proj-v1: absolute matchup projection challenger (distribution + full ladder)

A THIRD challenger (after arch-v1, contact-v1), MLB batting v1. Champion is
market-relative P(stat>LINE); proj-v1 is ABSOLUTE — what the hitter will DO —
emitted as a full distribution from which the WHOLE LADDER (P≥1,P≥2,P≥3) derives.
Champion untouched; nothing claimed; the ledger decides per rung, per stat.

- projection/distribution.js — Bayesian Gamma-Poisson → negative-binomial
  predictive. Admits over-dispersion; under-dispersion → Poisson approx
  (conservative, documented). Uncertainty scales with sample by construction
  (r=α): thin → WIDE (real mass on P≥1, honestly thin P≥3), thick → tight.
  NEVER abstains — width carries the honesty.
- projection/matchupRead.js — the input the book doesn't use. HONEST FIDELITY:
  pitcher repertoire is rich (97% pitch-mix) but hitters have NO pitch-type
  performance, so TRUE repertoire-vs-profile is impossible today. This is the
  COARSE version (arsenal buckets fastball/sinker/breaking + whiff/hard-hit
  tendency × hitter whiff/chase/gb-fb/hard-hit) — beats generic L/R, derived +
  documented + TESTED two-sided. A hitter pitch-type feed unlocks the true form.
- projectionChallenger.js — park RELATIVE to the player's own log exposure
  (isHome→own park, away→opp park; Phase B's raw-multiply bug solved), recency-
  weighted fit, per-factor breakdown (form/park/weather/platoon/matchup — show
  your work), full rung set + book-implied per rung. Combined non-form
  multiplier bounded.
- Wired after contact-v1, own try, flag PROJ_V1_ENABLED, reusing arch-v1's
  already-computed park/weather/platoon (no duplicate env I/O). Own ledger
  columns (migration 032, applied to prod): distribution, ladder, point, line,
  our-P, book-implied, factor breakdown — measurable per rung/stat after settle.

Phase 0 (prod-verified): venue join via isHome; NB family; uncertainty-as-width;
coarse matchup honest fidelity; no lineup-slot (per-game rate, volume implicit).
Sanity: thin-hot → wide (credible low rung, thin high rung); .300 hitter ≠ 3.0;
matchup two-sided; champion byte-identical. proj-v1 suites 23/23; snapshot/
ledger/siblings 74 green. Forward-only, version-stamped, PROJ_V1_ENABLED kill.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCNgGSt5qvcLxaeQqa7Zpj
This commit is contained in:
Kev
2026-07-23 03:59:36 -04:00
parent b6f12daa98
commit 6386e737b9
8 changed files with 815 additions and 0 deletions
+62
View File
@@ -232,6 +232,31 @@ async function loadStatcastRows(sport) {
} catch { return null; }
}
/**
* proj-v1 — opposing-pitcher arsenals by source_id (MLBAM id), classified once
* per snapshot. Read-only; a failure returns an empty map (proj-v1 then has no
* matchup contribution, honest-absent). Separate from loadStatcastRows (which
* keys by player name) because the opposing pitcher is resolved by ID.
*/
async function loadPitcherArsenals(sport) {
const out = new Map();
try {
if (String(sport).toLowerCase() !== 'mlb') return out;
const sb = require('../utils/supabase').getSupabaseServiceClient();
if (!sb) return out;
const matchupRead = require('./projection/matchupRead');
const { data, error } = await sb.from('statcast_aggregates')
.select('source_id,pitch_mix').eq('sport', sport).eq('role', 'pitcher').limit(5000);
if (error || !data) return out;
for (const r of data) {
if (r.source_id == null || !r.pitch_mix) continue;
const arsenal = matchupRead.classifyArsenal(r.pitch_mix);
if (arsenal) out.set(Number(r.source_id), arsenal);
}
return out;
} catch { return out; }
}
async function runSnapshot(sport, opts = {}) {
const sp = String(sport || '').toLowerCase();
const deps = {
@@ -534,11 +559,13 @@ async function runSnapshot(sport, opts = {}) {
// per grade. The batter hand rides on the statcast row; the rest is
// fetched once here. Best-effort: a context failure leaves archetype-only.
let contextFor = null;
let ctxInternals = null; // hoisted for proj-v1 (opposing pitcher resolution)
try {
const envCtx = deps.environmentContext || require('./environmentContext');
const ctx = await envCtx.buildContext(sp, {
origin: process.env.BACKEND_SELF_ORIGIN || 'http://localhost:3000',
});
ctxInternals = ctx._internals || null;
// Enrich each grade with the hitter hand the platoon estimate needs
// (statcast_aggregates.bats, already loaded above).
const handOf = (name) => {
@@ -570,6 +597,41 @@ async function runSnapshot(sport, opts = {}) {
} catch (e) {
console.warn(`[contact-challenger] ${sp} skipped:`, e.message);
}
// proj-v1 — ABSOLUTE matchup projection (MLB batting). Own try; flag-gated;
// reuses arch-v1's already-computed park/weather/platoon on each grade so
// it adds no duplicate env I/O. NEVER abstains — thin → wide distribution.
if (String(process.env.PROJ_V1_ENABLED || '1') !== '0') {
try {
const projection = deps.projectionChallenger || require('./projectionChallenger');
const { abbrOf } = require('./environmentContext');
const arsenalById = await (deps.loadArsenals || loadPitcherArsenals)(sp);
const oppByTeam = (ctxInternals && ctxInternals.oppPitcherByTeam) || new Map();
const mlbAdapter = deps.mlbAdapter || require('./adapters/mlbStatsAdapter');
withChallenger = await projection.attachProjection(withChallenger, {
batterRowFor: (g) => rowsByKey.get(nameKey(g.player || g.player_name || '')),
parkFor: (g) => (g.env_park_base != null ? Number(g.env_park_base) : null),
weatherFor: (g) => (g.env_weather_mod != null ? Number(g.env_weather_mod) : null),
platoonFor: (g) => {
const a = (g.challenger_adjustments || []).find((x) => x.axis === 'matchup');
return a ? a.multiplier : null;
},
arsenalFor: (g) => {
const pid = oppByTeam.get(abbrOf(g.team));
return pid != null ? (arsenalById.get(Number(pid)) || null) : null;
},
gameLogFor: async (g) => {
if (!g.playerId) return [];
try { return (await mlbAdapter.getPlayerGameLog(g.playerId)) || []; } catch { return []; }
},
});
const projected = withChallenger.filter((g) => g.proj_point != null).length;
const projMatchup = withChallenger.filter((g) => (g.proj_factors && g.proj_factors.breakdown || []).some((f) => f.label === 'matchup' && f.present)).length;
console.log(`[proj-v1] ${sp}${projected}/${withChallenger.length} projected (${projMatchup} with matchup)`);
} catch (e) {
console.warn(`[proj-v1] ${sp} skipped:`, e.message);
}
}
}
} catch (e) {
// The challenger must NEVER break the pipeline it is measured inside.