vyndr/tests/unit/testLedger.test.js

'use strict';

/**
 * The cumulative Bonferroni denominator, asserted as behaviour.
 *
 * The failure this prevents is silent and slow: correcting by 8 in a session
 * that tries 8 hypotheses, forever, while the programme as a whole has tried
 * sixty. Nothing looks wrong in any single run.
 */

const tl = require('../../src/services/model/testLedger');

const H = (o) => ({ sport: 'mlb', target: 'counter_residual', ...o });

describe('the denominator counts DISTINCT hypotheses across the lifetime', () => {
  it('accumulates across separate runs — it does not reset per session', async () => {
    const store = tl.memoryStore();
    const run1 = await tl.recordAndCount(store, [
      H({ stat: 'hits', archetype: 'BOMBER', interaction: 'barrel_x_park' }),
      H({ stat: 'hits', archetype: 'BOMBER', interaction: 'launch_x_gb' }),
    ]);
    expect(run1.cumulative_tests).toBe(2);

    const run2 = await tl.recordAndCount(store, [
      H({ stat: 'hits', archetype: 'GHOST', interaction: 'defense_x_contact' }),
    ]);
    // A per-session correction would have said 1 here. The whole point is 3.
    expect(run2.cumulative_tests).toBe(3);
    expect(run2.new_this_run).toBe(1);
  });

  it('RE-TESTING the same hypothesis does not inflate the denominator', async () => {
    const store = tl.memoryStore();
    const h = H({ stat: 'hits', archetype: 'BOMBER', interaction: 'barrel_x_park' });
    await tl.recordAndCount(store, [h]);
    const again = await tl.recordAndCount(store, [h]);
    // Waiting for more sample and re-asking is the SAME question, and must not
    // be punished — that discipline is what the programme depends on.
    expect(again.cumulative_tests).toBe(1);
    expect(again.repeat_this_run).toBe(1);
    expect(again.new_this_run).toBe(0);
  });

  it('the current batch IS included — a run is corrected for its own tests', async () => {
    const store = tl.memoryStore();
    const out = await tl.recordAndCount(store, [
      H({ stat: 'rbi', interaction: 'a' }), H({ stat: 'rbi', interaction: 'b' }),
    ]);
    expect(out.cumulative_tests).toBe(2);
  });

  it('the same interaction on a DIFFERENT stat/archetype/target is a NEW shot on goal', async () => {
    const store = tl.memoryStore();
    await tl.recordAndCount(store, [H({ stat: 'hits', archetype: 'BOMBER', interaction: 'x' })]);
    const out = await tl.recordAndCount(store, [
      H({ stat: 'total_bases', archetype: 'BOMBER', interaction: 'x' }),  // new stat
      H({ stat: 'hits', archetype: 'GHOST', interaction: 'x' }),          // new archetype
      H({ stat: 'hits', archetype: 'BOMBER', interaction: 'x', target: 'outcome' }), // new target
    ]);
    expect(out.cumulative_tests).toBe(4);
    expect(out.new_this_run).toBe(3);
  });

  it('the corrected alpha only ever gets HARDER as the programme runs', async () => {
    const cv = require('../../src/services/model/correlateValidator');
    const store = tl.memoryStore();
    const a = await tl.recordAndCount(store, [H({ stat: 's', interaction: 'i1' })]);
    const b = await tl.recordAndCount(store, [H({ stat: 's', interaction: 'i2' })]);
    const alphaA = cv.VALIDATION_REQUIREMENTS.max_p_value / a.cumulative_tests;
    const alphaB = cv.VALIDATION_REQUIREMENTS.max_p_value / b.cumulative_tests;
    expect(alphaB).toBeLessThan(alphaA);
  });

  it('the key is stable and case/shape insensitive', () => {
    expect(tl.testKey({ sport: 'MLB', stat: 'Hits', archetype: 'bomber', interaction: 'x', target: 'outcome' }))
      .toBe(tl.testKey({ sport: 'mlb', stat: 'hits', archetype: 'BOMBER', interaction: 'x', target: 'outcome' }));
  });

  it('a missing archetype is a real pooled test, keyed distinctly from a per-archetype one', () => {
    expect(tl.testKey(H({ stat: 'hits', interaction: 'x' })))
      .not.toBe(tl.testKey(H({ stat: 'hits', archetype: 'BOMBER', interaction: 'x' })));
  });
});