ecf78b911c96618e3ffb10943a7bbc872fa1d6d8
207 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 builtbykev
|
ecf78b911c |
Accrual watch + pre-registered resumption; the program is idle on modeling
PHASE 1 — the existence risk is resolved. Nineteen commits were local-only
with no push credentials. Three artifacts now exist off the working tree:
~/vyndr-full-history-2026-08-07.bundle 6.8M SELF-CONTAINED, clone it
~/vyndr-session-2026-08-07.bundle 244K needs existing history
~/vyndr-session-patches/ (20 patches) 1.5M
Use the full-history bundle -- `git bundle verify` shows the session bundle
requires ref
|
||
|
builtbykev
|
494c83cf76 |
Hunt the window-bug class: three more paths, and the forward re-audit rule
in code PHASE 0 — getStatRows is the single base-rate path, so every branch is audited, plus the feature builders since l20_avg is the season reference projectionFor reads: getStatRows MLB -> estimator base fullLog CORRECT ( |
||
|
builtbykev
|
929fd81940 |
Repair the champion: it was reading ten games, not a season
PHASE 0 — the defect is real past the peek. Against a FAIR point-in-time baseline (each player's rate over games strictly before that date, >=10 prior games, box scores back to 05-01), the served champion LOSES on all four stats, three of four CIs excluding zero: hits 0.00251 vs 0.00774 CI [-0.0074,-0.0011] TB 0.00393 vs 0.00619 CI [-0.0055,-0.0003] rbi 0.02481 vs 0.03133 CI [-0.0153,-0.0005] runs 0.00181 vs 0.00683 CI [-0.0114,+0.0008] PHASE 1 — the cause is the WINDOW, not the weights. estimateProbability builds its base rate as the frequency over every row it is handed, and featureCache.getStatRows handed it res.last10. So the "season rate" was a TEN-GAME rate, and 0.4 of the forecast was the last five OF THOSE TEN. The 0.40 recency weight costs resolution on all four stats (-0.00086, -0.00107, -0.00562, -0.00365). Nudges are mixed and small -- harmful on hits and rbi, marginally helpful on TB and runs -- so they are left alone. PHASE 2 — two lines, no new data, no extra API call, because fullLog was already fetched by the same adapter call that produced last10: getStatRows now reads fullLog, and RECENCY_WEIGHT goes 0.40 -> 0.20. hits 0.00251 -> 0.00817 (tripled; now above the fair baseline) TB 0.00393 -> 0.00734 (above baseline; vs old CI [0.0020,0.0067]) rbi 0.02481 -> 0.02727 (still below baseline, CI includes zero) runs 0.00181 -> 0.00436 (still below baseline, CI includes zero) Gate stated exactly: hits and TB now exceed the fair baseline on the point estimate; rbi and runs remain below but EVERY CI now includes zero, so no stat reliably loses to a frequency table. That is a tie on rbi/runs, not a win, and it is reported as one. Only TB's improvement over the old champion is CI-confirmed; the rest are directional. STALE-FIT GATE: CALIBRATION_DEPLOYED is now EMPTY. The low-param maps were fitted on the retired forecast and fromLedger cannot rescue them -- settled ledger rows still carry OLD p_win, so refitting today would refit the retired forecast. Nothing is served calibrated until dates settle under the repaired champion, and the favourite-longshot bias must be re-measured rather than assumed to survive. The shadow duel is void. PHASE 3 — the hits factor lift is NOT re-measured, and cannot be yet: it needs settled rows produced BY the repaired champion, which ships in this commit. Replaying would score the factors against a reconstruction rather than the served forecast. Deferred, explicitly. The factors remain wired and transmitting; only their lift is unquantified on the new baseline. PHASE 4 — standing flag, and it is large: EVERY factor verdict in this programme, every null and every THEATER, was measured against a champion worse than a frequency table. Signal added to noise reads as noise. Prior verdicts may deserve re-audit. Logged, not re-run. Re-queued not built: rbi lineup-slot / RISP opportunity through the two-part gate, now landing on a repaired champion. Serving-path change by design; the byte-identical invariant inverted and all four stats move. Nine frozen model modules verified unchanged. No Bonferroni slot -- resolution accounting on the champion's own knobs. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
65ca6493db |
Decompose the rbi anomaly: it is lineup ROLE, and the counter is
out-resolved by a frequency table on three of four stats
PHASE 0 — the 14.51% is REAL. Re-derived with a paged pull asserted
against an exact count (rbi 7,930 == 7,930; hits 11,690; TB 12,086; runs
6,440), since this harness produced a false null three times tonight. rbi
resolution 0.03268 reproduces, deciles are monotone through the middle,
and 20 raw rows are in the artifact for hand audit.
CAVEAT GOVERNING EVERYTHING BELOW: the naive forecasts are leave-one-out
ON THE EVALUATION WINDOW, so they see the rows they are scored on while
the model is strictly point-in-time. They are upper bounds on available
resolution, not fair competitors, and every comparison is read that way.
PHASE 1 — the split:
stat MODEL (a)player-base (b)lineup-slot (c)within-stratum
rbi 0.03268 0.01167 0.03608 0.01908
hits 0.00252 0.00446 0.00100 0.00473
TB 0.00442 0.01331 0.03448 0.00607
runs 0.00130 0.00262 0.01156 0.01170
FINDING 1 — rbi's resolution is LINEUP ROLE almost exactly. Batting-order
slot alone resolves 0.03608 against the model's 0.03268. A single integer
accounts for the whole anomaly and slightly more. That is opportunity, not
skill -- the cleanup hitter bats with runners on. 36% is matched by player
identity alone. Within similar-base-rate strata the model still resolves
0.01908, 58% of its total and higher than any other stat's ENTIRE model
resolution, so genuine within-role discrimination exists on top.
FINDING 2 — on three of four stats the model is beaten by "he's a .270
hitter". Base-rate-only out-resolves the model 1.8x on hits, 3.0x on TB,
2.0x on runs. Even allowing for the window-peeking advantage, a 1.8-3.0x
gap is not explained by that alone: the served counter appears to DESTROY
discrimination relative to the player's own rate. rbi is the one stat
where the model beats the naive baseline.
FINDING 3 — lineup slot out-resolves the MODEL on three stats: TB 7.8x,
runs 8.9x, rbi 1.1x. Hits is the only stat where batting order carries
less, which is mechanically right -- a hit is a hit wherever you bat, but
runs, RBI and total bases all scale with opportunity.
PHASE 2 — all three worlds are partly true, in measured proportions.
World A ~90% true (slot covers rbi's entire resolution). World B ~36% true
for rbi, but the WHOLE story for hits/TB/runs where base rate alone wins.
World C true with a low ceiling: hits' total available spread resolution
is 0.00446, i.e. 1.8% of variance from a forecast that has seen the
answers.
PHASE 3 — the next arc is NOT "strengthen hits factors". Hits has the
lowest available resolution on the board and last order's wiring already
took it to 1.39% of a ~1.8% ceiling. Named first factor order for next
session: LINEUP SLOT / RISP OPPORTUNITY on rbi through the two-part gate --
input already ingested and prod-verified (S89), resolution measured not
hypothesised, causally-correct unit is plate appearances with runners on.
Measured availability is not a pass; it still faces the gate.
And higher-value than either: the counter being out-resolved by a
frequency table on three of four stats is a defect in the CHAMPION, not a
factor problem, and it costs nothing to test -- the recency blend and the
+/-0.03 / +/-0.015 nudges are three lines in probabilityEstimator.
The hits transmission win from
|
||
|
builtbykev
|
43f65d30cb |
Wire the three proven hits factors pre-grade: transmission proven, gain
inconclusive THE BUG THIS NEARLY SHIPPED AS A FINDING. The first audit reported 0 factors fired on all 1,140 rows. Not a result -- my paging helper ordered by `id`, and batter_spray, team_defense, platoon_splits and statcast_aggregates have composite primary keys with NO id column. The query errored, the loop broke on error, and four fully-populated tables read as empty. hitsFactorContext.js -- the PRODUCTION loader -- had the identical defect, so live wiring would have loaded nothing and served unadjusted while logging success. Third occurrence of this class in one session. Both loaders now order by a real column and THROW rather than degrade. The Phase 2 gate is what caught it: no resolution number was quoted until transmission was proved. PHASE 1 — pipeline is now base -> FACTORS -> CALIBRATE -> GRADE. Context built in snapshotService BEFORE gradeAndCacheSlate (was line 640+, grade at 454), threaded per prop, applied to p_over before p_win is set with p_win_prefactor and a full trace retained. Hits only. Coverage 859/1140 rows (75%): 474 with all three factors, 256 two, 129 one, 281 none. PHASE 2 — TRANSMISSION PROVEN, 12/12 sign-correct, 4/4 per factor, each applied IN ISOLATION. My first table compared each factor's expected sign against the COMPOSITE change and showed 3 false failures -- with three factors firing the net can oppose any single member; that was a flaw in the test, not the wiring. Two under-side rows confirm the flip is handled: a factor raising p(over) correctly lowers p_win. Switch hitters (Bailey, Bell, Rocchio) took no spray adjustment while their other factors fired normally -- the refusal is selective, not a blanket skip. PHASE 3/4 — both maps refit on the factor-adjusted forecast; the shadow-duel baseline is VOID and restarts, since it accumulated against a different forecast. Point-in-time, 765 held-out rows: reliability 0.00795 -> 0.00828 RESOLUTION 0.00229 -> 0.00345 (variance explained 0.93% -> 1.39%) Brier 0.25398 -> 0.25305 delta -0.00093 CI [-0.00225,+0.00002] Resolution rose 51% relative. The CI TOUCHES ZERO on 4 eval dates, so the composition does NOT earn a proven keep -- three isolated passes did not grant a composed pass. INCONCLUSIVE, reported as such. The gain is far below the sum of the isolated effects, which is expected: all three run through the same pitcher-batter confrontation and share signal. PHASE 5 — 1.39% of variance is still far below what band separation needs. The pivot was correct and incomplete: the plumbing defect was real and is fixed, three proven factors reach the served number for the first time, and transmission alone did not buy grade separation. Next arc is factor STRENGTH and BREADTH, not more plumbing. PHASE 6 — rbi anomaly logged, not chased: 14.51% variance explained vs hits 1.03%, on the stat we do not serve corrected and which has no proven factors. Either the biggest lever on the board or a mirage; it deserves its own order. The byte-identical invariant INVERTED for hits by design. All 13 frozen non-hits modules verified unchanged, probabilityEstimator included -- the factors ride outside it. No new Bonferroni slot; the composed OOS claim is reported with its CI and not claimed as a pass. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
e872eff4ce |
Instrument the calibration duel forward; diagnose the resolution ceiling
— the proven factors were never wired in
PHASE 0 — two truths recorded. The swap is a BET, not an OOS win:
isotonic beat low-param on identical held-out rows (hits +0.0028, rbi
+0.0042, TB tied) and we serve low-param anyway on an untestable prior
about shared daily structure. At 19 dates nothing here can test it. And
the MIN_SLOPE catch is preserved as standing rationale: a near-zero or
negative slope collapses toward base-rate-for-everything, which LOWERS
Brier while destroying all resolution -- a metric win that guts the
product.
PHASE 1 — the duel is now falsifiable. Both corrections computed on every
hits/TB prop; p_win_lowparam served, p_win_isotonic_shadow logged in its
own try so it can never break serving. calibrationDuel.adjudicate encodes
the rule IN CODE before any forward date exists: >=10 forward dates and
isotonic winning with a date-block CI excluding zero => REFUTED, revert;
otherwise UPHELD; under 10 dates PENDING regardless of the numbers. A
date counts as forward only if NEITHER map was fitted on it -- otherwise
we would be scoring which map memorised better. Nothing swaps now.
PHASE 2 — the ceiling, quantified via Murphy decomposition:
stat reliability RESOLUTION uncertainty variance explained
hits 0.01353 0.00252 0.24532 1.03%
TB 0.01419 0.00442 0.24329 1.82%
rbi 0.00654 0.03268 0.22531 14.51%
runs 0.00788 0.00130 0.23182 0.56%
Calibration did exactly what theory says and nothing more: hits
reliability 0.01353 -> 0.00233 (-0.0112, 83% of the error removed) while
resolution moved -0.0002. Unexpected: rbi has 13x the resolution of hits
and is the one stat we do NOT serve corrected -- it needs calibration
least and discriminates most.
PHASE 2 DIAGNOSIS — NOT-TRANSMITTED, and not weak, ABSENT. Traced in code:
sprayDefense.js and platoonSeverity.js are required by NOTHING in src/,
only by analysis scripts and their own tests. The served p_win
(intelligence/probabilityEstimator.js:54) reads exactly four inputs --
game-log frequency, opp_rank_stat +/-0.03, home_away +/-0.015, and a cv
pull -- with zero occurrences of spray, platoon, hard-hit or
contact-profile. And snapshotService grades at line 454 while computing
challenger/context at 640+, so everything proven is computed DOWNSTREAM of
the grade it would inform. The three proven hits factors have never once
moved a served number.
That reframes the recent nulls: "calibrated p_win does not separate within
archetype" was never a statement about factors. The factors were not in
the forecast.
PHASE 3 — bands rebuilt on SERVED values (hits/TB low-param, rbi/runs
raw): 28 archetype slots across four stats, ZERO show lift. No longer an
open shrug -- it is the arithmetic of resolution 0.0013-0.0327 against
uncertainty ~0.23. A forecast explaining 1% of variance cannot produce
separating bands, and no correction to its numbers will change that.
HEADLINE: calibration is complete, delivered honest numbers on two stats
and zero grade separation, because the counter has no resolution -- and
the proven factors are not wired into the forecast at all. The second is
the reason for the first, and it is plumbing rather than a modelling wall.
Per-archetype grades need proven factors that actually reach p_win. Last
calibration order.
Serving unchanged from
|
||
|
builtbykev
|
74cf1ce974 |
Robust bias established; low-parameter correction replaces isotonic
PHASE 0 — sample-limit truth on record: on 19 dates BOTH stability
instruments are underpowered. LODO power 0.014-0.093 (best 0.337 across
every k tried); deploy CIs rest on 2-4 date clusters, where a
cluster-robust interval has ~1 df. This is the SAMPLE, not a fixable
instrument, and the gate-refinement loop stops here. Runs corrected: its
DATE-DRIVEN label was an artefact of the coin-flip ruler (2 reversals in
3 drops never cleared cutoff 2) -- it is an ordinary no-fittable-map
refusal.
PHASE 1 — the bias is ROBUST, tested model-free and map-free with a
date-block bootstrap. Pooled over-prediction rises monotonically -0.0076
/ +0.0428 / +0.0963 / +0.1589 / +0.2451 across deciles from 0.5 to 1.0,
sign stability 0.9946 over 17 date blocks, and 4 of 4 stats replicate
(bar was 3). Also visible: realized rate PLATEAUS at 0.65-0.68 from p=0.7
upward -- the 0.9+ bucket (0.6624) does no better than the 0.8-0.9 bucket
(0.6841). The model has no high-confidence reads, only high-confidence
numbers.
PHASE 3 — Platt, two parameters over the whole curve, shrunk toward
identity by fit-date count. Validated as a NEW estimator vs RAW with
date-block CIs:
hits a=0.406 shrink 0.565 0.2626 -> 0.2540 CI [-0.0112,-0.0069] DEPLOY
total_bases a=0.472 shrink 0.333 0.2490 -> 0.2429 CI [-0.0062,-0.0059] DEPLOY
rbi a=0.775 shrink 0.231 0.2011 -> 0.2007 CI [-0.0007, 0] REFUSE
runs a=-0.032 REFUSE
A GUARD THE FIRST RUN NEEDED: runs fitted a = -0.032. A non-positive
slope inverts the forecast rather than flattening it, and near zero the
curve collapses to a constant predicting the base rate for everything --
which LOWERS Brier while destroying all resolution. It would have scored
as a win while making the product worthless. MIN_SLOPE now refuses it by
name, with a test.
STATED PLAINLY: on the identical held-out rows isotonic BEAT the
low-param on hits (+0.0028) and rbi (+0.0042) and tied on TB. The swap is
a CAPACITY JUDGEMENT, not a measurement -- the window spans 2-4 date
blocks and that is exactly what a flexible map produces when it captures
structure shared by fit and eval. Labelled as a judgement.
PHASE 4 — hits and total_bases serve the correction, basis
direction_robust_magnitude_provisional (direction bootstrap-robust,
magnitude thin-sample and shrunk). rbi is WITHDRAWN to raw -- it was
deployed on isotonic at
|
||
|
builtbykev
|
ced40421ed |
Audit the LODO instrument: it cannot evaluate any stat, and both prior
FAILs were false
PHASE 0 — the gate at
|
||
|
builtbykev
|
1f40014256 |
Power-derive the LODO threshold: hits restored through the gate, rbi/runs
routed as date-driven PHASE 0 — threshold derived BLIND, before any stat was re-read. A reversal is informative only if that date's Brier delta is distinguishable from zero at its row count. Per-row Brier difference d_i = (pc-y)^2 - (p-y)^2, so SE(n) = SD(d)/sqrt(n) and n* = (SD(d)/|effect|)^2. Pooled across all four stats so no single stat's verdict could shape the threshold deciding it: pooled rows 3,417 | SD(d) 0.09816 | |effect| 0.01175 n* = (0.09816/0.01175)^2 = 69.8 -> 70 The hand-chosen 20 sat at 0.54 SE -- a coin flip. That is the defect this removes, and why the previous verdict moved with the number. Committed as calibrationRegistry.LODO_MIN_HELD_ROWS = 70 with LODO_THRESHOLD_BASIS; a test recomputes (SD/effect)^2 and asserts it equals the constant, so it cannot drift from its own justification. The derivation script prints no stat verdict, no date and no reversal. PHASE 1 — LODO at n*, applied cold: hits 5 informative drops, 0 reversals PASS total_bases 4 informative drops, 0 reversals PASS rbi reverses 2026-08-01 (n=99) FAIL runs reverses 08-01 (n=86), 08-05 (244) FAIL hits held-out deltas -0.0041/-0.0080/-0.0192/-0.0140/-0.0139 across 123-272 row dates, favourite sign holding on every testable drop. THIS IS THE INSTRUMENT FINALLY POWERED, NOT VINDICATION OF A PREDICTION -- the withdrawal at |
||
|
builtbykev
|
6ae11f1193 |
LODO-gated provisional calibration: total_bases deploys, hits withdrawn
PHASE 0 — I applied factorGate's >=40 date-cluster floor to a calibration layer without challenging the binding. That floor is a cluster-robust interval bar for a CAUSAL claim. Calibration makes no causal claim, has a bounded failure mode (it can only over- or under-shrink) and consumes no Bonferroni slot. Its real risk is that the correction is DATE-DRIVEN, and leave-one-date-out tests that directly -- a STRICTER bar, since a cluster count cannot detect a single day carrying the effect. The >=40 floor is retained, correctly scoped as the PROMOTION bar. PHASE 1 — both guards codified, 11 tests, green before Phase 2. Demonstrated on live data: raw population violated=true, mean_p 0.4962, both_sides_share 0.9763; after dedup violated=false, mean_p 0.6694. The null guard's test demonstrates the trap explicitly, since (null-1)**2 is 1 and (null-0)**2 is 0 so a Brier over nulls equals the win rate. PHASE 2 — LODO: hits n=1140 dates=17 2 reversals (07-22 n=20, 07-26 n=25) FAIL total_bases n=1050 dates=7 0 reversals, 0 sign flips PASS rbi n= 630 dates=5 1 reversal (08-01 n=99) FAIL runs n= 597 dates=5 2 reversals (08-01 n=86, 08-05 n=244) FAIL Threshold sensitivity reported because the verdict moves: total_bases passes at every held-size threshold, runs fails at every one, and hits fails ONLY when 20/25-row dates are admitted. I fixed MIN_HELD_ROWS=20 before seeing which stats passed and did not move it afterwards to preserve a deploy. Honest caveat: a per-date Brier delta on 20 rows has a standard error several times the effect, so the instrument is underpowered per-drop -- an argument for pre-registering a higher threshold, which is a Roundtable call, not one to make while holding the results. PHASE 3 — total_bases DEPLOY-PROVISIONAL, band [0.6-0.8]. hits, rbi and runs REFUSE. HITS WAS BEING SERVED CALIBRATED AND IS NOT ANY MORE. snapshotService hardcoded it since S91; it fails LODO, so it is out. A stat that cannot survive dropping one day was never calibrated, it was fitted to that day. The consequence is real -- hits props become unstackable for chain.chainAcross -- and it errs toward withdrawing a claim rather than preserving one on a fragile verdict. Deployment is now driven by a frozen, tested CALIBRATION_DEPLOYED set, not a hardcoded stat name. PHASE 4 — calibrationRegistry, 14 tests. Deploy needs BOTH gates, neither waivable. reverify auto-demotes on the first breach (CI stops excluding zero, or the favourite bias flips sign) and logs the breaking date. Promotion needs the original >=40 bar. A provisional deploy that cannot be taken away is just a deploy. PHASE 5 — TB bands rebuilt on calibrated values, 625 eval rows. The two-bar rule still bites: calibrated YES, proven NO, so they stay a base-rate read, now honestly numbered. Every archetype still collapses to one band -- calibrated p_win separates within archetype no better than raw. PHASE 6 logged only: the dead gradient is buried (hits~TB > runs > RBI, and RBI has the SMALLEST bias, so the skill-driven-gradient mechanism did not survive); the refused set is a map of missing inputs; a low-parameter calibrator is queued unbuilt. p_win never mutated; calibration rides as p_win_calibrated with calibration_status provisional. No Bonferroni slot consumed. Counter and frozen clusters byte-identical. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
f976df47b8 |
Settle model_snapshots + four-stat calibration: works, deploys nowhere
Settlement done (15,484 written). Calibration improves held-out Brier on
all three stats it can be fitted for, beating every factor ever tested.
No stat deploys: the date-cluster ceiling is 17, not 90.
PHASE 0 CORRECTIONS: 71,192 snapshots unsettled, not 22,032. Span is
07-19 -> 08-06 = 19 dates, not 05-01 -> 08-04. Nothing has ever been
rescaled on any stat -- all four are base-rate bands today -- and the TB
"inversion confirmed" was the units-bug artifact, UNPROVEN.
PHASE 1, two integrity findings both caught by the gate:
1. The dupe check hard-failed on snapshot id 33875. model_snapshots is
written by the cron at 14/19/22/1/3 UTC and an unordered .range() walk
over a live table returns overlapping pages. Fixed with .order('id').
2. 12,894 rows were logged AFTER first pitch -- cycles at ET 21/22/23 on
the game date (10,738) plus 664 the next morning. A 01:00-UTC cycle is
21:00 the previous evening Eastern, same game date, two hours into the
slate. Tested for contamination: bias +0.0058 in-game vs +0.0008
pre-game, so NOT sharper, just late. Excluded for provenance.
THE ENABLING MOVE DID NOT ENABLE. 71,192 rows collapse to 4,799 distinct
pre-game props (2.5x cycle fan-out, then 97.6% both-sides duplication,
then the pre-game filter). Hits ends at 1,140 rows against the ledger's
existing 1,312. Date-clusters: hits 17, TB 7, rbi 5, runs 5.
THE MEASUREMENT THAT NEARLY WENT THE OTHER WAY: 97.6% of props carry both
sides, whose p_wins sum to ~1 and whose outcomes are complementary, so
the raw population is pinned to 0.5 by construction. Measured that way
the counter reads +0.0002 on hits -- "perfectly calibrated" -- and would
have overturned three sessions. Deduped to the model-picked side it is
+0.0868. The tell was mean p_win sitting at 0.4998 on every stat.
PHASE 2/3, isotonic point-in-time, split by cumulative rows (a
60%-of-dates cut left 143 fit rows under the fitter's 200 minimum; still
strictly temporal):
hits n=1140 bias +0.0868 brier 0.2626 -> 0.2511 d -0.0115 CI [-0.0139,-0.0097]
TB n=1050 bias +0.0834 brier 0.2490 -> 0.2438 d -0.0052 CI [-0.0061,-0.0045]
rbi n= 630 bias +0.0164 brier 0.2011 -> 0.1965 d -0.0046 CI [-0.0092,-0.0010]
runs n= 597 bias +0.0410 no map fittable (173 fit rows < 200)
ALL FOUR REFUSE: 2-4 eval date-clusters against a floor of 40. The floor
is the order's own and was not relaxed to force a pass.
A NULL THAT SCORED ITSELF: the first run reported hits at Brier 0.5567,
worse than predicting 0.5 for everything. fitIsotonic returns null below
its minimum, applyIsotonic then returns null per row, and (null-1)**2 is
1 while (null-0)**2 is 0 -- so the "Brier" was silently just the win rate
(0.5684). This project's signature Number(null)===0 breach, in my own
measurement code. Now a hard refuse.
PHASE 4: the bias is NOT a uniform shift. Identical favourite-longshot
shape on all four stats -- near zero or negative at 0.5-0.6, rising to
+0.21 to +0.28 above 0.9. The counter is over-confident specifically
about its favourites, which is the population a user acts on. Gradient is
hits ~ TB > runs > rbi, not the TB > RBI > runs anticipated.
PHASE 5/6 NOT RUN -- both gated on a Phase 3 deploy that did not open.
PHASE 7, refusal accuracy, first real measurement: refused props are
FURTHER from a coin flip than graded ones (TB refusals went over 21.6% of
the time). The obvious explanation, that refusals concentrate on players
who barely played, was tested and does not hold -- refused mean 3.20 AB
vs graded 3.39, 6.6% vs 6.2% with <=1 AB. So we pass on what we have no
INPUT for, not on what we cannot call. Refusing to invent a number
without a reference stays correct; the pass is not landing on the
genuinely uncertain props.
p_win never mutated, no p_win_calibrated written since nothing deployed,
no Bonferroni slot consumed. Counter and frozen clusters byte-identical.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9
|
||
|
builtbykev
|
23d1b13176 |
runs + RBI: mostly-base-rate confirmed, and one level deeper than expected
Nothing proved. For RBI even the ARCHETYPE split is theatre, so the honest grade is the POOLED base rate. PREMISE NOTE: the order's closing line says the batter board is per-archetype-graded after this. Nothing has been rescaled for hits or total_bases either -- no archetype slot has ever reached sample and gradeBands remains built, gated and unwired. This is the fourth stat measured, not the completion of three. AUDIT: RBI 935 clean / 43 games; RUNS 617 clean / 33 games. Zero quarantined. No archetype slot reaches 500 -- and the signature archetypes the order names are the two SMALLEST slots on the board, RBI->DRIVER at n=24 and runs->CATALYST at n=9. RUNS is refused structurally before any factor is tested: 33 game clusters against a 40 floor. INPUTS RECONSTRUCTED rather than declared missing. lineup_context only covers 08-04 onward while settled rows start 07-31, so 187/617 runs rows joined. But the play-by-play cache runs from 05-01 and the batting order IS the order batters first appear -- slot, power-behind and reach-base all rebuilt point-in-time, coverage 187 -> 574. RBI, all THEATER: risp_opportunity +0.0047, extra_base_skill +0.0010, risp x extra_base +0.0056. RUNS, all refused on clusters and all pointing the wrong way: +0.0043 / +0.0008 / +0.0054. THE COMPOUND IS THE WORST VERSION IN BOTH STATS. The causally-correct compound was the most promising factor on the sheet and is the most harmful in each. Two multipliers that individually carry nothing do not cancel -- they compound each other's noise. Distinct from the collapsed-sequence lesson: there the product of two REAL effects was too small to use; here the product of two NULL effects is worse than either. THE ARCHETYPE DOES NOT RESCUE IT, and this is where the session nearly went wrong. The base rates look strongly differentiated (RBI DRIVER 0.609 vs BOMBER 0.413; runs GHOST 0.716 vs BOMBER 0.460). Gated directly against the pooled base rate: RBI +0.0010 CI [-0.0034,+0.0050] THEATER; runs -0.0028 CI [-0.0147,+0.0108] candidate at k=33. DRIVER's 0.609 is n=23 -- small-slot noise wearing a decimal point. Read off the table instead of gated, this would have shipped as "archetype differentiation is real and large". It is not. THE CROSS-STAT PATTERN THAT IS REAL -- the counter over-predicts every batter counting stat measured: total_bases p_win 0.5698 vs actual 0.5074 bias +0.0624 rbi p_win 0.4860 vs actual 0.4313 bias +0.0547 runs p_win 0.5949 vs actual 0.5749 bias +0.0200 Across four stats and three sessions, calibration is the systematic defect and factor scarcity is not. TB's held-out isotonic fix (-0.0039) still outperforms every factor tried on any stat, all null or theatre. NO RESCALE. Nothing proved, nothing certified calibrated, no slot at sample, and for RBI the archetype split is itself theatre -- so the honest band is the pooled base rate, which gradeBands returns by construction. Counter and frozen clusters byte-identical. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
6a327d9114 |
total_bases: every power factor is THEATER, and a units bug nearly hid it
PREMISE CORRECTION: the per-archetype rescale is not "proven and live on hits". gradeBands was built, gated and explicitly NOT wired two orders ago -- no hits archetype slot reached sample, every band came back base-rate, and only defense_by_direction proved pooled. This applies an unvalidated-at-archetype-level method to a second stat. FULL-HISTORY AUDIT: 988 clean settled TB rows (101 quarantined, 948 with p_win), 341 players, and only 9 DISTINCT GAME DATES. No archetype slot reaches 500 -- BOMBER 340, GHOST 147, BRUSH 55. Confirmed short on full history, not a windowed artifact. The 9-date figure matters more than the row count: ~49 games means any game- or venue-borne factor has almost no replication here. THE BASELINE HAD TO CHANGE, to a harder null. TB lines vary (1.5 on 559 rows, 0.5 on 345), so a per-line personal base rate would rest on ~2 rows per player-line and would have to be invented. The null is the counter's own p_win, which already prices the line -- beating the champion, not beating "he's due". THE UNITS BUG, caught, and it had produced the best result in the programme. The first run reported barrel_rate at Brier -0.0095, the largest improvement ever measured here. fromStatcastRow returns barrel_pct as a FRACTION (0.06) while the raw table stores 0-100, so (0.06 - 7.8) * 0.018 clamped EVERY row to the maximum negative shift. That uniform downward push "improved" Brier purely by leaning on the counter's over-prediction and contained no barrel information at all. Same family as the S80 trap, inverted. exit_velo was a second bug -- the column is avg_exit_velo, so it read null on every row and reported n=0. A zero is a wiring bug until proven an honest absence. GATE with units fixed, 138 cumulative tests: barrel_rate n=707 shift 0.0364 brier +0.0036 THEATER exit_velo n=707 shift 0.0229 brier +0.0022 THEATER hard_contact_allowed n=707 shift 0.0260 brier +0.0033 THEATER park_weather_hit_type n=651 36 entities PENDING (k<40) platoon_severity n=481 PENDING (n<500) THE PREDICTED INVERSION WENT THE OTHER WAY. BOMBER x barrel_rate is +0.0114, the single most harmful cell in the table, exactly where the strongest proof was predicted. GHOST +0.0012. All sample-blocked so not a verdict, but recorded so it is not claimed later. AND IT IS NOT DOUBLE-COUNTING -- tested and refuted: corr(barrel, p_win) = -0.061, the counter is not pricing barrel at all. The duller answer is corr(barrel, counter RESIDUAL) = -0.012. Barrel is a real skill that carries no information about what the counter gets wrong at this line. That also closes the S81 lead: hard_hit r=0.153 at n=295 drifted to 0.135 at n=383 and is THEATER at n=707. THE REAL FINDING: TB is miscalibrated, not under-factored. mean p_win 0.5698 vs actual 0.5074, bias +0.0624. Held out on a strict time split (fit < 2026-08-02, eval 651 unseen rows): raw 0.25007, constant de-bias 0.24740 (-0.00267), isotonic 0.24621 (-0.00386). Worth more than any factor tested and the only intervention pointing the right way -- and still refused at the corrected bar on 32 clusters. A CANDIDATE, not a result. It also explains the units bug's fake success exactly: a blanket downward shift is a crude de-bias. NO RESCALE. Nothing proved, nothing certified calibrated, no slot at sample -- every band would be the honest base-rate band gradeBands already returns by construction. Counter and frozen clusters byte-identical. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
8ab6557faa |
Collapsed sequence edge: two proven links whose product is too small to use
Nothing in this failed, which is what makes it the most instructive
negative so far. Link 1 proved (MAE 3.22 -> 2.80 batters faced). Link 2's
quality grain proved (2.70pp of realized separation). Both point-in-time,
both past cumulative correction. Their product is 0.37pp and detecting it
would take 52 seasons.
FRAMING CORRECTION: the order says Link 2 proved you can't predict the
reliever. Half true -- the INDIVIDUAL grain failed at 17.2%, but the
QUALITY grain PROVED. Pen-season-quality is a measured predictor here, not
a fallback after a failure.
TWO OF THREE SPECIFIED INPUTS COULD NOT BE USED HONESTLY. Pen archetype
did not prove (0.5669 vs a 0.5309 modal baseline, interval spanning zero)
so building it in would chain on an unproven link. And hitter
approach-identity -- "fastball-hunter", "finesse-vulnerable" -- does not
exist in this registry; MLB batter archetypes are BOMBER/GHOST/TORCH/
BRUSH/DRIVER/FLEX/ALPHA/HYBRID/CATALYST. Inventing one to condition on is
the fabrication the gate exists to catch. A power/contact split derived
from the sequence data was tested as a SEPARATE gated addition instead;
neither half proved.
GATE on the concentrated subset, 114 cumulative tests:
early-exit x WEAK pen n=1931 brier -0.0001 CI [-0.0014,+0.0010] NOT_PROVEN
early-exit x STRONG pen n=2574 brier 0.0000 CI [-0.0011,+0.0010] THEATER
all early-exit later ABs n=6869 brier -0.0001 CI [-0.0007,+0.0005] NOT_PROVEN
pooled all later ABs n=17891 brier 0.0000 CI [-0.0004,+0.0003] THEATER
Not pooled-diluted -- the concentrated subset was gated alone and is no
better.
THE CEILING, which explains it. The descriptive pass found the predicted
direction (+0.74pp weak pen, -0.79pp strong pen). The magnitude is the
problem and it is structural:
P(faces pen | early-exit flagged) 0.8075
P(faces pen | starter goes deep) 0.7149
exposure the flag actually buys 0.0925
hit-rate swing across pen quality 0.0394
MAX JUSTIFIABLE ADJUSTMENT 0.00365
actually applied 0.01930 -> 5.3x over-movement
A hitter's 3rd/4th plate appearance is ALREADY against the bullpen 71% of
the time when the starter is projected to go deep. Link 1 lifts it to 81%
-- nine points of extra exposure, not a change of opponent. The 5.3x
over-movement is precisely why the mirror subset reads THEATER rather than
as a small true effect.
A correctly-scaled version is not detectable either: 0.37pp is 0.37 SE at
n=1,931; the corrected bar needs n=168,488, an 87x shortfall, ~52 seasons.
STRUCTURALLY CLOSED, not sample-blocked. Waiting does not fix it.
NOT WIRED, and the self-check deliberately not wired either -- flagging
line-divergence on an adjustment measured as absent would advertise an
edge we just showed does not exist, which is fabricated reasoning one
layer up.
THE LESSON: link-by-link validation guarantees each link is real. It does
not guarantee the chain transmits anything. Size the multiplicative
structure BEFORE building -- one exposure term of 0.09 reduces a genuine
3.94pp signal to noise and no downstream care recovers it.
Link 3 confirmed skipped. Parallel track logged unchanged: TB n=948
pooled, BOMBER x TB 340, short by 160.
Counter and frozen clusters byte-identical.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9
|
||
|
builtbykev
|
b2e4c6c4fb |
Link 2 at the coarse grain: pen QUALITY proves, archetype does not
The refinement was right. Naming the individual reliever failed; the same
question at the grain the chain needs passes, and it transmits more than
anything else measured in this chain.
WHY IT WAS WORTH RE-ASKING: last session's null (the pen is on average no
softer, +0.0010 on 35,760 PAs) does NOT rule this out, and treating it as
though it did would have been the error. An average washing out is fully
consistent with quality VARIATION mattering. It does -- actual arm quality
moves the hit rate monotonically across quartiles, 0.2244 / 0.2293 /
0.2410 / 0.2501, a 2.57pp spread, larger than the whole times-through-
the-order effect.
CLUSTER UNIT CORRECTED, THEN CHECKED RATHER THAN ARGUED. Last session
refused Link 2 partly as team-borne (30 bullpens, the park ceiling). My
first re-check was that 76% of pen-quality variance is within-team -- but
that is a statement about TREATMENT variance, not about where errors
correlate, and stopping there would have been picking the convenient
answer. Measured the actual thing: ICC of prediction error by team =
0.0261, design effect 1.41, SEs inflated ~19%. So the verdict was run
three ways:
unclustered CI [-0.0067,-0.0010] excludes zero
team-clustered (30) CI [-0.0086,-0.0003] excludes zero (below the
40-cluster floor -- indicative, not a pass)
design-effect adjusted CI [-0.0072,-0.0005] excludes zero
QUALITY GRAIN PROVES on the concentrated elevated-early-exit subset:
n=501 team-games, 426 clusters, MAE 0.0294 -> 0.0260, delta -0.0034, CI
[-0.0063,-0.0005] at 110 cumulative tests. Pooled also proves, so it is
not a subset artefact.
ARCHETYPE GRAIN DOES NOT: 0.5669 vs a 0.5309 modal-guess baseline,
corrected interval [-0.1073,+0.0268] spans zero. Two grains tested, one
earned a place -- penQuality.js exposes no archetype and a test asserts
it.
WHAT LINK 3 RECEIVES, which is the number that actually matters -- not
the MAE gain but realized outcome separation, prediction strictly
point-in-time:
predicted BEST pen 167 games 2,044 PAs hit rate 0.2231 +/-0.0180
predicted WORST pen 167 games 1,799 PAs hit rate 0.2501 +/-0.0200
2.70pp separated, intervals non-overlapping, capturing nearly all the
2.57pp available at the quartile grain. Caveat stated not buried: the
tercile cut is chosen in-sample; the prediction driving it is not.
BUILT: penQuality.js + 9 tests. Abstains below 5 prior club games and 40
arm appearances -- a league-average stand-in would assert "this is an
ordinary bullpen", which is a claim, and usually the wrong one for exactly
the clubs whose pens just turned over.
Link 3 is unblocked on a proven Link 2 at the quality grain only. Not run
here; this order scopes to building and gating Link 2.
Parallel track logged unchanged: TB n=948 pooled, BOMBER x TB 340, short
by 160.
Counter and frozen clusters byte-identical.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9
|
||
|
builtbykev
|
e4dae0e6b0 |
Reliever chain: Link 1 proves, Link 2 does not, and the premise inverts
The causal insight is right -- the game is a sequence and the matchup does shift mid-game. The direction is backwards, measured on 93,663 plate appearances from 1,238 games pulled free from statsapi. LINK 1 PROVES. Starter batters-faced, point-in-time from his own prior starts only, clustered on the pitcher: MAE 3.2226 -> 2.7990, delta -0.4236, CI [-0.6006,-0.2731] at 0.9995 corrected for 107 tests, 1,706 starts across 204 pitchers. It finds the tail the chain needed -- early exits are a 23.2% base rate, model-flagged starts are 34.0% early, lift +10.8pp. Scope correction inside Link 1: the order specifies fatigue x GAME SCRIPT, but game script is not available at grade time -- whether he gets hit tonight is the thing being projected, not an input to it. Only the workload half is measured; the in-game half is recorded as a live feature, out of scope, rather than quietly folded in. LINK 2 DOES NOT PROVE, twice over. Model accuracy 17.2% vs an 8.6% baseline -- doubling it sounds good and is not, since naming a specific arm is wrong five times in six. And structurally the entity is the BULLPEN: 39,629 post-starter plate appearances across 30 clubs is 30 readings, below the 40-cluster floor, the same permanent ceiling as park geometry and team defence. LINK 3 NOT RUN, per the order's own rule. THE PREMISE IS REFUTED, and this chains on nothing so it was safe to measure: vs STARTER n=48,492 hit rate 0.2444 +/-0.0038 vs BULLPEN n=35,760 hit rate 0.2373 +/-0.0044 The pen is 0.7pp HARDER. The specific effect the chain exists to exploit -- early exit making later at-bats softer -- is +0.0010 on 35,760 PAs. A well-powered null, not a sample problem. What IS real is times through the order: TTO1 0.2351 -> TTO2 0.2515 -> TTO3 0.2518. A starter does decay as the lineup sees him again, but that advantage is SURRENDERED when he leaves, not extended -- the pen is harder than his second and third time through. A modern bullpen is a queue of fresh specialists throwing one inning each; there is no tiring arm to punish. So the insight survives inverted, and Link 1 stays valuable for the opposite reason it was built: a likely early hook predicts the hitter LOSES his third-time-through look (0.2518 -> 0.2373 on that PA). The mispricing is on hitters who get an EXTRA look at a starter going deep. BUILT: predictionGate.js + tests -- the two-part gate for a continuous prediction. factorGate binarises outcomes for Brier, which would destroy a target like batters faced. Same discipline, same THEATER verdict, real scale. PRE-REGISTERED NOT RUN: Link 2' using a PA-weighted bullpen AGGREGATE rather than a named arm. Recorded rather than substituted in -- running Link 3 on a swapped-in Link 2 is the assumed-link failure the order forbids. Given the premise result its expected value is now low. PARALLEL TRACK logged: total_bases n=948 pooled, BOMBER x TB 340, short by 160. Sample-readiness only, not a verdict. Counter and frozen clusters byte-identical. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
3081c92e00 |
Per-archetype grade bands: built, gated, and the rescale blocked twice
The premise does not hold. proven-status.js run fresh: PROVEN_SET is EMPTY, no archetype x stat reaches the gate. pitcher_contact_profile has a CI upper bound of exactly 0.0000 and platoon_severity is held on 4.5%-contaminated splits, so the proven set is one factor, pooled, not three archetype-conditioned ones. The specific pattern the order names -- defense strong for GHOST/BRUSH, null for BOMBER -- is the one I measured running the OTHER WAY yesterday, both noise-dominated. But the second blocker is new and matters more, because it would stop the rescale even if the factors had proved: the grade does not separate within any archetype. Every archetype collapses to ONE band at the corrected bar, because bands merge when their intervals overlap and publishing two letters we cannot tell apart is a distinction we have not measured. Uncorrected, so the ranking is visible rather than hidden by the bar, this INVERTS the order's design. The order gives contact types the factor-rich treatment and power types honest base-rate, reasoning that single-game hits are variance for a power profile. Measured: BOMBER n=466 corr(p_win,outcome) +0.207 quintiles 0.75 0.62 0.60 0.48 0.48 GHOST n=192 corr(p_win,outcome) -0.007 quintiles 0.47 0.63 0.74 0.58 0.45 BOMBER is the one archetype the model ranks, and it splits into a real A 0.660 / B 0.481 at 95%. GHOST is flat, and non-monotone -- its most confident reads hit 47% while its middle reads hit 74%. Shipping as specified would have given the factor-rich treatment to the archetype the model reads worst and left base-rate on the one it reads best. That is mechanically sensible in hindsight: a power hitter's hit tracks whether he can damage the arm, a contact hitter's depends on balls finding holes. BOMBER's split does not survive the cumulative correction at 106 tests. Exposing it by loosening the correction is the curve-to-make-A's the order forbids, so it stays one band. BUILT: gradeBands.js -- lift against the archetype's OWN base rate (the same 62% is lift for a 45% profile and a deficit for a 68% one), indistinguishable neighbours merged, thin bands PROVISIONAL not dropped, Wilson intervals widened by the cumulative correction. The two-bar rule is structural: proven-alone, calibrated-alone and neither all return base_rate with the reason stated, so with nothing proven no factor-informed band can be produced at all. reasoning() is built and tested but NOT wired to the card -- there is no per-archetype band being served, so attaching the copy now would ship product language for a rescale that does not exist. NOT BUILT: the specified power-type reason "the matchup edge is in total_bases". total_bases is recorded INCONCLUSIVE (+0.0038, CI [-0.068,+0.075]). Wiring it would assert an edge measured as indistinguishable from zero -- the exact fabricated-reason failure this module exists to prevent. BOMBER x hits is 29 rows short of the gate and is the archetype the model actually reads. That is the first slot to test, not GHOST. Counter and frozen clusters byte-identical. No letter was moved. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
6b17f79367 |
Per-archetype re-audit: no slot reaches 500, and the replication unit
decided everything The premise does not hold. prove-hit-factors.js has no date filter anywhere in it and pages the full table -- there was never a window to widen. Full clean history is 1,266 rows, not 2,715. platoon was not "proved" last session, it was explicitly held on 4.5%-median-contaminated season-to-date splits, and pitcher_contact_profile was demoted. The proven set going in was one factor, not three. STEP 1: no archetype slot reaches n>=500 on full history. Best is BOMBER at 408, and BOMBER is the most common archetype on the board. GHOST 173, BRUSH 64, DRIVER 43, CATALYST 16. These are confirmed genuinely short, not artifacts. STEP 2 is where the real finding is. park_hits initially PROVED at 619 rows across 45 games -- but those games only ever visited 14 distinct park values. A park effect is replicated across parks, and unmodelled park heterogeneity is confounded with the thing being estimated. Each factor is now clustered on the coarser of the game and the entity its treatment rides on. That flipped two verdicts and confirms Kev's causal-correctness thesis from a new direction: defense_by_direction has 442 hitter-team units of replication where crude team defense has 26. The correct atom is not just more accurate, it is the only one measurable at all. park_hits (14) and defense (26) can never be validated however long the ledger runs -- the same ceiling as park dimensions, reached independently. Also fixed a bar I got wrong last session: I transplanted the 500-row floor onto clusters, which refused a factor with 1,059 rows over 85 games while answering neither question. Two floors now -- rows>=500 for a stable estimate, clusters>=40 for a trustworthy interval. Not a lowered bar: park_hits and defense are still refused. PROVEN: defense_by_direction only, pooled, [-0.0054,-0.0012] at 99 tests. It stays POOLED-ONLY -- no per-archetype reasoning wired, nothing grandfathered. The card must not say "GHOST: defence matchup strong" because we have not earned that sentence. The predicted fingerprint did not appear either: BOMBER -0.0036 vs GHOST -0.0024, the opposite direction, both noise-dominated. Recorded so it is not claimed later. RESCALE: NOT READY. One proven factor worth -0.0031 Brier. Rescaling on that is relabelling. Counter and frozen clusters byte-identical. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
7b85934dc3 |
Under-querying vs out of data: the answer depends on the unit
The platoon test's n=452 described how much of the JOIN survived, not how much data exists. There are 1,266 clean settled hits rows and zero quarantined ones. platoon_splits had been ingested from tonight's lineups only (315 players), so any hitter who settled a prop without appearing in an ingest-day lineup was silently absent from every test. Backfilled all 380 hitters (81 fetched, 0 unresolved). Re-ran on 1,059 rows, up from 452. THE DEMOTION IS THE HEADLINE. pitcher_contact_profile, the strongest proven factor in the programme (-0.0064, CI [-0.0113,-0.0014]), roughly halved to -0.0034 on more than double the sample and its corrected interval now spans zero. The Bonferroni denominator also rose to 55, which widens every interval -- but a denominator cannot move a point estimate, and that halved on its own. platoon and platoon_severity now clear the bar and are NOT promoted. Upper bound -0.0001, on season-to-date splits that contain the games they predict: measured contamination is 4.5% median, 12.4% at p90, 137% worst. I had assumed ~1%. They stay CANDIDATE pending point-in-time splits. GAME-LEVEL IS A DIFFERENT PROBLEM. game_context held zero weather rows ever -- not because the fetcher was wrong (it correctly targets Open-Meteo's archive) but because ledger_entries keys a game as mlb:2026-08-03:Away@Home and game_context keys it as mlb:823437. Every lookup missed and NULL columns read as honest absence. Third occurrence of that class. Fixed the join: 96/101 settled games now carry actual archived weather, park dimensions backfilled 15 -> 30 venues. But 928 total_bases rows sit on 47 games at 17.6 rows per game. Park and weather assign one value per game, so resampling rows would have manufactured a pass. factorGate now resamples clusters when rows carry one and judges sample against effective_n; unclustered rows keep the original path byte-for-byte. Verdict: 47 clusters < 500, and the point estimate is +0.0011 -- worse, not merely unproven. Weather needs ~57 more days. Park dimensions need never: there are 30 ballparks in MLB, so a venue-constant factor can never reach 500 independent units. That bar was built for player-level factors and does not transfer. Wind is refused. We have speed and bearing for all 96 games; we lack park orientation, and 220 degrees is blowing out at one park and in at another. Using speed alone would assert an effect while discarding the sign that decides what it is. Counter and frozen clusters untouched. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
ff037e40c2 |
Re-adjudicate: nothing to demote, and close the hole that would have mattered
There is nothing to re-adjudicate. The proven set is empty and always has
been -- verified three ways: proven-status reports EMPTY, validatedSkills()
returns {} for every archetype, and zero conditioning entries have ever
reached PROVEN. The one PROVEN feature is recent_frequency_prior, which is the
incumbent counter itself, proven by the S78 ablation as ~100% of the
champion's resolution. It is the baseline every challenger is measured
against, not a conditioning interaction, and demoting it would leave the model
with nothing to grade from.
A correction to the premise: the cumulative gate did NOT catch a false
positive last session. It caught nothing, because there was nothing in the
proven set to catch. What it did was tighten alpha from 0.0026 to 0.0013
within one session, which demonstrated the mechanism working rather than a
demotion. So steps 3 and 4 -- demote, recalibrate -- are vacuous here, and
readjudicateAll says so plainly rather than glossing a no-op.
But the worry behind the order was well founded, and the audit found the real
exposure: promote() did not require the cumulative denominator. It checked n,
lift and CI, and nothing stopped a future session from testing eight
hypotheses, correcting by eight, and promoting on a p-value that would not
survive the programme's real denominator. That is precisely the hole that
makes a retroactive re-adjudication pass necessary later, so it is closed at
promotion time instead. isSufficient now refuses evidence carrying no
correction, evidence corrected against fewer tests than the cumulative count,
and any p-value that does not clear 0.05 over its own test count. The same
rule guards a PROVEN conditioning entry.
The second audit found two of four analysis scripts still correcting
per-session; pitcher-prove-k and tb-solo-and-interactions now use the
cumulative ledger, so the correction is native on every path.
reAblation.js is the standing second line: pure and injectable, so the
decision rule cannot drift from the gate's, and every verdict records both
p-values and both test counts so a demotion is re-derivable by anyone. A
feature promoted at alpha 0.05/20 can demote on the same p-value once the bar
is 0.05/60 -- correct, because the bar rose only after the programme had more
chances to get lucky. No fresh measurement is PENDING_RETEST and never a
demotion: absence of a re-test is not evidence, and demoting on it would
punish whichever stat happens to be off-season.
Net effect on the proven set is zero. No demotions, no recalibrations, and no
public ledger event -- announcing "recalibrated after re-adjudication" when
nothing changed would itself be a false signal of rigour.
4,238 tests green (337 suites); web build exit 0; counter byte-identical.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9
|
||
|
builtbykev
|
ece2b9f5f9 |
Ingest defence, and make Bonferroni cumulative across the programme
Two things shipped that stand regardless of sample. DEFENCE. Statcast Outs Above Average is free on the host we already pull six feeds from, so there was nothing to decide. 514 fielders, aggregated to team level -- the unit a batter's prop actually needs, the defence behind the pitcher he faces -- and persisted as 31 team rows. Verified in production. Cubs +56 best, Mariners -29 worst. Unknown is not zero, and it bites unusually hard here: an OAA of 0 is a REAL reading meaning exactly average, so coercing absence to 0 would assert that every unmeasured fielder is league-average, which is the commonest defensive profile there is. team_defense also carries as_of_date in its primary key from the first row -- statcast_aggregates was built upsert-in-place and that silently made every backtest leak the games it predicted, so point-in-time is available here before it is needed rather than after a wrong answer. A bug worth recording as a class: BASE already ends in /leaderboard, so the new feed built a doubled path and 404'd. Because a failing feed degrades to an empty index by design -- correct, so one broken source cannot fail the whole pull -- it surfaced as "fielding_oaa: 0 rows", which reads exactly like "Statcast has no fielding data". Graceful degradation makes a wiring bug look like an honest absence. CUMULATIVE CORRECTION. Bonferroni had been applied per session throughout: a run testing eight features corrected by eight. Across a programme's lifetime that is wrong in the dangerous direction, because every order gets a fresh generous alpha and the false-positive rate compounds quietly. Correcting by 8 when sixty have been tried is how a noise result eventually gets recorded as PROVEN with a p-value to point at. The denominator is now distinct hypotheses ever tested, persisted, and it moved 19 -> 38 within this session alone, alpha 0.0026 -> 0.0013. Re-tests deliberately do not inflate it: re-asking the same question on more data is not a new shot on goal, and counting it would punish the discipline of waiting for sample. THE MEASUREMENT. The differential the theory predicted is present: defence correlates with the counter's residual at +0.130 for GHOST, the contact and speed archetype, and -0.018 for BOMBER, the power archetype. A GHOST's hits depend on whether anyone can range to the ball; a BOMBER's barrels clear the defence entirely. So a flat BOMBER result is the theory working rather than the test failing. It is not a result. GHOST is n=104 against a 500 bar, with p=0.188 against a corrected alpha of 0.0013 -- three orders of magnitude short. Both are recorded as CANDIDATE with their measured lift, tagged contact-skill, so the re-run at full sample compares against a recorded baseline. Nothing proved, so nothing was recalibrated and nothing shipped. 4,228 tests green (336 suites); web build exit 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
ac1361486e |
Build the conditioning registry, and a probe so "proven" stops drifting
The order opens with "two proven clusters live". They are not proven -- the
proven set is empty -- and this is the fourth consecutive order to start from
a stronger claim than the measurements support. Correcting that in prose four
times has not worked, so this session adds scripts/proven-status.js, which
recomputes the answer from the ledger: hits LOSES (-0.096, CI excluding zero),
total_bases INCONCLUSIVE (+0.004), strikeouts INCONCLUSIVE (+0.259 at n=57).
It deliberately reports sample readiness separately from recorded verdicts, so
"n>=500" can never again be read as "passed".
A counting error worth recording. The first read of the top-volume archetype
said BOMBER x hits was 641 rows -- gate-ready. It is 287. model_snapshots
holds one row per prop PER SNAPSHOT CYCLE, so joining it to ledger_entries
counts each ledger row once per cycle it appeared in. Deduping on the ledger
row id gives the true figure, and my own status script had the same bug until
it was fixed. That is the difference between running the gate and being short
by 213.
So no archetype x stat combination reaches the gate. BOMBER x hits at 287 is
the closest; pitcher archetypes are untestable at 58 settled strikeout rows
across all of them, so the pitcher half of this order could not be run.
The registry is built: recordConditioning keys archetype x underlying-skill x
interaction x status with measured lift, and the skill tag is MANDATORY and
enforced -- untagged entries are refused, and PROVEN without sufficient
evidence is refused. validatedSkills() returns the coherent profile as it
stands, which is {} for every archetype, by design.
BOMBER x hits conditioning was tested across the order's categories and every
result is underpowered: arsenal (barrel x breaking share) incremental +0.043,
batted-ball (launch x pitcher GB) +0.001, contact quality -0.020 and -0.015,
K x K -0.063. Within BOMBER the counter still leads on hits, 0.218 to 0.160,
consistent with the closed pooled negative.
One bug fixed mid-run: fromStatcastRow maps percentage and raw fields only and
does not carry pitch_mix, so the arsenal category first reported n=0 for every
row -- it was measuring nothing rather than failing. Without catching it,
"arsenal doesn't matter" would have been recorded from a column that was never
populated.
On defense: I looked for a derivable proxy before calling it unsourceable, and
there isn't one. We ingest no fielding data at all, and opposing pitchers'
hits-allowed conflates pitching with defense, so it would validate the wrong
skill. It needs Savant's fielding endpoint -- free, same host as the five
feeds already ingested -- and it is not sourced here, because sourcing it to
test at n=282 would answer nothing.
Nothing proved, so nothing was recalibrated and nothing shipped.
4,221 tests green (335 suites); web build exit 0.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9
|
||
|
builtbykev
|
9538e11198 |
Derive the lineup K-rate free, and fingerprint the cap fix
Two premise corrections first. Pitcher stuff features have NOT proven solo through the gate -- every one was refused on sample (n=57 against 500). Four exceed the effect-size bar (arm angle -0.250, whiff +0.213, k rate +0.206, chase +0.195), which is why they are worth pursuing, but clearing one of three thresholds is not passing. And the carrier was not blocked only on the lineup input: that input was built and measured last session at 94.7% coverage. What blocks it is n, and n was being throttled by the grading cap. RUNG 1 IS DERIVED AND COSTS NOTHING. Opposing-team K-rate comes from joining the opposing roster to the batter k_pct values already in statcast_aggregates -- no new feed. The improvement this session is that it is PA-WEIGHTED: an unweighted roster mean counts a 12-PA callup the same as an everyday starter, which is not the lineup a pitcher faces. That change alone reversed the term's sign. Unweighted, the lineup term HURT the model (0.1738 -> 0.1285). PA-weighted, it HELPS (0.1738 -> 0.1953). Same hypothesis, same data -- the derivation was the problem, not the signal, which is the entire argument for deriving the best honest version before sourcing anything. Head-to-head is now +0.2592 with a CI of [-0.0167, +0.5645], very nearly excluding zero, at n=57. Within archetype, the two strata come out with OPPOSITE signs -- FLAME incremental -0.152, non-FLAME +0.145 -- and the pooled value (+0.077) sits between them, which is the shape a conditional effect makes and is invisible when pooled. That is what stratifying was for. But n is 20 and 24, the standard error on a correlation there is about 0.22, and the direction contradicts the theory that predicted a stronger effect for finesse arms. It is recorded as a structure to re-test, not as a finding. Rungs 2 and 3 are NOT triggered. A rung fails only once it has been fairly tested, and Rung 1 is n-blocked rather than failed. Sourcing confirmed lineups now would be paying for precision on top of a proxy we have not yet measured. THE RESULT THAT DECIDES THE TIMELINE: yesterday's cap raise is fingerprinted in production at 907 grades per snapshot, up from 334, with strikeouts going 6 to 17. That puts n>=500 for pitcher Ks about a week out instead of three months. Operational note: the manual internal snapshot endpoint now 524s at the Cloudflare edge because grading the full board exceeds 100s -- the run still completes server-side (this very snapshot was written by a 524'd request) and the cron is in-process, so a 524 there is not a failure. Nothing proven, nothing calibrated, nothing shipped. The counter remains anti-predictive on strikeouts at -0.064 and the skill model leads it by 0.26. 4,221 tests green (335 suites); web build exit 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
843c8c6d4b |
Build the pitcher engine, and find the cap was eating the whole board
Strikeouts are NOT proven -- n=57 against a bar of 500. But the finding that matters is not a correlation. THE CAP. Measured on the live slate via the refusal diagnostic: 1,244 unique gradeable props exist, the 500 cap graded about 334, and because dedupeProps takes first-row-wins in FEED ORDER, what survives is decided by feed position rather than value. Pitchers are 2.6% of a batter-dominated feed, so we were grading SIX strikeout props a slate against 32 available -- putting n>=500 three months away for every pitcher stat. Pitcher props were never being refused (graded 5, refused 0, suppressed 0); it was truncation. Raised 500 -> 1500 on measured cost: 721ms per prop at concurrency 5 is about 179 seconds for the full board, against a cron that runs five times a day and a fire-and-forget caller that never holds an HTTP response. statsapi is free and unlimited. Concurrency stays at 5 -- one variable at a time. This unblocks every n-blocked stat in the programme, not just pitchers. THE ENGINE. pitcherEngine.js is its own engine, not the batter engine pointed at pitchers: the batter model asks whether contact becomes a hit and reads contact quality, the pitcher model asks whether the plate appearance ends without contact at all and reads stuff. Archetypes are FLAME (whiff-led), SCALPEL (chase-led), SINKER (pitches to contact) and DEFAULT, and a test asserts the weight keys are not the batter engine's. The projection is K% by log5 against THIS lineup, times batters faced, through a binomial. An unclassifiable arm gets the balanced map, never a guessed archetype. THE MEASUREMENT, at n=57 and contaminated. Four solo features clear the 0.15 effect bar and fail only on sample: arm angle at -0.250 -- the largest correlation measured anywhere in this programme -- then whiff +0.213, k rate +0.206, chase +0.195. The batter cluster's best was 0.135. Head to head, pitch-v1 resolves 0.1285 against the counter's -0.0639, delta +0.192 with a CI spanning zero. That negative is the interesting number. The counter is ANTI-PREDICTIVE on strikeouts: counting a pitcher's recent Ks is worse than useless, because his recent totals track which lineups he drew and how long he was left in rather than his skill. It is the one stat where the incumbent has no defensible edge. A bug caught on the way. resolveTeam wants an abbreviation and the game log supplies full team names, so the roster join silently resolved nothing and the first run reported 0% lineup coverage -- the theorized stuff x lineup carrier was never being tested, not failing. Fixed; coverage is now 94.7%. The carrier still shows no incremental signal over whiff alone, and adding the lineup term lowered head-to-head resolution, which is recorded rather than dropped. Calibration was not reached: nothing passed the first bar. The batter model and the counter are byte-identical, verified by diff. 4,221 tests green (335 suites); web build exit 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
c0621e7aa2 |
Measure the batter cluster: the proven set is empty, and hits is closed
PREMISE CORRECTION FIRST, because it defines the bar. total_bases has not
passed BAR 1. Its head-to-head is inconclusive at parity -- delta +0.004 to
+0.007 with a CI spanning zero -- and it is contaminated, and no feature of
its passed the gate. It was described last session as the first challenger
that did not LOSE, which is not the same as proven. If it is installed as the
frozen proven reference and every other stat is held to "the identical bar
total_bases cleared", the bar becomes "be inconclusive at parity" and the
whole cluster passes on a null result. The proven set is EMPTY.
HITS IS NOW A FINAL ANSWER. At n=803 it clears the gate's sample requirement,
so its features were properly TESTED rather than refused: every one fails on
effect size (max marginal |r| 0.053 against a 0.15 bar), every interaction's
incremental contribution collapses to about zero, and the model loses
head-to-head by 0.096 with a CI excluding zero. That is a well-powered
negative and hits should be closed rather than retried.
The rest are n-blocked: total_bases 383, rbi 391, home_runs 228, runs 188,
against a bar of 500. Two leads are worth carrying. home_runs barrel rate has
a marginal r of -0.135, and the sign matters -- higher barrel rate goes with
the counter OVER-predicting, which would be a correction rather than a new
predictor. And runs batterK x pitcherK has the largest incremental in the
cluster at +0.132, with a clean mechanism: strikeouts destroy plate
appearances, and a PA that never happens cannot score.
RBI deserves a caveat rather than a verdict. It is power times OPPORTUNITY,
and we ingest no baserunner state at all, so half its mechanism is missing. A
weak RBI result is evidence that we are modelling half the stat.
total_bases was held frozen: git diff on skillProjection against the prior
commit is empty. The counter is untouched.
Also fixed and verified in production: the point-in-time retention shipped
after yesterday's refresh had already run, so statcast_history was empty, and
its first run then failed on a hand-enumerated schema that had already drifted
from its source ("could not find the 'swing_pct' column"). The refresh itself
still succeeded and wrote all 1,387 aggregate rows, which confirmed the
best-effort guard in prod. The table now mirrors the source via LIKE and the
writer passes rows through whole. Verified live: 1,387 rows retained at as_of
2026-08-03. A usable point-in-time window starts 2026-08-04.
Stage B has nothing to calibrate. Everything now waits on a point-in-time
window and on sample -- both waiting problems, not building problems.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9
|
||
|
builtbykev
|
4aab18096f |
Prove both on total bases -- and find that my own fix destroyed the backtest
Nothing passed. Nothing promoted. Counter byte-identical. THE BLOCKER, which is the real finding. statcast_aggregates is upserted in place and holds exactly one as-of date. Yesterday's skill backtest was honest only by accident: the nightly refresh was unreachable code, so the profiles sat frozen at 2026-07-21 -- before the settled window. Repairing that cron was right for production and it refreshed them to today, destroying every prior version. Scoring a 2026-07-25 game now uses a season aggregate that contains that game. Point-in-time validation is structurally impossible from that table, so every number in this run is contaminated and directional, and none of it is a gate verdict. Fixed forward: statcast_history retains a dated snapshot on every refresh, so point-in-time becomes "as_of_date < game_date, most recent". Retention is best-effort and cannot fail the refresh; both properties are unit-tested. It has one day of data, which is not yet a window. SOLO BASELINE, n=383, Bonferroni across 12 tests (alpha 0.00417): nothing passes. hard_hit_pct is closest at marginal r 0.135 with p 0.0080, failing both the 0.15 effect bar and the corrected alpha. And it drifted DOWN from 0.153 at n=295 -- an estimate regressing as noise averages out, not an effect firming up. I called that number encouraging yesterday; on 88 more rows it is fading, and it should not keep being quoted at its best value. INTERACTIONS, each scored by partial correlation against the counter residual controlling for both of its own components: none pass. Only barrel x power archetype has an incremental exceeding its parts (-0.101 against 0.019) at n=260 -- the shape Discipline 2 predicts, but a lead, not a finding. A methodological catch worth keeping. The archetype conditioner was first built as barrel_pct over league barrel -- a monotone transform of one of its own components -- so the "interaction" was barrel squared, measuring nonlinearity in barrel rate rather than any archetype effect, and it produced this run's only positive result. A Gauss-Jordan pivot test does not catch that, because the two columns differ by a scale factor. Fixed with a scale-free collinearity check plus real archetype labels joined from model_snapshots. Without it this document would have reported a fabricated interaction as the session's finding. COMBINED vs COUNTER on total bases: 0.2718 against 0.2647, delta +0.0071, CI [-0.065, +0.079] -- inconclusive, and the first time a challenger has not lost. The same engine on hits was -0.116 with a CI excluding zero. That contrast is the whole argument for total bases, and it is what the physics said: contact quality governs extra bases, not whether a grounder finds a hole. Also built: the compound TB projection. skillProjection no longer refuses total bases -- a deterministic bases-per-hit multiplier had made P(TB>=2) exactly P(hits>=1), a relabelled hits curve. It is now a convolution over per-PA base outcomes with hit-type shares shifted by skill. Non-degeneracy is locked by test. 4,204 tests green (334 suites); web build exit 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
c7cc8f5e52 |
Build the gate, run it, and find we were proving things on the wrong stat
PREMISE CORRECTION FIRST. statModel.js and correlateValidator.js do not exist in this repository. The validation spec's only prior form is src/services/python/blueprints/unconventional.py -- a Flask blueprint in the Python service that is offline in production, scoring NBA factors against a warehouse that was never populated -- and tests/unit/supplementSystems.test.js requires only fs and path while defining its own validateFactor inline at line 368. Those tests assert a re-implementation of the thresholds, not an implementation, which is exactly why they passed for months while nothing was connected. The diagnosis behind the order is right -- every challenger was measured without a gate -- but the cause is that there was no gate on the Node side to import. So it is built, to the exact spec. correlateValidator: n>=500, |r|>=0.15, p<0.05, Bonferroni across the sweep. The p-value is exact rather than approximated (t-transform through a regularized incomplete beta) and is verified in the suite against known values, because scipy is not available here. Pairs with an unknown side are dropped, never zero-filled -- a zero-fill inside a correlation does not add noise, it invents a point at the origin. THE RUN, hits, n=570, Bonferroni-8: every skill feature fails, and not narrowly. The strongest marginal correlation against the counter's residual is 0.062 against a 0.15 bar. That is an effect-size failure at a sample that would have found a real effect comfortably -- a clean, well-powered negative. The head-to-head agrees: value engine 0.0499 against the counter's 0.166, delta -0.116 with CI [-0.189, -0.043]. Not promoted. THE RUN, total bases, n=295: cannot be tested, and that is the finding. hard_hit_pct shows a marginal r of 0.153 -- above the threshold -- and exit velo 0.124, refused solely because n is 205 short of 500. It is the most encouraging number this work has produced, and it is what the physics predicts: contact quality governs extra bases, not whether a grounder finds a hole. We have been testing skill inputs on the one stat where they should not matter much. Two things the run forced. Feature verdicts are now PER STAT, because marking these DEAD sport-wide on hits evidence would have killed, for total bases, the features that look most alive there -- per-sport doctrine one level deeper. And the gate now reports r and p even when underpowered, because "not enough data yet" and "nothing here" demand opposite decisions and a bare refusal was hiding the best signal on the board. Next: build the compound TB projection (skillProjection still refuses total bases by design, since a deterministic bases-per-hit made P(TB>=2) identical to P(hits>=1)), accrue to n>=500, re-run this gate. Leave hits alone. 4,200 tests green (334 suites); web build exit 0; counter byte-identical. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
258d8a6655 |
The skill engine: built, gated by construction, and Stage A honestly lost
Built src/services/model/ -- the forward, archetype-selected, skill-based projection, as a challenger. The champion is untouched. featureRegistry makes "earn its place or it's out" structural rather than aspirational: CANDIDATE / PROVEN / DEAD per feature per sport, liveFeatures() returns PROVEN only, promotion requires n>=200 with positive lift and a CI excluding zero, and there is deliberately no override argument. It ships with exactly ONE proven feature -- the incumbent counter, because it is the only one with a measurement. A test asserts that with only PROVEN features allowed the projection returns null, so an unproven model cannot reach a user by accident. The three champion adjustment layers are registered DEAD with their reasons so they cannot be silently rebuilt. skillProjection is a PA outcome tree: K and BB combined by log5 odds-ratio against league (both identities unit-tested), then archetype-weighted contact quality against contact allowed, then Binomial(PA, p_hit) mixed over a PA distribution. Archetype is a FEATURE SELECTOR, not a nudge -- BOMBER reads barrels at 0.50 and ground-ball speed at 0.00, GHOST inverts it -- and a test locks that the same hitter read two ways moves more than 0.15. STAGE A: IT LOSES. Out-of-sample on 570 settled hits props with 91.9% opposing-pitcher coverage, resolution 0.0499 against the champion's 0.166, delta -0.116 with CI [-0.189, -0.043]. It is not selective either: its eight most confident picks hit 50%, a lift of -0.065. Not promoted. The gate did its job on its first real test, which is the point of having built it that way. Two false starts, both recorded because they nearly produced a wrong verdict: statcast_aggregates stores PERCENTAGES, so raw rows made bip = 1-29.6-17.1 and refused 568 of 576 -- the honest-absent guards made a units bug loud instead of silent, and the conversion now lives at one chokepoint. And the first run resolved an opposing pitcher for 1 of 570 rows, because ledger team/opponent are NULL, so it would have reported "skill-v1 loses" while measuring a batter-only model with no matchup in it at all. The verdict above is from the corrected run. The loss is real but partial: park was passed as 1.0, handedness and opportunity_drift never fired, PA is season-PA over a constant, and the skill profiles carry no recency at all while the champion has a last-5 term. Also fixed: the Statcast nightly refresh was unreachable code. It sat inside tick() below "if (!HOURS_UTC.includes(h)) return" while testing h === 11, so it had never run once; the aggregates were 13 days stale and both of its alerts were in the same dead branch. It now runs on its own tick, and the test that passed happily throughout -- it only checked the string existed -- is replaced by one that asserts it is not behind the guard. 4,182 tests green (333 suites); web build exit 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
c551bf0340 |
Reality assessment: the forward model exists, wired to the wrong side of the pipe
READ-ONLY. src/ and web/ untouched. Inventoried every forward-model component against the real objective -- a forward matchup projection, not an edge number. The finding is that all of it already exists and is already loaded in production, and 100% of it sits DOWNSTREAM of the grade in challenger columns nothing serves. The served p_win reads three features and a game log; it has never seen a pitcher. Inputs are HAVE, not missing: statcast_aggregates carries 1,354 rows (750 pitchers, 604 batters) with exit velo, launch angle, barrel, hard-hit, whiff, chase, pitch mix, GB/FB, arm angle, and handedness complete on every row. Real gaps are team defense and catcher/umpire. So Stage A is a plumbing-and- modelling job, not a data-acquisition job. Found along the way: the Statcast nightly refresh is unreachable code. tick() returns for any hour not in HOURS_UTC (14,19,22,1,3) and the refresh block then tests h === 11, which that guard can never admit. The mechanism data has been frozen at its 2026-07-21 backfill for 13 days, and the block's own failure alert sits in the same dead branch -- the identical silently-guarded- out shape as the settlement outage. Design shows the counter: every factor label the SIGNAL BREAKDOWN renders is a restatement of recent frequency (l5_hot_vs_line, l20_over_line, back_to_back, home_game) plus several structurally-NBA labels (referees, coach pace, starters out) inside a baseball product. Not one names a pitcher, pitch type, handedness or park. The card's forward-read slots already exist and go unfilled -- the surface needs feeding, not redesigning. On what changes: the prior measurements were outcome-accuracy, not edge, so the metric was right and the question was narrow. proj-v1.1 and hits-v1 stay correctly refuted as DISTRIBUTION swaps on thin inputs -- neither tested a matchup-fed projection. arch-v1 is a market-relative nudge by construction and is the one component genuinely measured on the wrong axis. AT CEILING is provisional: measured only against features the champion already reads. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
d8bf7765db |
Decompose the champion: its whole edge is a hit-rate counter
READ-ONLY. src/ and web/ untouched; 4,159 tests still green. WHAT THE CHAMPION IS. probabilityEstimator is five lines of arithmetic: the empirical frequency of (stat > THIS line) over the game log, blended 0.6/0.4 with the last-5 frequency, then +/-0.03 opponent, +/-0.015 home/away, a cv>0.40 pull toward 0.50, and a clamp to [0.10, 0.95]. It reads three features. featureCache retains a dozen more that p_win never touches. THE ABLATION IS EXACT, NOT A REFIT. Every adjustment is closed-form from stored features and the consistency step is linear, so each layer subtracts algebraically out of the stored p_win -- no re-estimation, no re-fetch, no lookahead possible. Per stat, paired bootstrap: removing ALL THREE adjustments changes resolution by NOTHING on every stat hits -0.0059 total_bases -0.0015 rbi +0.0106 runs +0.0130 walks +0.0008 and rbi's home/away is mildly HARMFUL (+0.0053, CI excludes zero). So ~100% of the champion's resolution is base+recency: how often this player has cleared this number lately. Everything else is decoration. A CORRECTION. Pooled, the champion resolves 0.46; per stat it is 0.196 (hits) to 0.499 (rbi). Pooling stats with different base rates inflates correlation, so 0.46 should not be quoted as the champion's resolution. Last session's paired differences remain valid; only the absolute level was inflated. THE BIGGEST LOSS IS NOT A MISSING FEATURE -- IT IS THE CLAMP. 358 of 1,741 settled rows (20.6%) sit on the boundary, so the model emits a constant there and cannot rank a fifth of the book at all. And that constant hides two opposite failures: 0.900 covers home_runs-under truly winning 99.5% (9.5pts under-confident) next to hits-under truly winning 51.9% (38.1pts over- confident). PROB_CEIL=0.95 makes the 99.5% case inexpressible. Global over-prediction is +3.5pts, +7.6 on total_bases. None of this needs new data. ONE REAL MISSING-WEIGHTING LEAD: opportunity_drift, residual corr +0.156 on hits and +0.145 on total_bases -- it REPEATS across independent stats, unlike the weather hits on TB which sit inside the expected false-positive count (70 tests at alpha .05 expects 3-4). And we already compute it: arch-v1's opportunity axis uses it and extracts nothing (delta +0.0001). Wrong implementation, not a missing feature -- opportunity must scale the rate, not nudge the probability. ARCHETYPE IS UNMEASURABLE, NOT REFUTED. Only 2 of 41 labels (BOMBER, GHOST) reach n>=40 settled rows and every mean residual straddles zero. That is "we have not measured it", and it does not license acting in either direction. Why every challenger has failed is now legible: the ladder and hits-v1 REPLACE the frequency question with a fitted distribution; the environment axis adds inputs the champion ignores. Asking the frequency question at the traded line is the thing that works. Flagged, not fixed: model_snapshots.outcome is NULL on all 22,032 rows -- the retention table built for exactly this replay was never settled, so labels had to be joined from ledger_entries. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
f897c7ec06 |
hits-v1 fingerprint PASSED: 72/72 written in prod, 45 outside the band modelled anyway
The prod-write fingerprint that was blocked by the odds outage has landed on the first snapshot after deploy. hits-v1 records exactly as the live-board verification predicted, and the takeable axis behaves as specified -- scope is book identity, never price shape. The verdict is unchanged: hits-v1 is REFUTED and stays unpromoted. This confirms only that it is recording, so the forward accrual can judge the backtest. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
3ba3dd28f3 |
Scoreboard every challenger; diagnose the 429 as odds-api, not PropLine
PROMOTE-THE-EARNED. Nothing was promoted, because nothing earned it -- not because the bar was held high. Measured on the same bar that refuted hits-v1: own rows only, direction-aligned, paired bootstrap, promote only on a CI excluding zero. arch-v1 n=1741 delta 0.0000 CI[-0.0050,+0.0054] inconclusive contact-v1 n=1055 delta +0.0008 CI[-0.0052,+0.0069] inconclusive proj-v1.1 n=1664 delta -0.0301 CI[-0.0543,-0.0060] reliably WORSE matchup/tb-v1/hits-v1 n=0 genuinely pending (rows dated 08-02+) arch-v1 is the interesting one: it MOVED 76% of rows by 2.5 points on average and resolution is identical to the champion to four decimals, on the moved rows too. That is active movement carrying no information -- a finding, not a pending verdict. These are true prospective holdouts: arch-v1 and contact-v1 wrote p_win at grade time into their own columns before the game. Nothing recomputed. THE 429, read-only. The premise was that we re-pull the full picture every slot and blow the quota. Measured: PropLine is at 5 calls of 3,000/day -- 0.17%. One snapshot is ONE PropLine call per sport, all markets comma-joined. There is no request-pattern problem, so a change-based pull cannot fix it and no tier upgrade is needed. The 429 is odds-api: 478/500 MONTHLY, blocked at 95%. oddsService falls through silently when PropLine returns empty, and the backup's quota gate throws the error -- so an empty slate is indistinguishable from an outage and the message names the wrong provider. Flagged for its own order. Could NOT verify PropLine movement endpoints: docs are auth-gated and the keys are production-only. Not asserted either way. The movement-as-data argument stands on its own merits and should be justified that way, not as a quota fix it isn't. Book-breadth invariant written down: we never discard books. All are kept and shown (DISPLAY_BOOKS = MODEL + REFERENCE + DFS); DFS pick'em is excluded from PRICING only, because a fixed-payout shaded number is not a market price. Verified this is already what bookRoles.js does. Champion byte-identical; every challenger stays wired. 4,159 tests green (332 suites); web build exit 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
2394fb04a1 |
Record the hits-v1 fingerprint as PENDING, and why
The prod-write fingerprint did not land: the odds provider is returning 429 (quota exhausted), so the snapshot refuses with gradeCount 0 and the MLB board has been frozen since 07:30 UTC. The 14/19/22 UTC cron slots failed the same way, all before this change deployed -- hits-v1 sits inside the snapshot's existing try/catch, is purely additive, and had zero grades to attach to. Firing is already verified against the real production snapshot through the real attachProjection path (158/159). What is pending is only confirmation that the deployed process writes the columns, which needs a slate the pipeline can fetch. The exact fingerprint query is recorded in the spec. The odds quota exhaustion is a live outage of the whole grading pipeline and is flagged for its own order, not folded into this one. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
07626de3de |
hits-v1: built on the right structure, measured honestly, REFUTED
Hits was diagnosed as a family mismatch: 84% of hits rows trade at 0.5, so the stat rides on P(0), and a negative binomial has unbounded support and no notion of opportunity at all. hits-v1 models it as the bounded conversion it is -- N ~ the player's empirical at-bat distribution, hits|N ~ Binomial(N,q), with the multiplier scaling q (conversion) and never N (opportunity). STEP 0 confirmed the inputs before the model existed: 30/30 real ledger players, 100% combined-input coverage. Every read goes through knownRate -- a row with no atBats is dropped, never counted as a 0-at-bat game. It FIRES: 158/159 hits props (99.4%) on the live production snapshot, through the real attachProjection path. Scoping by book IDENTITY rather than price shape kept 94 out-of-promotion-band props on the board, 93 of them modelled -- 59% that a price rule would have deleted. And it LOST. Point-in-time replay (game log truncated strictly before each row's game_date, real grade-time multiplier), hits-only, direction-aligned, n=242: resolution champion 0.195 / ladder 0.048 / hits-v1 0.026. Paired bootstrap on the same rows: hits-v1 - ladder = -0.022, CI95 excluding zero. Not promoted. The value is in what it eliminates. The family was wrong AND the mean was not the constraint -- hits-v1 moved the line-0.5 mean 0.554 -> 0.581 toward a 0.598 base rate while resolution fell. What is left is per-prop discrimination: the ladder's inputs, not its distribution. The pre-registered fallback is recorded as WRONG rather than deleted. It said hits might be genuinely low-resolution for anyone; the champion scores 0.276 on the identical 189 rows, so there is real signal and the ceiling claim was the comfortable reading, not the honest one. Its own control refuted it, and that control was already in hand when the branch was written. hits-v1 stays wired as a challenger writing its own ledger columns so the forward accrual can confirm the backtest. Champion, ladder, ranking, calibration, reference ruler and the four accruing verdicts are byte-identical -- the diff has zero deleted lines. Tests 4,156 green (332 suites); web build exit 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1sivYNqY2TS5ftykmHBU9 |
||
|
builtbykev
|
f67245e1e5 |
Re-stamp A: 862 rows recovered by honest join (not 936 -- see deviation)
Database only; no application code changed, so the served path, champion and reference ruler are byte-identical. RESULT: 862 rows re-stamped from the takeable LOCK-TIME price in lock_lines, 862/862 now anchored to takeable books, tagged price_source='archive_restamp', quarantine lifted. 812 pending clean rows recovered into the accruing verdicts. Holdout verification: 2,792 rows, 862 re-stamped included, 0 re-stamped rows non-takeable, 144 still excluded, 0 quarantined rows leaked, and 0 NON-TAKEABLE rows remain in the holdout population since 2026-08-01. DEVIATION, stated rather than buried: the order authorised 936. That figure came from a takeable book posting the same LINE. Requiring what a re-stamp actually needs -- that book's price for the GRADED SIDE at LOCK TIME -- resolves 862. Of the other 74, 73 have a takeable side-price only OUTSIDE the lock window and 5 are genuinely one-sided markets. I did not widen the window to reach 936. A takeable price captured hours after the grade is a later market moment, not a lock price; substituting it is precisely the reconstruct-vs-join line this order was fenced against, and it would have been invisible in the totals -- showing only as a cleaner-looking 936. Those 74 were also RE-TAGGED, because their old label had become a lie: recoverable_same_line -> no_takeable_lock_price_for_side. A future attempt reading the old tag would have been invited to widen the window and call it recovery. takeable was RECOMPUTED from the recovered price rather than carried over -- the old flag was computed FROM the contaminated price and was wrong on its own terms. 101 rows had their flag change, which is the direct measure of how wrong it was. Provenance travels with the data (price_source), on the same principle as is_proxy: a value recovered by a later join is not identical in kind to one captured natively at grade time, even when it is the same number. EVIDENCE FOR THE NEXT ORDER'S INVARIANT: 5 of the excluded rows are one-sided TAKEABLE markets, and betrivers/hardrockbet legitimately quote one side only. A guard that inferred takeability from price shape would throw away real markets while still admitting a DFS book at -119 -- takeability is book IDENTITY, never price extremity or one-sidedness. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc |
||
|
builtbykev
|
e29ab6fd6a |
Takeable enforcement: verified on real rows, 1,006 tagged, re-stamp call ready
PART 1 verified by inducing the REAL rowsFromSnapshot over REAL lock_lines
rows from prod. Three cases, 0 non-takeable anchors:
Narvaez (dabble/kalshi/prizepicks/smarkets, NO takeable book)
-> book=null, price=null, takeable=null [honest absent]
Schwarber(bovada/dabble/novig/PINNACLE before draftkings)
-> draftkings +102 [pinnacle SKIPPED, proving TAKEABLE not MODEL]
Ohtani (dabble/onexbet before draftkings) -> draftkings -266
Narvaez is the case that matters: pre-fix he was stamped dabble +104
takeable=true; he is now honestly absent.
A HARNESS BUG RECORDED: my first verification pulled live /api/odds/mlb,
which returned {"error":"Odds data temporarily unavailable"}. The script
read that as 0 props and printed "all from takeable books? true" -- a
VACUOUSLY TRUE pass. I caught it only because I also printed the book list
and it was empty. Same family as the silent-false traps: a probe that finds
nothing looks identical to a probe that finds nothing wrong.
PART 2: 1,006 rows tagged via the purpose-built quarantine_reason at ROW
level with three sub-cases (recoverable_same_line 936, no_takeable_quote
49, takeable_line_differs 21). getModelAggregate ALREADY excluded
quarantined rows, so the public record and the n>=20 gate were clean
automatically; all five committed holdout scripts now carry the exclusion
explicitly.
PART 3 -- the re-stamp call is now fact-based. The takeable LOCK-TIME price
is recoverable for 936/1,006 (93.0%) from lock_lines, the correct
instrument. Only 431 appear in closing_captures, which is the wrong timing
for a lock price anyway.
LINE CONTAMINATION ANSWERED (previously unverified): the stored line
MATCHES a takeable book's line on 936 (93.0%), DIFFERS on 21 (2.1%), and is
unverifiable on 49 (4.9%) where no takeable book quoted the prop at all.
That makes it cleanly row-level: re-stamp the 936 as an honest JOIN and
recover 886 pending rows for the holdouts, or leave all 1,006 excluded.
Either way the 21 + 49 stay out -- re-stamping those would invent a lock
price, or a line, we never captured. Nothing re-stamped; Kev's call.
Gates: 4,111 tests / 330 suites green; next build exit 0.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc
|
||
|
builtbykev
|
08e5c908e6 |
Takeable audit: the ledger is contaminated, and I caused it
READ-ONLY. Nothing enforced or fixed; the five challengers untouched. VERDICT: gaps exist, and one is LIVE CONTAMINATION of the ledger -- the exact table every accruing holdout resolves against. book, locked_odds and the takeable flag ITSELF are being stamped from books you cannot bet: DFS dabble (707 rows, 24% of all rows), offshore bovada (214), onexbet (42), exchange kalshi (7, mean |odds| 1120). 0% before 2026-08-01. 47.9% on 08-01. 42.5% on 08-02. It began the day I widened the books for display. LEAK LOCATED, not inferred: recordPipelineGrades indexes byKey over the FULL display-widened props list, then prefers that prop -- book: (prop && prop.book) || g.book, and locked_odds/takeable both fall back to oddsForSide(prop). The grade is computed on a MODEL book and the ledger row is then re-stamped from whatever book indexed first. The takeable flag is therefore not merely mislabelled: it is computed FROM the contaminated price, so it is wrong on its own terms. The served grade path is clean TODAY (428 grades, 100% MODEL books), so dedupeProps' gate works. But MODEL_BOOKS is NOT a subset of TAKEABLE_BOOKS -- pinnacle is model-eligible and correctly not takeable -- so the projection may anchor to a reference line by design. Harmless while pinnacle returns nothing; live again when it recovers. BLAST RADIUS bounded but growing: 47 contaminated rows have already settled (21% of settled rows since 08-01) and ~700 are still pending and will settle into the holdouts. The damage is mostly ahead of us, which is what makes this urgent rather than historical. NOT VERIFIED and not claimed either way: whether the stored `line` is also contaminated. It traces to the graded prop, but I did not check it end-to-end; the enforcement order should. The prediction-vs-reference distinction HOLDS and must not be collapsed: the prediction target must be takeable, while fair_prob / consensus / edge stay reference. The bug is not the three-way split -- it is that one write path ignores it. Stack sequenced in the plan: (a) takeable enforcement, (b) structural Number(null)===0 guard (hits will re-trigger it -- its 0.5 lines make P(0) the whole game), (c) hits. Carry-forward: tb-v1 verdict, the third pre-registered branch, and the 100s Cloudflare timeout vs a ~115s snapshot. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc |
||
|
builtbykev
|
aa1228ec42 |
tb-v1 report + plan: diagnosis on trial, branch pre-registered
Firing verified on a real prod snapshot: 10/10 total_bases props carry proj_tb_p_over. The snapshot HTTP call returned 524 (Cloudflare's 100s origin timeout vs a ~115s snapshot) but the work completed server-side -- confirmed from the ledger rather than assumed. Face validity is good and diagnostic: means agree almost exactly with the ladder (1.813 vs 1.833), so this is a SHAPE-ONLY intervention, which is what was intended. Component rates are plausible, and Carroll's triples rate (0.112, far above his peers) is a clean check -- he is a speed player and the model sees it. AN OBSERVATION I AM NOT RESOLVING BY EYE: tb-v1 reads systematically LOWER than the ladder (0.424 vs 0.540 at the same mean). That is the expected DIRECTION, since the NB overstates P(>=2) by treating a home run as four accumulating events -- but whether 0.424 is right or an overcorrection is not knowable from face validity. A ~1.8-TB hitter clearing 1.5 empirically sits nearer 45-50%, between the two. I am not claiming tb-v1 is better; the holdout decides. BRANCH PRE-REGISTERED, before the result, so the verdict cannot be reinterpreted afterward: improves -> family-mismatch HOLDS, similarity stays off the critical path, hits is next; does not improve -> hypothesis WRONG and the mean-weakness/similarity branch REOPENS. Also recorded: I hit Number(null)===0 in my own new module -- a null component rate treated as a measured zero, the difference between "never triples" and "we don't know his triple rate". A test caught it. Sixth appearance of this trap in this codebase, and it caught the person writing the warnings about it. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc |
||
|
builtbykev
|
48706210fe |
Diagnose proj-v1.1: concentrated mean failure, NOT a similarity problem
READ-ONLY. Nothing built or fixed; the four challengers untouched. 41% OF THE REPORTED GAP WAS A MEASUREMENT ARTIFACT. p_win is P(graded side); proj_p_over_line is P(over); 31.4% of settled rows are UNDER-graded, so comparing them raw measures the ladder backwards on a third of the sample. Matched + direction-aligned (n=437): 0.252 vs champion 0.352, not 0.108 vs 0.331. The PRODUCT is not making this mistake -- I checked; projectionChallenger normalises both to the over basis deliberately. The error was in the measurement. THE LOSS IS CONCENTRATED. hits (n=245, res 0.060) and total_bases (n=49, res 0.009) are 67% of rows and carry essentially no signal. Everything else is fine or better: walks 0.519 vs champion 0.544, runs mean 0.345 vs 0.392, and on DOUBLES the ladder's mean BEATS the champion's (0.207 vs -0.062). IT IS THE MEAN, NOT THE SHAPE. On the two failing families the mean itself carries no signal (0.052, -0.019) against the champion's 0.158 and 0.085. Where the mean is good the probability is good -- shape follows mean. A HYPOTHESIS I TESTED AND DISPROVED: prediction compression. I expected P(>=1 hit) to sit in a narrow band and fail to rank. It does not -- spread ratio 0.94 overall, 0.80 for hits, 0.94 for total_bases. The ladder has comparable spread; it is spread in a direction uncorrelated with outcomes. Recorded because it was a plausible story the data refused. PRIORS AND PLUMBING CLEAN. proj_factors carries form_rate, combined_multiplier and breakdown on every row; proj_point 100% populated with sane centres (hits 0.830 vs line 0.578). Not the environment-style silent-null failure. NAMED CAUSE (structural, flagged as hypothesis not finding): the count model mismatches those two stats. total_bases is a WEIGHTED SUM (1B..HR = 1..4), so an NB treats one home run as four events and mis-states variance -- and TB has the worst result in the table. hits is BOUNDED BY AT-BATS and mostly traded at 0.5, so almost everything rides on P(0), the region where the wrong family hurts most. walks/runs/doubles ARE genuine low-rate counts and are exactly the ones that work. FIX BRANCH: targeted per-stat fix for hits and total_bases. THIS REMOVES THE MLB SIMILARITY BUILD FROM THE CRITICAL PATH -- that branch assumed a GLOBAL mean weakness, and the mean is fine or better on three of six stat families. Similarity may be worth building later, on evidence, not on this. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc |
||
|
builtbykev
|
f5997778a2 |
Dormant-layer audit: nothing to connect; proj-v1.1 is live and losing
READ-ONLY. Nothing connected, built or wired; the accruing challengers were not touched. "Dormant" meant three different things and in no case is the answer "connect it". DISTRIBUTION LADDER IS NOT DORMANT. projection/distribution.js is consumed by projectionChallenger (proj-v1.1), live on every snapshot at 94.2% coverage (276/293) with 437 settled rows since 2026-07-23. It is a FOURTH accruing challenger, and it is LOSING: resolution 0.108 vs the champion's 0.331. That verdict is no longer thin. It is also PER-STAT and doctrine-correct -- nine distinct league priors (hits 0.90, total_bases 1.45, home_runs 0.15, ...) each feeding a gamma-Poisson posterior into a negative binomial. Correcting the plan: §10.3's "single additive index across hits/Ks/TB" is engine1's GRADE, not this ladder, which made a solved problem look open. SIMILARITY IS WRONG-SPORT. Zero callers, and its weights are NBA vocabulary: pace 0.15, referee_tendency 0.06, lineup_context 0.12, score_state_context 0.05, travel_fatigue 0.08. MLB has no pace and no referees. Connecting it would be the sport-stubbed-in-on-another-sport's- template breach, and it would fail QUIETLY -- missing factors are skipped, so the score would silently collapse onto whatever few dimensions happened to exist. CONSTRUCT, not connect. BAYESIAN WOULD REGRESS THE MODEL. Zero callers, and DISTRIBUTION_SHAPES keys on rbis / runs_scored / strikeouts_batter / outs_recorded / pitcher_strikeouts / walks_allowed / pitches_thrown -- NONE of which are live stat keys (S41: they are rbi / runs / outs / strikeouts). getDistributionShape defaults to 'normal' on an unknown key, so wiring it as-is would model COUNT stats as Gaussian, silently, on most MLB props. It is also superseded by distribution.js. Do not connect; retire or rewrite. DEPENDENCY, inverted: a better mean would help the ladder, but the ladder is already connected and both would-be foundations are unusable -- so this is not "connect similarity first", it is "the ladder is live and underperforming, and strengthening its mean requires BUILDING an MLB similarity layer that does not exist". Next-order pointer moved to diagnosing proj-v1.1: the only candidate already carrying settled evidence, and its diagnosis decides whether the similarity build is worth doing at all. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc |
||
|
builtbykev
|
ec815b0e37 |
Matchup axis report + plan reconciled: three challengers now accruing
Records the verification that matters: firing measured on a real prod snapshot rather than inferred. environment 248/293 (84.6%) -- also its FIRST confirmed ledger write, which the previous session could only infer -- and matchup 243/293 (82.9%) on tier batter_own_split. Both were 0/634. Collinearity guard passed at n=243: r = -0.003 vs the projection, +0.074 vs p_win, +0.003 vs line, -0.068 vs environment, -0.150 vs opportunity. The axis is not re-encoding recent form. The nudge distribution is also the right SHAPE -- mean +0.0007, 123 positive / 120 negative -- a balanced two-sided signal; a one-sided distribution would have suggested a sign or baseline error. Plan reconciled in place: arch-v1 condition axes marked firing, three challengers listed with coverage and their own holdout queries, and the next-order pointer moved to connecting the still-dormant layers (similarity, Bayesian, distribution ladder) with archetype_x_archetype as the named alternative. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc |
||
|
builtbykev
|
cfda597fb5 |
Reconcile MASTER-PLAN to true state; next order = matchup axis
Reconciled in place, not regenerated. Next-order pointer now MATCHUP AXIS with its verified sourcing table, and an explicit note that SOURCE-LINEUPS-first is NOT needed. Marked DONE with their evidence: p_win ranking + edge retirement, calibration DECIDED, MLB isotonic DECIDED (provisional label retracted), grade cap 25->500 (board 7->365+), book widening, S59 invariant armed, environment axis repaired. Records the honest shape of Phase 1: it is further along than the phase table implied, but mostly because the work turned out to be CONNECTION AND REPAIR rather than construction -- the ladder question dissolved, the cap was discarding 95.7% of the slate, and two condition axes were wired but firing on zero rows. Carried forward without softening: WNBA is NOT BUILT rather than failed, and the ruler is MARKET-not-SHARP with PENDING-RECOVERY status until PropLine answers the Pinnacle question -- not to be enshrined as permanent. Remaining ~19 orders, ~9 unblocked. The two accruing verdicts are time, not code. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc |
||
|
builtbykev
|
0d43fb7db8 |
arch-v1 axis audit: env/matchup were dead; environment fixed
Report for the audit + fix already committed. Records the two things worth carrying forward: 1. The environment axis has NOT yet been observed writing to the ledger, and I am not claiming it has. recordPipelineGrades upserts with ignoreDuplicates and dedupes on (user_id, player_key, stat, line, side, game_id) -- correctly, so a re-run never overwrites the original lock. Today's 429 rows predate the fix, so the axis cannot backfill onto them; first ledger observation is tomorrow's slate. What IS directly verified is the resolver (105/120) and the join key (416/416) -- the two things that were actually broken. 2. Matchup is not fixed and is not claimed as fixed. It needs the opposing starter and BOTH hands, and the audit shows three separate absences: oppPitcherByTeam 0, handById 0, bats 0/120. Fixing the pitcher feed without the hands, or the hands without the feed, still produces an axis that fires on zero rows. Also noted: the S59 slate JOIN INVARIANT keys off the same null `team` field, so it is currently inert too. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc |
||
|
builtbykev
|
48a2f764ac |
opportunity_drift: coverage 94%, collinearity PASSES, holdout n-blocked
STEP 1 -- input mapped and measured. opportunity_drift 94% coverage on 100 real props: 100% for batters (total_bases, hits, home_runs), 40-67% for pitchers, which is correct -- pitchers accumulate few at-bats so the ratio is genuinely undefined and ABSTAINS rather than being invented. STEP 2 -- THE COLLINEARITY GUARD PASSES DECISIVELY. Pearson r on n=94: drift vs l20_avg -0.020, vs l5_avg +0.027, vs ab_per_game -0.029. All essentially zero, so the axis is orthogonal to every existing projection input and carries information the projection does not already contain. That also validates the ratio-over-level decision EMPIRICALLY: ab_per_game is the same quantity over the same denominator as l20_avg, so the level would have been redundant. Dividing by the player's own baseline removed the collinearity -- r = -0.029 against the very quantity it is built from. STEP 3 -- live as a challenger, verified on prod over an induced 416-grade snapshot: 142 of 276 rows (51.4%) carry the opportunity axis, the challenger moved on 190 rows, mean |delta| 0.034, range -0.089..+0.108. Champion p_win and the live grade path are unchanged. STEP 4 -- HOLDOUT IS n-BLOCKED BY CONSTRUCTION and I am not manufacturing one. Settled rows carrying the axis: 0. Its first rows carry game_date 2026-08-01 -- games that have not been played. Running the test on rows the axis never touched would dilute the comparison with rows where challenger === champion by construction, making a null result look like a small positive one. Query committed for when n arrives; it filters to axis-carrying rows for exactly that reason, buckets before measuring reliability, and splits time-forward. BOTH metrics must improve or the axis is shelved. A MEASUREMENT TRAP RECORDED: the first prod run showed drift at 0% while ab_per_game read 94% -- indistinguishable from "the feature does not compute". It was the 120-second feature-vector cache serving payloads written by the previous image. A new feature field is invisible for one cache generation after deploy. I nearly reported it absent, having already confirmed atBats is present in the live statsapi payload and that the code produced drift = 1.05 locally on that exact data; the contradiction between those two facts is what saved it. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc |
||
|
builtbykev
|
8a02c75aec |
Step 0 input check: stop before wiring opportunity, and why
READ-ONLY. Live grade path byte-identical -- no layer wired, no threshold
moved, no challenger added, no holdout run.
INPUTS ARE 100% POPULATED (n=80 real MLB props, through the grader's own
path): ab_per_game, rest_days, l5_avg, l20_avg, l10_stddev and
game_count_in_7d all 100%; opp_rank_stat 65% overall and 0% on
stolen_bases. So there is no honest-degradation problem to solve.
FOUR FINDINGS THAT STOP THE WIRING, three of which would have made the
work unmeasurable or wrong:
1. THE PREMISE IS WRONG. There is no built opportunity layer to connect.
ab_per_game is consumed in exactly one place -- analyzeViaEngine1:379,
which renders "4.3 AB/G" on the grade card. engine1 has NO opportunity
or usage factor at all. A projected opportunity was never built;
building one is construction, not connection.
2. THE INPUT IS THE WRONG SHAPE. ab_per_game = season atBats/games. It is
a per-player CONSTANT (measured: varies for 3 of 20 players, and those
cannot be legitimate since the value can't depend on stat_type), so it
can only move all of a player's props together, never separate them.
And it is collinear with the projection: l20_avg = seasonTotal/games,
the SAME denominator, so l20_avg already embeds opportunity
multiplicatively. Adding it additively double-counts.
3. THE REAL INPUT DOES NOT EXIST. depthChartService returns battingOrder:
null for MLB ("the one lineup slot the free schedule feed exposes") and
PropLine /context carries lineup_confirmed as a BOOLEAN, not the order.
4. ARCHITECTURE: wiring it into engine1 would be unmeasurable BY THIS
ORDER'S OWN TEST. Step 2 proves reliability and resolution, both
measured on p_win. engine1 factors move the grade LETTER and never
touch p_win. The layer belongs in probabilityEstimator, which already
adjusts on opp_rank_stat, home_away and a consistency pull.
SEQUENCING IS ALSO STALE: challengerProjection (arch-v1) is already live
with archetype, matchup (platoon) and environment (park) axes, writing
p_win_challenger to the ledger. Step 2 of the order's sequence is partly
done -- and the harness this order needed already exists.
RECOMMENDED INSTEAD, as its own order: an `opportunity` axis on that
harness driven by DRIFT, not level -- recent AB/G (last 5) over season
AB/G. A deviation is not collinear the way the level is. Per-game atBats
is present in the statsapi log rows but MLB_LOG_FIELD never maps it, so it
is a small contained BUILD, which is why it gets its own order. Honest
caveat carried forward: it is still a proxy, not tonight's opportunity.
PROBE BUG RECORDED: the first run reported 0% for every feature including
l5_avg, on a pipeline that had just graded 365 props -- impossible, so the
probe was wrong. getFeatures takes camelCase and returns { features: {} };
I passed snake_case and read the top level. Fixed to call
computeFeaturesForProp. Same class as the earlier silent-false harness: a
measurement that makes working code look broken invites you to "fix"
something that was never broken.
Gates: 4,059 tests / 325 suites green; next build exit 0.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc
|
||
|
builtbykev
|
11b0139481 |
Verify the cap raise on prod: 7 -> 365 graded props
Induced, not projected. DEFAULT_LIMIT=500 produced 365 graded props in 114s (was 7 in 16s) -- 52x the board. All 365 carry a unique forecast_rank and ZERO leak p_win to anonymous callers, so the tier gating holds at 50x the volume. Anon payload 220KB in 0.44s. Stat mix went from three stats to ten. Health green. Measured cost curve via the ?limit= bisect hook: 1->42s, 25->58s, 60->42s, 120->66s, 500->114s. About 42s of that is FIXED overhead (odds fetch, roster logs, archetype classify, retention), paid whether we grade 1 prop or 500 -- grading is the cheap part. MY PRE-FLIGHT ESTIMATE WAS WRONG. I predicted ~72s from per-prop latency measured in isolation, which ignored the fixed cost. Real figure 114s. A FALSE ALARM RECORDED because acting on it would have meant reverting a fix that works: the first induced run 502'd at 13.4s and I hypothesised load -- memory or a proxy timeout under 20x the work. Wrong. A limit=25 run then 502'd in 2 seconds, which no amount of load explains, and both recovered on retry. The 502s were the deploy rolling, not the cap. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc |
||
|
builtbykev
|
a7d6cf8e36 |
Raise the grade cap 25 -> 500 on measured cost; refusals are correct
PART 1 (read-only, measured on a live prod slate, n=80) OVERTURNS THE
PREMISE. The refusal rate is not a data problem -- it is 98% correct
behaviour. The cap is the entire problem, and it is worse than "25 of 546".
Composition: GRADED 44 (55.0%) | POLICY-SUPPRESSION 35 (43.8%) |
FETCHABLE-GAP 1 (1.3%) | FALSE-THRESHOLD 0 | ARCHETYPE-GAP 0 |
GENUINE-ABSENCE 0.
THE FIFTH BUCKET the order did not anticipate: all 35 "refusals" are
rare_event_over_below_line -- the 2026-07-19 betting-logic audit
deliberately refusing 0.5-line rare events, setting the SAME
insufficient_data flag as a real data gap, which is why they read as one.
They are entirely doubles (18) and stolen_bases (17), while hits (19/19),
rbi (19/19) and total_bases (5/5) grade at ~100%. Had we "fixed" this we
would have re-introduced exactly the bets a previous audit removed, and the
count would have looked like progress.
THE CAP: 585 unique gradeable props, cap 25 -> 560 discarded (95.7%).
Traced to Session 32 (
|
||
|
builtbykev
|
6c97f59546 |
WNBA truth correction + THE p_win FLIP (live, rollback armed)
PART A -- WNBA TRUTH CORRECTION (no behaviour change).
WNBA does not "abstain" and is not "anti-predictive". The -0.12 that
produced those words was NBA-template machinery run on WNBA data -- WNBA
has never had its own archetypes, variables, conditions or calibration,
which is precisely the "sport stubbed in on another sport's template"
CLAUDE.md forbids. That is an UNBUILT MODEL'S EXPECTED FAILURE, not a
verdict on the sport; reading it as a verdict would quietly retire a sport
we never actually attempted. Its own build is QUEUED, after MLB.
The guard CODE is unchanged -- FORECAST_RANKED_SPORTS = {'mlb'} and the
inheritance test are correct live safety either way. Only the meaning is
corrected, and generalised into the doctrine-as-a-gate: a sport ranks on
p_win ONLY once its OWN model is built and shown to predict (calibration
AND resolution on its own holdout). Others are held out as NOT-BUILT,
never as failed. Re-labelled across gradeRanking, snapshot route, tests,
MASTER-PLAN and the challenger report.
PART B -- THE FLIP, gated on a full-slate re-run.
The re-run found something better than a bigger sample. An induced
snapshot graded 7 props: gradeAndCacheSlate runs with DEFAULT_LIMIT = 25
and ~72% of those refuse for insufficient_data, while 546 props are
gradeable. So 8 props IS the board, structurally -- not a small sample of
it. Logged as its own finding; the cap is a separate order.
For a statistically meaningful delta I used 11 real historical boards
(n=328, board sizes 14-57): 79.9% of rows move, mean 5.16 places per
board, TOP READ CHANGES ON 9 OF 11 BOARDS. The re-ordering holds at real
board size. Query committed.
FLIPPED:
- rankGrades drops its edge key (safe for every sport: removes a
non-predictive tiebreak without putting p_win in front).
- selectTopGrades leads on forecast_rank, edge key removed.
- flattenToEdgeBoard sorts on forecastRank, not edge -- this board had
edge as its PRIMARY key, so the whole mobile board was ordered by a
quantity measured not to predict.
- forecast_rank threaded onto strip props.
Sports whose model is not built supply no forecast_rank, so their boards
fall through to the unchanged grade chain -- the fallback is the guard.
ROLLBACK ARMED: boards sort by forecast_rank WHEN PRESENT, so
FORECAST_RANK=0 reverts every surface on the next response -- no deploy,
no client release.
Edge is still computed, stored, carried and displayed as a labelled
diagnostic. Retired from ranking, not deleted.
Eight superseded tests updated to strictly stronger INVERSE properties --
they now fail if edge is ever re-introduced as a ranking key, which the
originals could not detect.
Gates: 4,045 tests / 323 suites green; next build exit 0.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc
|
||
|
builtbykev
|
ef4ac60b81 |
Per-sport rank guard + edge diagnostic-only display + delta report
DELTA MEASURED on live prod grades (live ordering unchanged): MLB 7/8 props move (87.5%), mean 2.5 places, TOP READ CHANGES (corey seager hits 1.5 under -> jake burger hits 0.5 over). WNBA 25/25 move, mean 4.1, max 12. This is a large re-ordering, not a tweak. Caveat recorded rather than buried: MLB had only 8 graded props at measurement time. The percentages are real; the sample is one small slate. Re-run before the flip -- it is one call. PER-SPORT DOCTRINE ENFORCED IN CODE. WNBA moves the most and must NOT adopt this: its p_win is anti-predictive, so ranking that board by p_win would sort it by a signal measured to point the WRONG WAY -- worse than the incumbent, not better. A comment would not have stopped a future flip from going global, so FORECAST_RANKED_SPORTS = Set(['mlb']) gates the forecast_rank stamp, with tests asserting no sport inherits MLB's result. A sport joins only by passing its own holdout. EDGE IS NOW DIAGNOSTIC-ONLY IN DISPLAY. MobileEdgeBoard.EdgeCell rendered green (--g-a) for positive edge and red (--miss) for negative. Two things were wrong: green/red IS a quality claim on a quantity that does not predict, and ROW-GRAMMAR reserves red for settled-negative ONLY -- a negative diagnostic is not a settled loss. Now neutral mono with a diagnostic tooltip; header reads "MKT GAP · DIAGNOSTIC". The number is still shown -- no display went blank. DeskShowcase neutralised likewise. PINNACLE LOGGED, NOT ENSHRINED. Per the order, "market-not-sharp" is PENDING-RECOVERY rather than a confirmed permanent limitation. The single question for PropLine is in BLOCKERS.md with its evidence, and MASTER-PLAN now carries the pending status instead of the permanent claim. Live sorts remain byte-identical: selectTopGrades, flattenToEdgeBoard and topGradedService all still call the incumbent. Gates: 4,041 tests / 323 suites green; next build exit 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc |
||
|
builtbykev
|
7140e62b65 |
MLB re-run vs consensus ruler: premise dissolved, isotonic DECIDED
MEASURE-ONLY. No promotion, no flip, no tier spend. Live path
byte-identical: CURRENT_RULER_VERSION still v1_first_book, model still
consumes MODEL_BOOKS only.
MANDATE 1'S PREMISE DOES NOT HOLD. The p_win calibration is
RULER-INDEPENDENT, confirmed two ways: estimateProbability takes
{gameLogs, line, statType, features} and never sees a market price, and
the calibration fits p_win against OUTCOMES. Reliability and resolution
are both p_win-vs-outcome measures, so fair_prob cannot enter either.
There is nothing to re-fit -- the ruler changes edge, CLV and takeable,
not calibration.
I RETRACT MY OWN LABEL. I declared the MLB isotonic result PROVISIONAL
"because it was measured against the bent ruler". That over-applied the
ruler caveat to a measurement the ruler never touched. The result was
never contaminated; it moves PROVISIONAL -> DECIDED, not by re-running but
because the gate I attached does not apply.
RAN THE GENUINELY RULER-DEPENDENT QUESTION INSTEAD -- does a median
consensus rescue EDGE? Timing held constant (both rulers at close; a
lock-time reconstruction joins only 43 rows, and mixing lock-incumbent
with close-consensus would confound WHEN with WHAT).
n=200 MLB settled rows: mean |ruler gap| 0.0085. corr(edge_v1, outcome)
-0.0101; corr(edge_v2, outcome) -0.0220; corr(p_win, outcome) +0.2598.
THE HEADLINE: p_win predicts outcomes at +0.26 while p_win minus the
market predicts nothing under EITHER ruler. Subtracting the market price
destroys the signal -- a direct empirical vindication of the identity now
at the top of CLAUDE.md. Market edge is not merely a poor criterion here;
it is a strictly worse instrument than the raw forecast.
CALIBRATION REFRESH (ruler-independent, but n grew 119 -> 250):
time-forward holdout n=125, reliability 0.0846 (was 0.0939), resolution
0.190 (was 0.123). Both hold and both improved on a fresh later window
the earlier fit never saw. Independent replication.
THE LIMITATION THAT BLOCKS A FULL VERDICT: closing_captures holds only
MODEL books -- exchange quotes were never stored, because normalizeProps
discarded them until yesterday. Mean 1.97 books in the historical join. So
this tested a US-books-median ruler, not the exchange-inclusive consensus
whose live delta showed p90 +10 points. That ruler is UNTESTABLE on
existing data at any n. Per Mandate 4's third outcome: inconclusive, not
forced.
SEPARATE FINDING -- LIVE FEED REGRESSION: pinnacle MLB captures went 4,022
-> 0 on 2026-07-31 and have not returned, while every other book continued
(103,940 captures in the prior 10 days). This also corrects an Order Zero
claim of mine: "no sharp anchor exists in our feed" was accurate for the
day measured but wrong generally -- pinnacle was there until 07-30 with
17,090 two-sided captures. line_type='sharp' is a label in closingCapture
via SHARP_BOOKS, not a separate provider. We had a sharp anchor and lost
it two days ago; not caused by anything in this session.
Both queries committed: scripts/ruler-comparison.sql,
scripts/pwin-timeforward.sql.
Gates: 4,028 tests / 322 suites green; next build exit 0.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QJs13VsyiSKYQP6rj3NNmc
|