@event4u/agent-config 9.9.0 → 9.10.0

package/dist/agent-src/skills/prediction-pool-optimizer/SKILL.md

@@ -30,10 +30,10 @@ install:
 
 ## When to use
 
-When someone wants the best tips for a prediction / betting pool
+Use when someone wants the best tips for a prediction / betting pool
 (kicktipp-style company pools — football WM, basketball WM, …) and the
-target is **pool points**, not match truth. Triggered by
-[`/prediction-pool`](../../commands/prediction-pool.md) (Steps 3–5) or directly
+target is **pool points**, not match truth. Triggered by the
+[`/prediction-pool`](../../commands/prediction-pool.md) command (Steps 3–5) or directly
 when a user asks to optimize / maximize their pool picks.
 
 **The one idea that makes this skill correct:** the highest-probability
@@ -48,22 +48,22 @@ more. **Always optimize the pool's points, never the truth of the match.**
   parsed (Procedure step 1). Strategy is a function of the rules.
 - **Answer EVERY open question.** A pool has scores *and* bonus / award /
   special questions ("which team supplies the top scorer?", "most yellow
-  cards?", "champion?"). Scorelines only, bonus questions blank = a **failed
-  run** — enumerate every open question in step 1, carry each to an answer
-  (steps 5–6). No silent skips.
-- **Odds are the primary signal — multi-book consensus, not one book.**
-  Bookmaker probabilities already fold in form, squad, injuries, travel,
-  climate. Build the base from a **consensus across the 5–10 biggest
-  publicly-viewable books** (step 2), de-vigged, **sharpness-weighted** —
-  never mirror a single portal. Override only with *current* info (confirmed
+  cards?", "champion?"). Producing scorelines only and leaving the bonus
+  questions blank is a **failed run** — enumerate every open question in
+  step 1 and carry each to an answer (steps 5–6). No silent skips.
+- **Odds are the primary signal — as a multi-book consensus, not one book.**
+  Bookmaker / market probabilities already fold in form, squad, injuries,
+  travel, climate. Build the base from a **consensus across the 5–10 biggest
+  publicly-viewable books** (step 2), de-vigged, **sharpness-weighted** — never
+  mirror a single portal. Only override with *current* information (confirmed
   lineups, late injuries, suspensions, manager change).
 - **No invented numbers.** Emit no probability you cannot derive from real
-  odds or **actually executed** code. Tournament/outright/award numbers come
-  from real markets **or** the executed Poisson helper — never a claimed
+  odds or from **actually executed** code. Tournament/outright/award numbers
+  come from real markets **or** the executed Poisson helper — never a claimed
   "I ran 10,000 simulations".
-- **Scorelines computed, not guessed.** EV-max tip per match from the executed
-  grid optimiser (`score_ev.ts`, step 4a), never the eye. A 3:2 / 4:1 / 1:4 in
-  the output = signature of a skipped computation.
+- **Scorelines are computed, not guessed.** The EV-max tip per match comes
+  from the executed grid optimiser (`score_ev.ts`, step 4a), never the eye. A
+  3:2 / 4:1 / 1:4 in the output is the signature of a skipped computation.
 - **One-sentence justification** per answer. Short.
 
 ## Procedure
@@ -73,42 +73,44 @@ more. **Always optimize the pool's points, never the truth of the match.**
 From the pool's rule page, extract and document:
 
 - Points for **exact result** / **goal (point) difference** / **tendency**.
-- **Every bonus / award / special question** (champion, top scorer, "team of
-  the top scorer", group winners, most cards, longest unbeaten,
-  will-there-be-a-red-card, over/under totals …). **Write them all down as an
-  explicit checklist** — this list is the run's contract; every entry must
-  reach an answer.
+- **Every bonus / award / special question** the pool asks (champion, top
+  scorer, "team of the top scorer", group winners, most cards, longest
+  unbeaten, will-there-be-a-red-card, over/under totals …). **Write them all
+  down as an explicit checklist** — this list is the run's contract; every
+  entry must reach an answer.
 - **Joker / multiplier** rules, per-question point weights.
-- **Quote / rarity** scoring (rare correct tips score more)? — flips strategy
-  toward contrarian (step 4).
-- Special scorings, **per-question deadlines**, **strategy limits** (e.g. max
-  N identical tips).
+- **Quote / rarity** scoring (rare correct tips score more)? — flips the
+  whole strategy toward contrarian (step 4).
+- Special scorings, **per-question deadlines**, and **strategy limits**
+  (e.g. max N identical tips).
 - **The goal**: place well, or *win* a large pool? (changes variance — step 4.)
 
 ### 2. Build the data base — a consensus across the major books
 
-Primary signal: current bookmaker odds, **aggregated across the 5–10 biggest
-publicly-viewable books**, not a single portal:
+Primary signal: current bookmaker odds, but **aggregated across the 5–10
+biggest publicly-viewable books**, not a single portal:
 
-1. **Collect** odds for each market (1X2, exact-score, outrights, and each
-   special/award market a bonus question needs) from several books.
+1. **Collect** the odds for each market (1X2, exact-score, outrights, and
+   each special/award market a bonus question needs) from several books.
    Odds-comparison aggregators (Oddschecker, Oddsportal / Betexplorer) show
-   many books at once; supplement with named books. Book list + weighting
-   recipe in [`reference/odds-and-bonus.md`](reference/odds-and-bonus.md).
+   many books at once; supplement with named books. Concrete book list and
+   the weighting recipe live in [`reference/odds-and-bonus.md`](reference/odds-and-bonus.md).
 2. **De-vig each book** independently (remove its margin) → per-book implied
    probabilities. Raw odds sum to >100%; never treat them as probabilities.
 3. **Aggregate with a healthy weighting**, not a blind average: weight
-   **sharp, low-margin books higher** (Pinnacle, Betfair Exchange),
-   recreational books lower; weighted mean or trimmed median so one outlier
-   book cannot swing the base. Result = the **consensus probability** — the
-   calibration base.
-4. **Single-book outlier = flag, not truth** — investigate *why* (priced-in
-   injury? stale line?) before moving off consensus. Cross-portal agreement is
-   signal; one portal disagreeing is a prompt to check, not to follow.
-
-Secondary (only when it adds signal the consensus has not absorbed): confirmed
-lineups, injuries, suspensions, manager change, recent form, home advantage,
-head-to-head, rest/travel, weather, model forecasts (Opta), Elo/SPI ratings.
+   **sharp, low-margin books higher** (Pinnacle, Betfair Exchange) and
+   recreational books lower; use a weighted mean or a trimmed median so one
+   outlier book cannot swing the base. The result is the **consensus
+   probability** — the calibration base.
+4. **Treat a single book's outlier as a flag, not a truth** — investigate
+   *why* (a known injury already priced? a stale line?) before moving off
+   consensus. Cross-portal agreement is signal; one portal disagreeing is a
+   prompt to check, not to follow.
+
+Secondary (only when it adds signal the consensus has not yet absorbed):
+confirmed lineups, injuries, suspensions, manager change, recent form, home
+advantage, head-to-head, rest/travel, weather, model forecasts (Opta),
+Elo/SPI ratings.
 
 ### 3. Per-match probabilities (sport block)
 
@@ -141,8 +143,9 @@ step-1 rules** — not the prettiest match.
 
 #### 4a. The EV-max scoreline is computed, never eyeballed
 
-Don't hand-pick a scoreline. Run the executed grid optimiser — builds the full
-Poisson score grid, returns the EV-max tip under the step-1 point tiers:
+Do **not** hand-pick a scoreline. Run the executed grid optimiser — it builds
+the full Poisson score grid and returns the expected-points-max tip under the
+step-1 point tiers:
 
 ```bash
 npx tsx node_modules/@event4u/agent-config/src/scripts/prediction-pool/score_ev.ts --lh <home-xg> --la <away-xg> \
@@ -151,45 +154,48 @@ npx tsx node_modules/@event4u/agent-config/src/scripts/prediction-pool/score_ev.
     --tendency <t> --diff <d> --exact <e>          # batch, prints a ranked table
 ```
 
-Two facts the grid makes unavoidable, intuition gets wrong:
-
-- **High scorelines almost never EV-max.** Under partial points a moderate
-  favourite peaks at **1:0 / 2:0 / 2:1**; **1:0 wins surprisingly often**, top
-  of the surface is *flat* (1:0 vs 2:1 vs 2:0 within hundredths). 3:2 / 4:1 /
-  1:4 never optimal — such a tip means the grid wasn't run.
-- **Draws under-tipped.** A correct draw banks the goal-difference tier on
-  every draw scoreline, so in a close match (xG within ~0.4) a 1:1 can
-  out-score a 1:0 — and for low-scoring even games (λ ≲ 1.0/side) a 0:0 is the
-  EV-max. Let the grid decide; the eye tips too few draws.
-
-- **Standard fixed-point scoring + goal "place well"** → tip the grid's EV-max
-  per match. **No contrarian** — only your tip scores, tipping "different"
-  burns EV.
-- **Quote / rarity scoring** → weigh rarer-but-plausible results against payout;
-  take rarity when `payout × probability` wins (raise `--exact` or post-process
-  the ranked table by the multiplier).
+Two facts the grid makes unavoidable — and intuition gets wrong:
+
+- **High scorelines are almost never EV-max.** Under any partial-points rule a
+  moderate favourite peaks at **1:0 / 2:0 / 2:1**; **1:0 wins surprisingly
+  often**, and the top of the EV surface is *flat* (1:0 vs 2:1 vs 2:0 separated
+  by hundredths). A 3:2 / 4:1 / 1:4 tip is never the optimum — if a tip like
+  that appears, the grid was not run.
+- **Draws are under-tipped.** A correctly-tipped draw banks the goal-difference
+  tier on every draw scoreline, so in a close match (xG within ~0.4) a 1:1 can
+  out-score a 1:0. The grid surfaces this; the eye does not. People tip too few
+  draws — let the computation, not the gut, decide.
+
+- **Standard fixed-point scoring + goal "place well"** → tip the grid's
+  EV-max per match. **No contrarian** — only your tip matters for your score,
+  so deliberately tipping "different" just burns EV.
+- **Quote / rarity scoring** → weigh rarer-but-plausible results against their
+  higher payout; take rarity when `payout × probability` wins (raise `--exact`
+  weight or post-process the ranked table by the multiplier).
 
 #### 4b. Large pool, goal "win it" — measure P(finish 1st), don't guess
 
-Goal = **win** a large pool → target flips from E(points) to **P(finish ahead
-of the field)**; pure EV-max converges with the crowd, can't open a gap.
-Measure it with the executed field simulator, not a "rough Kelly" hand-wave:
+When the goal is to **win** a large pool (not place), the target flips from
+E(points) to **P(finish ahead of the whole field)** — and pure EV-max converges
+with the crowd, so it cannot open a gap. Measure it with the executed field
+simulator instead of a "rough Kelly" hand-wave:
 
 ```bash
 npx tsx node_modules/@event4u/agent-config/src/scripts/prediction-pool/pool_winsim.ts pool.json --runs 4000 --max-flips 4
 ```
 
-Models the field as softmax-EV tippers, reports `P(win)` for EV-max-everywhere,
-then greedily reports **which few tips to flip** off EV-max (EV cost + P(win)
-gain each). Read it as the field threshold, empirically:
+It models the field as softmax-EV tippers, reports `P(win)` for the
+EV-max-everywhere baseline, then greedily reports **which few tips to flip**
+off EV-max (and the EV cost + P(win) gain of each). Read the output as the
+field threshold, empirically:
 
-- Pool **N < 20** → sim shows flips barely move P(win); maximize EV, ignore the
-  field.
-- **20 ≤ N < 100 and in the prize positions** → maximize EV.
-- **N ≥ 100, or outside the top ~20%** → take the sim's suggested flips: a
-  handful of higher-variance scorelines on high-consensus matches lift P(win)
-  most per unit EV given up. Flip only what the sim says pays — variance you
-  don't need is wasted EV.
+- Pool **N < 20** → the sim shows flips barely move P(win); maximize EV, ignore
+  the field.
+- **20 ≤ N < 100 and you are in the prize positions** → maximize EV.
+- **N ≥ 100, or you are outside the top ~20%** → take the simulator's
+  suggested flips: a handful of higher-variance scorelines on high-consensus
+  matches lift P(win) most per unit of EV given up. Flip only what the sim says
+  pays — variance you don't need is wasted EV.
 
 Respect all strategy limits from step 1 (max identical tips, etc.).
 
@@ -200,8 +206,9 @@ question type — full taxonomy + per-type method in
 [`reference/odds-and-bonus.md`](reference/odds-and-bonus.md):
 
 - **Tournament structure** (group winners, KO rounds, finalists, champion):
-  real **outright market odds** ("to win group", "to reach final", "outright
-  winner") aggregated per step 2, **or** the executed Poisson simulator:
+  use real **outright market odds** ("to win group", "to reach final",
+  "outright winner") aggregated per step 2, **or** the executed Poisson
+  tournament simulator:
 
   ```bash
   npx tsx node_modules/@event4u/agent-config/src/scripts/prediction-pool/poisson_sim.ts <teams-xg.json> --runs 20000
@@ -214,18 +221,18 @@ question type — full taxonomy + per-type method in
 - **Award / player markets** (top scorer, most assists, "which team supplies
   the top scorer", golden boot, most cards): use the matching **special
   market** — e.g. aggregate per-player "top goalscorer" odds **by team** to
-  answer "which team has the top scorer". No clean market → derive from a
-  stated model (squad strength × games-expected) and **label it a model
-  estimate**, not a market number.
+  answer "which team has the top scorer". Where no clean market exists, derive
+  from a stated model (e.g. squad strength × games-expected) and **label it
+  as a model estimate**, not a market number.
 
-- **Binary / over-under specials** (red card yes/no, over/under total
-  goals/cards): de-vig the consensus probability for the line, pick the EV-max
-  side under the question's point weight.
+- **Binary / over-under specials** (will there be a red card, over/under total
+  goals/cards): take the de-vigged consensus probability for the line and pick
+  the EV-max side under the question's point weight.
 
 Optimize every answer on the same expected-points basis as the scores. Re-run
 as late as each question's deadline allows: re-check confirmed lineups,
-injuries, suspensions, odds movement, then adjust. The per-question deadline is
-the only hard constraint.
+injuries, suspensions, and odds movement, then adjust. The per-question
+deadline is the only hard constraint.
 
 ## Output format
 
@@ -238,59 +245,61 @@ the only hard constraint.
    `Books used` names the consensus base (e.g. "consensus of 7 books, sharp-weighted").
 
 2. **Bonus & special answers** — one row per open question from the step-1
-   checklist, **every entry answered** (none blank):
+   checklist, **every entry answered** (none left blank):
 
    ```
    Question | Answer | Prob / EV | Risk | 1-line reason | Source (market / model)
    ```
 
 3. **Group standings and the full bracket** where the event has them.
-4. **Self-check note** — (a) tips reconcile with
-   [`reference/ev-fixtures.md`](reference/ev-fixtures.md) (known rules + odds →
-   known-good EV tip); (b) bonus table has the **same number of rows as the
-   step-1 checklist** — a shorter table means a question was dropped. If your
-   method disagrees with a fixture, your method is wrong — find the error
-   (usually a forgotten partial-points term, un-de-vigged odds, or following
-   one book instead of the consensus), don't ship the tip.
+4. **Self-check note** — (a) confirm the tips reconcile with
+   [`reference/ev-fixtures.md`](reference/ev-fixtures.md) (known pool rules +
+   market odds → a known-good EV tip); (b) confirm the bonus table has the
+   **same number of rows as the step-1 checklist** — a shorter table means a
+   question was dropped. If your method disagrees with a fixture, your method
+   is wrong — find the error (usually a forgotten partial-points term,
+   un-de-vigged odds, or following one book instead of the consensus), don't
+   ship the tip.
 
 Handed back to [`/prediction-pool`](../../commands/prediction-pool.md) for the approval
 gate — the skill never enters or submits anything.
 
 ## Gotcha
 
-- **Answering only the scores.** Bonus / award questions carry real points;
-  leaving them blank because they are "not a scoreline" forfeits them. The
-  step-1 checklist exists so every question is answered.
+- **Answering only the scores.** A pool's bonus / award questions carry real
+  points; leaving them blank because they are "not a scoreline" silently
+  forfeits them. The step-1 checklist exists so every question is answered.
 - **Following one portal.** A single book can be stale or shaded; build the
-  base from a sharp-weighted consensus across several; an outlier is a flag to
-  investigate, not a number to copy.
-- **Tipping the modal result, not the EV-maximal one.** The single most likely
-  scoreline rarely maximizes partial points — run `score_ev.ts` across the
-  result grid, don't eyeball the favourite.
-- **Hand-picking a high scoreline.** 3:2 / 4:1 / 1:4 never EV-max under partial
-  points — moderate favourites peak at 1:0 / 2:0 / 2:1. A high tip = grid
-  skipped; run `score_ev.ts`.
+  base from a sharp-weighted consensus across several and treat an outlier as
+  a flag to investigate, not a number to copy.
+- **Tipping the modal result, not the EV-maximal one.** The single most
+  likely scoreline rarely maximizes partial points — run `score_ev.ts` across
+  the result grid, don't eyeball the favourite.
+- **Hand-picking a high scoreline.** 3:2 / 4:1 / 1:4 are never EV-max under
+  partial-points rules — moderate favourites peak at 1:0 / 2:0 / 2:1. A high
+  tip in the output means the grid was skipped; run `score_ev.ts`.
 - **Under-tipping draws.** A correct draw banks the goal-difference tier on
-  every draw scoreline, so a close match can want 1:1 (or 0:0). Let the grid
+  every draw scoreline, so in a close match a 1:1 can beat a 1:0. Let the grid
   decide; the eye tips too few draws.
-- **"Rough Kelly" variance for a large pool.** Don't guess deviation amount —
-  run `pool_winsim.ts`; returns the exact flips that raise P(finish 1st) most
-  per unit EV given up.
-- **Forgetting to de-vig.** Raw bookmaker odds sum to >100%; treating them as
-  probabilities inflates the favourite. Remove the margin **per book** before
-  aggregating.
-- **Contrarian under fixed points.** Deviating "to stand out" only helps under
-  quote/rarity rules or a win-a-large-pool goal — otherwise it burns EV.
-- **Claimed-but-unrun simulation.** "I ran 10,000 tournaments" without
-  executing `poisson_sim.ts` is hallucinated — run the code or use outright odds.
+- **"Rough Kelly" variance for a large pool.** Don't guess how much to deviate
+  — run `pool_winsim.ts`; it returns the exact flips that raise P(finish 1st)
+  most per unit of EV given up.
+- **Forgetting to de-vig.** Raw bookmaker odds sum to >100%; treating them
+  as probabilities inflates the favourite. Remove the margin **per book**
+  before aggregating.
+- **Contrarian under fixed points.** Deviating "to stand out" only helps
+  under quote/rarity rules or a win-a-large-pool goal — otherwise it burns EV.
+- **Claimed-but-unrun simulation.** Numbers like "I ran 10,000 tournaments"
+  without executing `poisson_sim.ts` are hallucinated — run the code or use
+  outright odds.
 
 ## Do NOT
 
 - Leave any open pool question (bonus / award / special) unanswered.
 - Build the base from a single bookmaker, or skip de-vigging before aggregating.
 - Tip the most likely result instead of the EV-maximal one.
-- Hand-pick a scoreline instead of running `score_ev.ts` — never emit a
-  3:2 / 4:1 / 1:4 tip, never EV-max under partial points.
+- Hand-pick a scoreline instead of running `score_ev.ts` — and never emit a
+  3:2 / 4:1 / 1:4 tip, which is never EV-max under partial points.
 - Go contrarian under standard fixed-point scoring with a "place well" goal.
 - Guess large-pool variance ("rough Kelly") instead of running `pool_winsim.ts`.
 - Report Monte-Carlo numbers without running `poisson_sim.ts` / `pool_winsim.ts`.
@@ -301,14 +310,14 @@ gate — the skill never enters or submits anything.
 
 - [`/prediction-pool`](../../commands/prediction-pool.md) — the orchestrator (event,
   persistence, Playwright entry, gates).
-- [`reference/odds-and-bonus.md`](reference/odds-and-bonus.md) — major-book list
-  + sharpness-weighted consensus recipe, and the bonus / award / special
+- [`reference/odds-and-bonus.md`](reference/odds-and-bonus.md) — the major-book
+  list + sharpness-weighted consensus recipe, and the bonus / award / special
   question taxonomy with a per-type method.
 - [`reference/ev-fixtures.md`](reference/ev-fixtures.md) — known-good
   rules+odds → EV examples.
 - `node_modules/@event4u/agent-config/src/scripts/prediction-pool/score_ev.ts` —
-  executed exact-score EV optimiser (step 4a; λ + rule → EV-max scoreline).
+  the executed exact-score EV optimiser (step 4a; λ + rule → EV-max scoreline).
 - `node_modules/@event4u/agent-config/src/scripts/prediction-pool/pool_winsim.ts` —
-  executed field model + P(finish 1st) simulator and flip-finder (step 4b).
+  the executed field model + P(finish 1st) simulator and flip-finder (step 4b).
 - `node_modules/@event4u/agent-config/src/scripts/prediction-pool/poisson_sim.ts` —
   the executed tournament simulator (step 5).

package/dist/agent-src/skills/prediction-pool-optimizer/reference/ev-fixtures.md

@@ -26,15 +26,15 @@ EV-max tip : 1:0  (EV 1.574)
   2:0  1.477
 ```
 
-**Reasoning:** top of the EV surface is **flat** — 1:0, 2:1, 2:0 all bank the
-tendency (2) plus goal-difference (3) on many neighbours, within hundredths of
-each other. Grid puts **1:0 narrowly first**; eyeballing the modal *result*
-(2:1) lands a near-tie, not the optimum. Run the grid — don't assert the
-favourite's "obvious" score.
+**Reasoning:** the top of the EV surface is **flat** — 1:0, 2:1 and 2:0 all
+bank the tendency (2) plus goal-difference (3) on many neighbours and sit
+within hundredths of each other. The grid puts **1:0 narrowly first**;
+eyeballing the modal *result* (2:1) lands a near-tie, not the optimum. Run the
+grid — do not assert the favourite's "obvious" score.
 
-**Known-good tip:** **1:0 home** (2:1 essentially tied; with the real de-vigged
-λ either can lead — the grid decides). (Risk: low.) **Not** contrarian — under
-fixed points only your own tip scores, so deviating costs EV.
+**Known-good tip:** **1:0 home** (2:1 essentially tied; with the real
+de-vigged λ either can lead — the grid decides). (Risk: low.) **Not**
+contrarian — under fixed points only your own tip scores, so deviating costs EV.
 
 ---
 
@@ -63,17 +63,17 @@ the multiplier; take the max.
 **Match (football):** a near-coin-flip favourite, Home 52% / Draw 26% /
 Away 22%.
 
-**Reasoning:** N ≥ 100 and you behind → pure EV converges with the field, can't
-create the gap; target is **P(finish 1st)**, not E(points). Don't guess the
-variance: run `pool_winsim.ts` with the pool's `N` and your `my_lead`. Shows
-P(win) collapsing under EV-max-everywhere, returns the **specific flips**
-(higher-variance scorelines on high-consensus matches) that raise P(win) most
-per unit EV given up.
+**Reasoning:** with N ≥ 100 and you behind, pure EV converges with the field
+and cannot create the gap you need — the target is **P(finish 1st)**, not
+E(points). Don't guess the variance: run `pool_winsim.ts` with the pool's `N`
+and your `my_lead`. It shows P(win) collapsing under EV-max-everywhere and
+returns the **specific flips** (higher-variance scorelines on high-consensus
+matches) that raise P(win) most per unit of EV given up.
 
 **Known-good tip:** EV-max on the safe matches; the **simulator's suggested
 flips** on the 2–4 matches it names, to manufacture upside. (Risk: high —
-intentional.) Verify the sim shows a P(win) gain — flips not moving it (small
-N) → don't add variance you don't need.
+intentional.) Verify the sim shows a P(win) gain — if flips don't move it
+(small N), don't add variance you don't need.
 
 ---
 
@@ -94,18 +94,18 @@ spread). Tip the winner plus the modal margin bucket.
 
 ## Fixture 5 — multi-book consensus (de-vig per book, sharp-weighted)
 
-**Rule:** any — checks the **odds base**, not the EV map.
+**Rule:** any — this fixture checks the **odds base**, not the EV map.
 
 **Market (football, 1X2):** two books.
 - Book S (sharp, weight 3): 1.80 / 3.60 / 4.50 → de-vig 0.526 / 0.263 / 0.210.
 - Book R (recreational, weight 1): 1.75 / 3.50 / 4.20 → de-vig 0.522 / 0.261 / 0.217.
 
 **Reasoning:** de-vig **each book** first (raw `1/o` sums to >1; normalise),
-then sharp-weighted mean per outcome and renormalise. Aggregating raw odds, or
-using one book, is wrong.
+then take the sharp-weighted mean per outcome and renormalise. Aggregating
+the raw odds, or using one book, is wrong.
 
-**Known-good base:** **Home 0.525 / Draw 0.262 / Away 0.212.** A run that fed
-the EV grid one book's raw odds has the wrong base — fix it before the tip.
+**Known-good base:** **Home 0.525 / Draw 0.262 / Away 0.212.** A run that
+fed the EV grid one book's raw odds has the wrong base — fix it before the tip.
 
 ---
 
@@ -115,16 +115,16 @@ the EV grid one book's raw odds has the wrong base — fix it before the tip.
 scorer?"
 
 **Market (top-goalscorer outright, de-vigged player probabilities):**
-- Team A: A1 14%, A2 5% → team A total **19%**.
-- Team B: B1 16% → team B total **16%**.
-- Team C: C1 9%, C2 4% → team C total **13%**.
+- Team A: player A1 14%, player A2 5% → team A total **19%**.
+- Team B: player B1 16% → team B total **16%**.
+- Team C: player C1 9%, player C2 4% → team C total **13%**.
 
-**Reasoning:** the most-likely *player* (B1, 16%) is on team B, but the
-question asks the **team** — sum each squad's players. Team A 19% beats team B
-16%. Answer the asked question, not the adjacent one.
+**Reasoning:** the single most-likely *player* (B1 at 16%) belongs to team B,
+but the question asks for the **team** — sum each squad's players. Team A's
+19% beats team B's 16%. Answer the asked question, not the adjacent one.
 
-**Known-good answer:** **Team A.** (Source: market, aggregated by team. Risk:
-medium.) **Not** team B — the modal-player trap.
+**Known-good answer:** **Team A.** (Source: market, aggregated by team.
+Risk: medium.) **Not** team B — that is the modal-player trap.
 
 ---
 
@@ -137,7 +137,7 @@ medium.) **Not** team B — the modal-player trap.
 | Match (λ) | EV-max | a high tip's EV | verdict |
 |---|---|---|---|
 | Senegal–Iraq (2.0:0.7) | **1:0** (1.881) | 4:1 ≈ 1.55 | high tip leaks ~0.33 |
-| Qatar–Switzerland (0.6:2.1) | **0:1** (1.981) | 1:4 ≈ 1.65 | tipping the underdog's goals = costliest move on the board |
+| Qatar–Switzerland (0.6:2.1) | **0:1** (1.981) | 1:4 ≈ 1.65 | tipping the underdog's goals is the costliest move on the board |
 | Spain–CapeVerde (2.3:0.6) | **2:0** (2.033) | 3:1 ≈ 1.88 | only at λ ≳ 2.3 does 2:0 edge past 1:0; never higher |
 
 **Reasoning:** under partial points the value sits in the tendency and
@@ -147,8 +147,9 @@ only near λ ≈ 2.3–2.4; above that, never. **3:2 / 4:1 / 4:2 / 1:4 are never
 EV-max.** Adding goals — especially the underdog's — only shrinks the hit
 probability without protecting the diff/tendency points.
 
-**Known-good behaviour:** any 3:2 / 4:x / x:4 tip in the run → the grid wasn't
-run; `score_ev.ts` is the gate. (Risk: low; correctness fixture, not strategy.)
+**Known-good behaviour:** if the run emits any 3:2 / 4:x / x:4 tip, the grid
+was not run — `score_ev.ts` is the gate. (Risk: low; this is a correctness
+fixture, not a strategy one.)
 
 ---
 
@@ -168,8 +169,8 @@ run; `score_ev.ts` is the gate. (Risk: low; correctness fixture, not strategy.)
 goal-difference tier (3) on *every* draw scoreline, so in a **low-scoring even
 match (λ ≲ 1.0/side) the draw — usually 0:0 — is the EV-max**, tied with 1:1.
 As λ rises past ~1.1 a one-goal win edges ahead, but the draw stays in the top
-tips. Grid surfaces this; intuition suppresses it.
+tips. The grid surfaces this; intuition suppresses it.
 
 **Known-good behaviour:** a tip set with **near-zero draws across many
-low-scoring even matches** is a red flag — re-run `score_ev.ts`, let the grid
-decide, don't default every close game to 1:0.
+low-scoring even matches** is a red flag — re-run `score_ev.ts` and let the
+grid decide, don't default every close game to 1:0.