vyndr/scripts/link2-reliever-identity.js

#!/usr/bin/env node
'use strict';

/**
 * LINK 2 — can we say WHICH arm faces the later plate appearances?
 *
 * Link 1 proved, so this link is allowed to be attempted at all. It is gated the
 * same way: predict the reliever who actually threw a given post-starter plate
 * appearance, against a naive baseline, point-in-time.
 *
 *   BASELINE     the team's most-used reliever to date — "guess the busiest arm"
 *   PREDICTION   the reliever that team has most often used IN THIS INNING to
 *                date, which is the cheapest expression of bullpen ROLE
 *
 * Loss is misclassification: 0 when the named arm actually threw it, 1 otherwise.
 *
 * ── THE REPLICATION UNIT IS THE BULLPEN, AND THERE ARE THIRTY ────────────
 * Bullpen usage is a team-level process — the same manager, the same arms, the
 * same roles all season — so errors are correlated within team and the entity
 * this prediction rides on is the club. That caps replication at 30 whatever the
 * row count, exactly like park geometry and team defence. Reported explicitly
 * rather than dissolved into a row count of tens of thousands.
 *
 *   node scripts/link2-reliever-identity.js
 */

require('dotenv').config();
const fs = require('fs');
const path = require('path');
const pg = require('../src/services/model/predictionGate');
const tl = require('../src/services/model/testLedger');
const { createClient } = require('@supabase/supabase-js');

const CACHE = process.env.SEQ_OUT || path.join(process.cwd(), '.seq-cache', 'sequences.json');

/** Pick the key with the highest count; null when there is nothing to pick from. */
function argmax(counter) {
  let best = null; let bestN = -1;
  for (const [k, v] of counter) if (v > bestN) { best = k; bestN = v; }
  return bestN > 0 ? best : null;
}

function build() {
  const { games } = JSON.parse(fs.readFileSync(CACHE, 'utf8'));
  games.sort((a, b) => String(a.date).localeCompare(String(b.date)) || a.gamePk - b.gamePk);

  // Point-in-time bullpen histories, accumulated as we walk forward in time.
  const overall = new Map();          // team -> Map(pitcherId -> appearances)
  const byInning = new Map();         // `team|inning` -> Map(pitcherId -> appearances)
  const rows = [];

  for (const g of games) {
    for (const side of ['home', 'away']) {
      const team = g[side].abbr || g[side].team;
      if (!team) continue;
      const starter = (g[side].arms || []).find((a) => a.started);
      if (!starter) continue;
      const relievers = new Set((g[side].arms || []).filter((a) => !a.started).map((a) => a.id));
      if (!relievers.size) continue;

      // This side PITCHES in the opposite half-inning.
      const half = side === 'home' ? 'top' : 'bottom';
      const post = g.pas.filter((p) => p.half === half && p.pitcher !== starter.id);

      for (const pa of post) {
        const ov = overall.get(team);
        const inn = byInning.get(`${team}|${pa.inning}`);
        const basePick = ov ? argmax(ov) : null;
        const modelPick = inn ? argmax(inn) : basePick;
        // No history yet is honestly unreadable, not a wrong guess.
        if (basePick === null || modelPick === null) continue;
        rows.push({
          cluster: team,
          baseline: Number(basePick) === pa.pitcher ? 1 : 0,
          prediction: Number(modelPick) === pa.pitcher ? 1 : 0,
          actual: 1,
          inning: pa.inning,
        });
      }

      // Now fold this game into history — never before predicting from it.
      if (!overall.has(team)) overall.set(team, new Map());
      const ovm = overall.get(team);
      for (const r of relievers) ovm.set(String(r), (ovm.get(String(r)) || 0) + 1);
      for (const pa of post) {
        const k = `${team}|${pa.inning}`;
        if (!byInning.has(k)) byInning.set(k, new Map());
        const m = byInning.get(k);
        m.set(String(pa.pitcher), (m.get(String(pa.pitcher)) || 0) + 1);
      }
    }
  }
  return rows;
}

(async () => {
  const rows = build();

  let cumulative = 1;
  try {
    const sb = createClient(process.env.SUPABASE_URL,
      process.env.SUPABASE_SERVICE_ROLE_KEY || process.env.SUPABASE_SERVICE_KEY,
      { auth: { persistSession: false } });
    const mc = await tl.recordAndCount(tl.supabaseStore(sb), [
      { sport: 'mlb', stat: 'reliever_identity', archetype: null, interaction: 'link2:reliever_identity', target: 'actual_arm' },
    ]);
    cumulative = mc.cumulative_tests;
  } catch { /* offline */ }

  const verdict = pg.adjudicate(rows, {
    link: 'link2_reliever_identity',
    loss: 'absolute',
    cumulativeTests: cumulative,
  });

  const acc = (k) => (rows.length ? rows.filter((r) => r[k] === 1).length / rows.length : null);

  console.log(JSON.stringify({
    link: 'LINK 2 — reliever identity',
    post_starter_plate_appearances: rows.length,
    distinct_bullpens: new Set(rows.map((r) => r.cluster)).size,
    cumulative_tests: cumulative,
    baseline_accuracy: round4(acc('baseline')),
    model_accuracy: round4(acc('prediction')),
    verdict,
    structural_note: 'the entity this prediction rides on is the BULLPEN, and there are 30 — row count cannot create replication that does not exist',
  }, null, 2));
  process.exit(0);
})();

const round4 = (v) => (v == null ? null : Math.round(v * 10000) / 10000);