||
const raws = forwardMixtures(
|
||||
ids.map((id) => ({ ranges: rangesOf(s.input.candidates[id]) })),
|
||||
s.params.lambda,
|
||||
);
|
||||
const m = raws[ids.indexOf(s.input.candidate)]!;
|
||||
close(worldBits(m, s.input.b, width), s.expected.worldBits, BITS_TOL, "世界比特");
|
||||
assert.equal(cellIndex(s.input.b, width, s.expected.edgeMinus1), -1, "正好在 b − Δ 边界上的值归第 −1 格");
|
||||
s.input.values.forEach((v: number, i: number) => checkSurprise(m, s.input.b, width, v, s.expected.surprise[i], `实测 ${v}`));
|
||||
});
|
||||
|
||||
test("info.json landing_segments_endpoints", () => {
|
||||
const s = pickInfo.get("landing_segments_endpoints");
|
||||
const samples = s.input.cases.map((c: any) => ({ range: range(c.range), value: c.value as number }));
|
||||
assert.deepEqual(
|
||||
samples.map((c: any) => placement(c.range, c.value)),
|
||||
s.expected.segments.map((x: string) => PLACEMENT[x]),
|
||||
);
|
||||
const cov = coverage(samples);
|
||||
assert.equal(cov.rate.status, "measured");
|
||||
close((cov.rate as { value: number }).value, s.expected.coverage, TOL, "覆盖率");
|
||||
});
|
||||
|
||||
test("info.json coverage_no_samples", () => {
|
||||
const s = pickInfo.get("coverage_no_samples");
|
||||
assert.equal(s.expected.coverage.status, "noSamples");
|
||||
assert.equal(coverage(s.input.cases).rate.status, "unmeasured", "没有样本时是明确状态");
|
||||
});
|
||||
|
||||
test("info.json track_record_counts", () => {
|
||||
const s = pickInfo.get("track_record_counts");
|
||||
const samples = (["forward", "ablation"] as const).flatMap((phase) =>
|
||||
s.input[phase].map((x: any) => ({ researcher: "r", phase, range: range(x.range), value: x.value as number })),
|
||||
);
|
||||
const got = trackRecord(samples);
|
||||
assert.deepEqual(got.map((g) => g.phase), ["forward", "ablation"]);
|
||||
for (const g of got) {
|
||||
const e = s.expected[g.phase];
|
||||
assert.deepEqual(
|
||||
{
|
||||
medianHigh: g.tally.medianHigh,
|
||||
medianLow: g.tally.medianLow,
|
||||
pierceUpper: g.tally.aboveTop,
|
||||
pierceLower: g.tally.belowBottom,
|
||||
covered: g.tally.covered,
|
||||
},
|
||||
e,
|
||||
`${g.phase} 战绩`,
|
||||
);
|
||||
}
|
||||
});
|
||||
|
||||
test("info.json author_vs_merged", () => {
|
||||
const s = pickInfo.get("author_vs_merged");
|
||||
// 只收跑过、有有效成绩的候选（由调用方筛）。
|
||||
const items = s.input.items
|
||||
.filter((i: any) => i.ran && i.value !== null)
|
||||
.map((i: any) => ({
|
||||
candidate: i.candidate,
|
||||
author: "author",
|
||||
authorRange: range(i.author),
|
||||
mergedRange: range(i.merged),
|
||||
value: i.value,
|
||||
}));
|
||||
const got = authorVsMerged(items, s.params.direction);
|
||||
assert.equal(got.length, s.expected.rows.length);
|
||||
got.forEach((g, i) => {
|
||||
const e = s.expected.rows[i];
|
||||
assert.equal(g.candidate, e.candidate);
|
||||
close(g.optimism, e.q5Diff, TOL, `${g.candidate} 作者比合并乐观多少`);
|
||||
assert.equal(g.authorPlacement, PLACEMENT[e.authorSegment]);
|
||||
assert.equal(g.mergedPlacement, PLACEMENT[e.mergedSegment]);
|
||||
});
|
||||
});
|
||||
|
||||
for (const name of [
|
||||
"entries_rule1_unique",
|
||||
"entries_rule2_author_wins",
|
||||
"entries_rule2_smallest_index",
|
||||
"entries_identical_prefs",
|
||||
"entries_rule3_exhausted",
|
||||
"entries_N1",
|
||||
"entries_natural_rule2",
|
||||
"entries_natural_rule3",
|
||||
]) {
|
||||
test(`misc.json ${name}`, () => {
|
||||
const s = pickMisc.get(name);
|
||||
const got = assignEntries({
|
||||
researchers: s.input.researchers.map((id: string) => ({ id, choices: s.input.preferences[id] })),
|
||||
entries: s.input.entries,
|
||||
});
|
||||
assert.deepEqual(
|
||||
Object.fromEntries(got.map((a) => [a.researcher, { entry: a.entry, choice: a.rank }])),
|
||||
s.expected.assignments,
|
||||
);
|
||||
// 结果按研究者编号（自然序）排，与 Python 的输出次序一致。
|
||||
assert.deepEqual(got.map((a) => a.researcher), Object.keys(s.expected.assignments));
|
||||
});
|
||||
}
|
||||
|
||||
function balanceRow(total: number, runs: RunState[], batchCap: number) {
|
||||
const b = runBalance(total, runs);
|
||||
return {
|
||||
charged: b.charged,
|
||||
occupied: b.charged + b.reserved,
|
||||
balance: b.balance,
|
||||
forwardK: forwardBatchSize(batchCap, b.balance),
|
||||
ablationMax: ablationCellLimit(b.balance),
|
||||
};
|
||||
}
|
||||
|
||||
test("misc.json balance_part7_table", () => {
|
||||
const s = pickMisc.get("balance_part7_table");
|
||||
let runs: RunState[] = [];
|
||||
s.input.steps.forEach((st: any, i: number) => {
|
||||
runs = [...runs, ...st.added];
|
||||
const { step, added, ...e } = s.expected.afterEachStep[i];
|
||||
assert.equal(step, st.step);
|
||||
assert.deepEqual(balanceRow(s.params.totalRuns, runs, s.params.batchCap), e, `第 ${i} 步 ${step}`);
|
||||
});
|
||||
});
|
||||
|
||||
for (const name of ["balance_mixed_states", "balance_0", "balance_1", "balance_2"]) {
|
||||
test(`misc.json ${name}`, () => {
|
||||
const s = pickMisc.get(name);
|
||||
assert.deepEqual(balanceRow(s.params.totalRuns, s.input.runs, s.params.batchCap), s.expected);
|
||||
});
|
||||
}
|
||||
|
||||
for (const name of ["seed_study-a_r1", "seed_15-real-1_r3"]) {
|
||||
test(`misc.json ${name}`, () => {
|
||||
const s = pickMisc.get(name);
|
||||
const { studyId, round, version } = s.input;
|
||||
assert.equal(canonical({ studyId, round, version }), s.expected.canonical, "规范 JSON");
|
||||
const seed = decisionSeed({ studyId, round, version });
|
||||
assert.equal(seed, s.expected.seed, "种子");
|
||||
// 第 counter 个数取 sha256(`${seed}:${counter}`) 的前 6 字节（约定 40），这里只核对两边对这个式子的理解相同。
|
||||
assert.deepEqual(
|
||||
[0, 1, 2].map((c) => createHash("sha256").update(`${seed}:${c}`).digest().subarray(0, 6).toString("hex")),
|
||||
s.expected.first6BytesHex,
|
||||
);
|
||||
const rng = seededRandom(seed);
|
||||
assert.deepEqual([0, 1, 2, 3, 4].map(() => rng.uniformInt(10)), s.expected.uniformInt10First5);
|
||||
assert.deepEqual(seededSample(s.input.candidates, s.input.batchSize, seed), s.expected.batchSample, "抽候选");
|
||||
assert.deepEqual(seededSample(s.input.cells, s.input.cellCount, seed), s.expected.cellSample, "抽格");
|
||||
// 十二个编号：候选和因子都按自然序（c2 < c10、p2 < p10）排好再抽。
|
||||
assert.deepEqual(seededSample(s.input.candidatesMany, s.input.manyCount, seed), s.expected.batchSampleMany, "抽候选（12 个）");
|
||||
assert.deepEqual(
|
||||
seededSample(s.input.cellsMany, s.input.manyCount, seed),
|
||||
s.expected.cellSampleMany,
|
||||
"抽格（12 个）",
|
||||
);
|
||||
});
|
||||
}
|
||||
|
||||
test("info.json、misc.json 每个场景都已覆盖", () => {
|
||||
assert.deepEqual(pickInfo.unused(), []);
|
||||
assert.deepEqual(pickMisc.unused(), []);
|
||||
});
|
||||
Reference in New Issue
Block a user