vyndr/tests/unit/predictionGate.test.js

'use strict';

/**
 * The two-part gate for a CONTINUOUS prediction.
 *
 * Same discipline as factorGate, different units — and the same dangerous
 * failure: a link that moves off the naive baseline while predicting nothing
 * makes the projection LOOK like it read the game script.
 */

const pg = require('../../src/services/model/predictionGate');

/** n rows where the prediction tracks truth to a given degree. */
function rows(n, { skill = 1, clusters = 60, seed = 5 } = {}) {
  let s = seed;
  const rnd = () => (s = (s * 1103515245 + 12345) % 2147483648) / 2147483648;
  const out = [];
  for (let i = 0; i < n; i += 1) {
    const actual = 20 + (rnd() - 0.5) * 12;
    const noise = (rnd() - 0.5) * 12;
    out.push({
      cluster: `c${i % clusters}`,
      baseline: 20,
      prediction: 20 + skill * (actual - 20) + (1 - skill) * noise,
      actual,
    });
  }
  return out;
}

describe('a link that genuinely predicts', () => {
  it('PROVES when it beats the naive baseline out-of-sample', () => {
    const v = pg.adjudicate(rows(1200, { skill: 0.8 }), { link: 'good' });
    expect(v.verdict).toBe('PROVES');
    expect(v.improvement.loss_delta).toBeLessThan(0);
    expect(v.improvement.ci[1]).toBeLessThan(0);
  });

  it('does NOT binarise the target — that is why factorGate cannot do this job', () => {
    // Brier collapses the outcome to 0/1. A target like "batters faced" would be
    // destroyed by that, so the loss here stays on the real scale.
    const v = pg.adjudicate(rows(1200, { skill: 0.9 }), { link: 'scale' });
    expect(v.improvement.loss_baseline).toBeGreaterThan(1);
  });
});

describe('the failures it must name', () => {
  it('THEATER — moves off the baseline and predicts nothing', () => {
    const v = pg.adjudicate(rows(1200, { skill: 0 }), { link: 'noise' });
    expect(v.verdict).toBe('THEATER');
    expect(v.movement.mean_abs_shift).toBeGreaterThan(0);
    expect(v.consequence).toMatch(/LOOK like it read/);
  });

  it('INERT — never departs from the baseline at all', () => {
    const flat = rows(1200, { skill: 0 }).map((r) => ({ ...r, prediction: r.baseline }));
    const v = pg.adjudicate(flat, { link: 'flat', minMovement: 0.01 });
    expect(v.verdict).toBe('INERT');
  });

  it('thin sample is PENDING, never a verdict', () => {
    const v = pg.adjudicate(rows(100, { skill: 0.9 }), { link: 'thin' });
    expect(v.verdict).toBe('PENDING_SAMPLE');
    expect(v.rows_needed).toBe(400);
  });
});

describe('replication is counted in arms, not in starts', () => {
  it('refuses when the entity it rides on has too few clusters', () => {
    // 39,629 post-starter plate appearances across 30 bullpens is 30 readings.
    const v = pg.adjudicate(rows(5000, { skill: 0.9, clusters: 30 }), { link: 'bullpen' });
    expect(v.verdict).toBe('PENDING_SAMPLE');
    expect(v.reason).toMatch(/30 independent clusters < 40/);
    expect(v.clusters_needed).toBe(10);
  });

  it('the clustered interval is wider than the unclustered one', () => {
    const r = rows(1500, { skill: 0.5, clusters: 45 });
    const clustered = pg.adjudicate(r, { link: 'a' });
    const flat = pg.adjudicate(r.map(({ cluster, ...x }) => x), { link: 'b' });
    const w = (v) => v.improvement.ci[1] - v.improvement.ci[0];
    expect(w(clustered)).toBeGreaterThan(w(flat));
  });

  it('the cumulative correction widens the interval', () => {
    const r = rows(1500, { skill: 0.6 });
    const one = pg.adjudicate(r, { cumulativeTests: 1 });
    const many = pg.adjudicate(r, { cumulativeTests: 108 });
    expect(many.improvement.ci_level).toBeGreaterThan(one.improvement.ci_level);
  });
});

describe('honesty', () => {
  it('an unreadable row is dropped, never zero-filled', () => {
    const r = rows(600, { skill: 0.8 });
    r[0].prediction = null; r[1].actual = null; r[2].baseline = null;
    const v = pg.adjudicate(r, { minN: 100 });
    expect(v.improvement.n).toBe(597);
  });
});