- the ESPN feed description and attribution line are gone from goal
panels whenever the report narrative or shot data tells the story
(attribution lives in a tooltip); bookings keep their reason line
- one report sentence per event, ranked by event vocabulary with a
bonus when the player is the actor ('Quinones, who drove a low
shot…' beats 'goals from Quinones and Jimenez gave…')
- momentum verdicts only ever applied to goals (a clear-pressure
booking no longer claims it was 'scored against the run of play')
Routine events the report never mentions (e.g. an early booking) show
what the sources have: the reason. There is no richer feed for those.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
'X is shown the red card' explains nothing. ESPN's summary carries the
full post-match report (Reuters-style narrative) that we fetched and
discarded — it has exactly the missing why ('red-carded for bringing
down Gutierrez just outside the box').
- normalizer keeps the report (headline + plain-text story, schema v4;
boot backfill re-stores played matches automatically)
- expanding an event surfaces the report sentences about that player,
scored by event vocabulary so a player's sending-off sentence beats
his goal mention; attribution line marks the source
- the raw no-reason fallback line is suppressed once the report
explains a booking; xG/momentum/VAR layers stay underneath
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The buildup timeline mostly surfaced unrelated events (a substitution
before a goal explains nothing). Replaced with the sources that
actually describe the event:
- goals match to their captured shot: situation (corner / counter /
set piece / penalty), distance to goal, xG as a plain-language
chance percentage, and xGOT for the finish quality
- the attack-momentum curve judges whether the goal came with or
against the run of play (prior five minutes, only when clear-cut)
- VAR / video-review feed lines still surface on the matching event —
the one slice of play-by-play that genuinely explains a decision
- the feed's action description stays as the de-emphasized last line,
with the redundant scorer prefix stripped; booking reasons unchanged
- name matching shared from the lineup pitch (diacritic/order-proof),
with a unique same-side-and-minute fallback
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- Finished matches show the STARTING XIs on the pitch (red markers with
the minute on everyone subbed off) with 'Subbed on' / 'Subbed off'
lists below, minutes and ratings included; live matches keep the
current-XI view that swaps substitutes in
- Title-race chart gets a sort toggle, defaulting to 'Biggest movers'
(the teams whose odds changed most at the latest update — what's
relevant now) with 'Title favorites' as the alternative
- Entering what-if on the bracket now pre-fills the model's most likely
tournament: group slots seeded from win-group/advance odds (best-
thirds assigned to their allowed slots via backtracking), every
pairing picked by the model — a complete overview to edit by tapping;
Reset returns to the projection
- Team fixtures drop the US 'vs/@' convention: always 'vs' plus an H/A
badge with a tooltip
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
'X is shown a red card' alone isn't insight — the story is in the
surrounding plays. The ESPN summary carries a ~110-line play-by-play
feed (attempts, fouls, corners, VAR checks) we cached but never used:
- normalizer keeps a trimmed commentary list (schema v3; the boot
backfill re-stores older matches automatically)
- previews serve it; expanding a timeline event now shows up to four
feed lines from the three minutes leading in, then the event's own
description — e.g. Korea's saved attempt and corner right before
Czechia's counter-goal header, or the foul behind a booking
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Goals and bookings on the match timeline now expand on tap/click (or
Enter/Space) to show what actually happened, parsed from the live
feed's commentary: the shot description for goals ('header from very
close range to the bottom right corner…') and the reason for cards
('For a bad foul.'). A chevron marks expandable rows; substitutions
and neutral rows carry nothing extra so they stay inert. Works on both
the center-spine and the mobile rail layouts.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Coming-up cards and the post-match comparison now use the model's most
likely score ('2-0') instead of decimal goal expectations ('2.3-0.4');
the pre-match model card keeps just the honesty note since the bar's
chip already carries the predicted scoreline.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- Scheduler now captures FotMob details for fixtures inside 48h, so the
projected XIs exist before kickoff; the Lineups tab shows the pitch
pre-match under a 'Predicted lineups' header with an honest note
(official lineups ~1h before kickoff), switching to the confirmed
view at kickoff
- Finished matches get their forecast back: the preview falls back to
the prediction frozen <=15min before kickoff (the scoreboard's
no-hindsight snapshot), with the most-likely-score chip rebuilt from
the frozen expected goals; the model card now reads 'Model's
pre-match expected goals: 1.60 - 1.02 · final score 2-1', and the
market-movement chart returns to finished matches too
- Upcoming match cards append the model's expected goals to the hint:
'Model: Brazil 64% · 1.3-0.9 goals'
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- LineupPitch: both XIs on a vertical pitch at FotMob's per-player
formation coordinates — shirt numbers, live ratings, goal badges,
formation + coach labels. Substitutes take over the outgoing player's
slot (paired through ESPN's 'X replaces Y' commentary with a unique
same-minute fallback — the sources romanize names differently), with
a subbed-off strip below; the page's live refetch keeps it current
through the match. Falls back to the list view (and hides predicted
pre-kickoff XIs) when no confirmed lineup is captured.
- /api/match-rich now serves the trimmed FotMob lineup (only complete,
fully-positioned XIs)
- Fix: vs-Market label box was too narrow — the probability bar covered
the end of 'DraftKings'
- Timeline spine no longer runs past the kick-off/full-time pills
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Design handoff steps 4-5:
- LivePage: headline live-match hero (gradient card, live ring, smallcaps
stage/venue + minute, big mono score, 3-segment in-play win-prob bar);
favorite team's live match takes the hero slot
- MatchCard: played matches as stacked team rows with the beaten side
dimmed; scheduled matches as a centered 'vs' pairing (model hint and
venue stay)
- GroupTable: Form column — tiny W/D/L bars (accent/gold/loss) computed
from finished group matches
- BracketPage: one round-selector layout on every screen size (cards in
a 2-col grid, losers dimmed), gold 'Projected champion' banner on the
Final view; what-if mode, advance bars, R32 and the third-place
play-off all unchanged
- Predict title race: leader bar, rank and percentage in gold
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Implements steps 1-3 of the Claude Design handoff:
- MatchTimeline: vertical center spine (home left, away right, minute
pills on the rail), goal cards with parsed scorer/assist/running
score, sub and booking chips, synthetic kick-off/half-time/full-time
dividers; single left rail under the sm breakpoint
- matchEvents: pure ESPN commentary parser (scorer, assist, penalty,
own goal, sub in/out, embedded score) with tests on real feed shapes
- Hero scoreboard: panel gradient + accent glow, smallcaps meta, mono
score, stat chips (xG / POTM / attendance / referee; possession and
shots while live); weather line stays for upcoming matches
- Sticky Summary/Timeline/Stats/Lineups sub-nav; all existing cards
re-bucketed with no feature loss (in-play win prob, swing chart,
xG race, shot map, momentum, odds movement, form, H2H, lineups)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The captured FotMob/FIFA/Open-Meteo data becomes visible. Match pages
now carry: a cumulative xG race with goal dots and team totals, a full-
pitch shot map (each side attacking its own end, dots sized by xG,
goals filled), the 90-minute attack-momentum chart, player-of-the-match
with rating, the official info line (stadium · attendance · referee),
and a kickoff-hour weather line for upcoming matches with an altitude
chip above 1,000m. All hand-rolled SVG on the existing token
conventions — design-ready for the upcoming visual overhaul. EN/DE
included, with an honest 'xG and ratings are FotMob estimates' note.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
All twelve third-placed teams ranked by points/GD/goals under the
group grid — top 8 highlighted (they reach the Round of 32), the rest
dimmed. Appears once group play has started.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Fully progressive: without VAPID keys in the environment the API says
404, the bell never renders, and the service worker addition (a push
handler via workbox importScripts — no SW strategy change) is inert.
With keys: a bell on each team page requests permission, subscribes
(one team per device) and the server diffs fixture states on every
broadcast to push Kickoff / Goal / Full time to that team's followers.
Dead endpoints (404/410) self-clean. Round-trip verified locally with
dev VAPID keys; disabled mode verified too.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
ESPN's keyEvents carry participants[].athlete for goals — no text
parsing needed. The normalizer now extracts scorer/scoring/shootout
(payload versioned, with a boot backfill that re-stores summaries
saved by the old normalizer), /api/goldenboot aggregates per-player
goals (own goals and shootout kicks excluded), and the Teams page
leads with the top-10 race. Verified against tonight's real goals.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
When the live connection drops, a slim notice under the header shows
the timestamp of the last snapshot — the page keeps working from it.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The Methodology page lists each recompute (the finished match that
triggered it) with the biggest title-odds move it caused — the model's
thinking made visible, feeding the openness story.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
/compare (also in the mobile More sheet): pick any two of the 48 —
defaults to the top title favourites — and get the model's
neutral-ground matchup plus the full head-to-head from the historical
archive (wins/draws/goals and the last six meetings).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A compact card up top: yesterday's scores at a glance and the teams
whose championship odds moved most over the last day (from the model's
recompute history), with up/down trends linking through to team pages.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A keyboard-first palette (plus a header button) that jumps to any team
page or match page — arrow keys, enter, esc; flags and kickoff days in
the results. Pure client, searches the snapshot already in memory.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
buildRatings samples each WC team's rating along the full walk (yearly
historically, monthly since 2022) into elohistory.json (~72KB, 48
teams). Team pages plot it as a clean SVG line with year and rating
gridlines — Germany's century, 1908 → today, in one glance.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The scoreboard gains a Biggest surprises card — finished matches whose
actual outcome the frozen model priced under 30%, sorted by shock
value, each linking to its match page. Pure client derivation from
data the scoreboard already had.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The CV harness gained a calibration experiment: per-outcome isotonic
maps (pool-adjacent-violators) fit walk-forward on the five folds and
judged leave-one-fold-out against a pre-registered bar. It cleared it:
LOFO ECE improves 16% (0.0146 → 0.0122) with RPS slightly better too
(0.1724 → 0.1722). The final maps (fit on all folds) are committed as
a research artifact, embedded into ratings.json by buildRatings when
the shipped config matches, and applied in matchMatrix by scaling the
score-matrix outcome regions — scorelines, Monte Carlo and displayed
probabilities all stay mutually consistent. Without the field, output
is bit-identical (golden tests).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Once a group reaches its closing stretch (≤3 open matches), every
remaining win/draw/loss combination is enumerated and ranked with the
real tiebreaker logic. Under each table: Top 2 secured / Top 2 with a
win / Still possible (n of N outcomes) / Can't reach the top 2 — with
an honest footnote that tight cases hinge on goal difference and third
place runs through the cross-group best-thirds race. Pure, tested
enumeration in src/lib/scenarios.ts.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A star on the team page (localStorage, no accounts) pins that team's
next or running match in a My team section at the top of the Live tab.
EN/DE strings + aria-pressed on the toggle.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A wand toggle turns the bracket interactive: tap a side to send that
team through; W/L placeholders resolve down the tree (pure, tested
logic in src/lib/whatif.ts). Real results always override picks; picks
that stop making sense after an upstream change are pruned. Each open
pairing shows the model's advance probability (ratings.json fetched
lazily), and once your final resolves, a summary banner names your
champion with the model's chance of exactly that run. EN/DE included.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The odds history we have been capturing every 3h finally gets a face:
de-vigged DraftKings probabilities drift as solid lines toward
kickoff, with the model's numbers as dashed references — the honest
benchmark framing, right on the match page. Renders only when at least
two pre-kickoff lines exist. EN/DE copy included.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
While a match runs, every poll records the in-play model probability
per game state (insert-if-new on minute+score) into inplay_history.
The match page draws it as a stacked area chart — home fills from the
bottom, away from the top, the gap is the draw — with minute ticks and
a 50% guide. Shows live (under the win-probability bar) and after full
time as its own card. EN/DE strings included.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Upcoming fixtures now appear grouped under localized day headers
(Coming up · Mon 15 Jun) regardless of whether something is on today —
not just when the day was empty. Pure grouping logic lives in
src/lib/fixtures.ts with day-boundary tests; prediction chips on the
cards come for free from MatchCard.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A tiny typed i18n layer (no library): en.ts is the single source of UI
copy and the clarity rewrite lives there — shorter sentences, plain
words, the dense Methodology/Scoreboard copy untangled. de.ts mirrors
its shape exactly, enforced by the compiler, with placeholder parity
covered by tests. Every page now reads from the dictionary via useT();
dates flip locale through useFormat() (en-GB/de-DE); raw server values
(status, outcome, stage) map through total records.
The header gains an EN/DE toggle (persisted, defaults from the
browser language); <html lang> stays in sync.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Validated on the strict 2018-2022 window and confirmed on the untouched
2022-2026 test set (RPS 0.1703 vs 0.1721 over 4,448 matches):
- the Elo member now blends 30% of a 3x-faster Elo walk, so recent
results move ratings much harder
- ensemble weight shifts from 75/25 toward Elo to 45/55 toward the
time-decayed Team-DC member — the recent-form model now leads
- Team-DC refits nightly (and at boot) on the 15-year window plus every
finished 2026 match, via a new committed-at-build dcTrain.json
(server-only, excluded from the PWA precache)
- a recent-form goal multiplier was also tested and did NOT validate;
it ships disabled, and backtest.json records the whole decision
buildBacktest.ts grew the experiment harness: wider xi/k grids, the
fast-Elo and form variants, a pre-registered ship bar (>=0.0005
validation RPS), and a 7-day refit-cadence check. Older ratings.json
files still work — all new model fields are optional with golden
regression coverage.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- prediction_snapshots: model + de-vigged market frozen ≤15min pre-kickoff
(or at first sight of a live match, flagged 'late' and excluded from totals).
- src/lib/model/scoring.ts: ONE shared RPS/Brier/log-loss implementation for
the backtest and the live scoreboard.
- /api/scoreboard + /scoreboard page: per-match model-vs-bookmaker bars, RPS
for both after FT, 'closer' badges, running head-to-head with honest rules
printed (small-sample caveat included). Nav: 'vs Market'.
- Methodology page now shows the three-way split + ensemble bake-off variants.
- Verified end-to-end with a simulated match: snapshot froze model 80.7% and
DraftKings 67.0% (de-vig correct), both scored at FT, late-flag honored.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- src/lib/model/teamDc.ts: per-team attack/defence Dixon-Coles via weighted MLE
(Maher iterations), exponential time-decay, shrinkage for thin histories,
learned home multiplier; log-pool of score matrices. 7 vitest cases.
- buildBacktest.ts rewritten as a strict three-way-split bake-off: params
pre-2018, tune (xi, k, w) on 2018-2022 validation, final scores on untouched
2022-2026 test (4,448 matches). Result: ensemble RPS 0.1721 beats Elo-DC
0.1726 and Team-DC 0.1801; ECE stays 0.01. Tuned: xi=0.5 k=5 w=0.75.
- Runtime now IS the backtested model: ratings.json carries teamDc+ensembleW;
matchMatrix() pools both members for predictions, Monte Carlo and advance
probs; ModelEngine re-rating preserves ensemble params; lambdas reported as
matrix expectations (drives in-play).
- scripts/buildSquadValues.ts: Transfermarkt FIWC participants page -> all 48
squad market values (France 1.52bn ... Qatar 20m). Display/availability layer
only — June-2026 values are NOT in the backtested model (would leak).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- docs/V3-GIGA-PLAN.md: the v3 plan (data lake to 7+GB, GIGA ensemble, scoreboard,
UI clarity) with the honest reframe: perfect accuracy = perfect calibration;
'beat the betting sites' = a live public head-to-head, scored with proper rules.
- src/lib/odds.ts: American-ml → decimal, de-vig (normalize away the margin),
overround; 3 vitest cases incl. tonight's real opening lines.
- ESPN core odds adapter (server/src/ingest/espnOdds.ts): captures DraftKings
1X2 moneylines + O/U + spread per fixture; follows $ref pointer items.
- odds_history table (insert-if-changed → clean line-movement history);
scheduler odds sweep every 3h over a 14-day horizon, first sweep at boot;
/api/odds + /api/odds/:num. Odds are a benchmark ONLY — never a model input.
- Boot speed-up: fixture↔event mapping skips dates already fully mapped.
- Verified: 54 fixtures captured with real moneylines locally.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- src/lib/model/inplay.ts: in-play win probability — remaining goals modelled as
time-scaled Poisson processes convolved with the current score; recomputed each
tick. 4 vitest cases (locks at FT, lead grows decisive over time, sums to 1).
- ESPN summary normalizer extended with the live event timeline (keyEvents);
preview now carries liveStats + events. Scheduler refreshes LIVE matches'
summaries every live tick (~20s) for fresh stats/timeline.
- /match/:num is now a live match center: when live it shows in-play win
probability (driven by the WS score/clock), match stats bars and an event
timeline, polling while live; preview content for scheduled games, recap when
finished. Verified with a simulated live state (94% live vs 81% pre-match).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- scripts/buildBacktest.ts: honest walk-forward validation — params fit on
pre-2018 internationals, tested out-of-sample on 7,988 matches (2018-2026)
predicting each game from prior data only. Proper scoring (Brier/log-loss/RPS/
accuracy) vs uniform / base-rate / Elo-only baselines + a calibration analysis
(reliability bins + ECE). Results: 60% accuracy, RPS 0.171 (beats all
baselines), ECE 0.01 (excellent calibration).
- Methodology page (/methodology): plain-language model walkthrough, the backtest
scorecard, a custom-SVG reliability diagram, and honest limits. Transparency is
the differentiator — no market odds, no overclaiming.
- ReliabilityDiagram component; 'Model' nav entry.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Persistence via Node's built-in node:sqlite (zero native deps) on a Docker
volume: response cache, source health, fixture↔provider id map, per-fixture
enrichment, ingest log. Runtime bumped to node:24-slim + --experimental-sqlite.
- Resilient fetcher: DB cache + per-source rate-limit + jittered backoff +
circuit-breaker (blocked sources trip + skip; UI reads DB, never breaks).
- ESPN hidden API as the PRIMARY rich source (works from the VPS where SofaScore
403s): scoreboard (live scores w/ clock) + summary (venue, H2H, recent form,
lineups, team stats). football-data / SofaScore are fallbacks.
- Scheduler: maps all 72 group fixtures to ESPN event ids, polls live on a
dynamic cadence, enriches imminent fixtures into match_ext. /api/sources/health.
- Verified: DB populates (real H2H + form for opening matches), 22 tests pass,
Docker image runs node:sqlite on the volume and persists across restart.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- buildStatsbombViz.ts: processes the 2022 WC Final (Argentina 3-3 France) from
StatsBomb open data → shots+xG, cumulative xG race, starting-XI pass networks,
totals, shootout result. Output committed (11KB) to avoid build-time fetch
- Custom SVG viz (no chart lib): reusable Pitch (StatsBomb 120x80 coords),
ShotMap (xG-sized dots, teams attacking opposite goals), XgRace (stepped
cumulative xG with goal markers, d3-scale), PassNetwork (nodes ∝ involvement,
links ∝ pass volume)
- StoryPage: narrative with hero scoreline, by-the-numbers bars, and the three
visualizations with explanatory copy
- Verified in browser: all three render correctly, no console errors
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
NilsBriggen