A = MPS grade A (75+) B = MPS grade B (60-75) C = MPS grade C (45-60) D/F = MPS grade D or F AT_RISK = direction lock with consecutive opposing signals DIR_LOCK = direction locked against SM CSV raw direction
Current Gate
v12 — User Curated Lean Gate
Composite Gate Score — 54.3/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
95
30% weight
Ctrl Retention (recall)
4
7/165 (4%)
Avg MPS
67
20% weight
Turnover
50
48% TRIM/SELL
Coverage
25
48% avg
Dir Health
100
5% weight
Pass-Set Quality — control tickers scoring ≥4/5 under this gate (precision view — what passes; complements Ctrl Retention's recall view)
Tickers Passing
9
≥4/5 rules · in control
Avg Raw Return
+59.42%
return_pct, unweighted mean
Win Rate
77.8%
% beating SPY (excess>0)
Gate Rules
RuleGradeThresholdCoverageDistSIL Advisor
RSI-Net EBITDAB 69248.620 higher48.3%76KEEP44
★★★★
FCF EfficiencyB 720.050 lower45.9%83KEEP90
★★★★★
ROIC-EBITDA QCC 45153.570 higher43.8%51KEEP52
★★★☆☆
Avg EPS GrowthB 7037.030 higher70.2%58KEEP64
★★★☆☆
FCF QualityD 440.190 lower32.4%65KEEP35
★★★★
Avg MPS: 59.9MAX 333
TIGHT6 pass all rules — gate is working. Even 0 is normal. Gated Rank differentiates within this set.
Tickers Scored
5,780
of 5,780 in SM CSV
Pass All Rules
6
0.10% of scored
Score 4+/5
87
1.5% of scored
Max Score
333
total dist points
Score Distribution
5/56 (0.1%)
4/581 (1.4%)
3/5262 (4.5%)
2/5459 (7.9%)
1/51,087 (18.8%)
0/53,885 (67.2%)
Selectivity Benchmarks
0–30 pass-all → TIGHT — gate is working
31–80 pass-all → MODERATE — Gated Score sorts it
81–200 pass-all → TOO LIBERAL — tighten
>200 pass-all → UNUSABLE — no discriminating power
Even 0 pass-all is fine — Gated Score ranks 4+/5 tickers.
Tiebreaker task open: see TASKS.md.
Signal Independence Grade
A
Overlap
Low overlap — 5 distinct signal families: RSI-Net EBITDA, FCF Efficiency, ROIC-EBITDA QC, Avg EPS Growth, FCF Quality. No direct input redundancy.
RuleSignal FamilyWhat it measures
RSI-Net EBITDARSI-Net EBITDARSI-Net EBITDA — see METRIC_FORMULAS.md
FCF EfficiencyFCF EfficiencyFCF yield relative to price — operational cash generation filter
ROIC-EBITDA QCROIC-EBITDA QCROIC-EBITDA QC — see METRIC_FORMULAS.md
Avg EPS GrowthAvg EPS GrowthAvg EPS Growth — see METRIC_FORMULAS.md
FCF QualityFCF QualityFCF Quality — see METRIC_FORMULAS.md
✓ No HIGH overlaps detected between rules in this gate.
Portfolio Turnover Impact
48%
of held positions would be TRIM/SELL under this gateHIGH TURNOVER
ADD MORE20 positions
ALAB, ALGM, AMD, ASML, BE, BWAY, CRDO, ETON +12 more
HOLD25 positions
AMSC, ARGX, AVGO, CIEN, CLS, COCO, FTNT, GSAT +17 more
TRIM13 positions
AMAT, AMZN, ANET, ASYS, CCJ, CRS, DASH, HWM +5 more
SELL28 positions
AGX, APH, APP, BLBD, CAT, DE, EME, ENVA +20 more
Top Buy Candidates (4+ rules · not held · ranked by Gated Score)
TickerRankScoreGated ScoreRSI-Net EBITDAFCF EfficiencyROIC-EBITDA QCAvg EPS GrowthFCF Quality
PLTR#1/57805/5333
ASND#5/57805/5333
OSS#6/57805/5333
KRO#7/57804/5282
CPSH#8/57804/5282
UROY#9/57804/5282
ATRC#11/57804/5282
WYY#12/57804/5282
INNV#13/57804/5282
SYM#14/57804/5282
Alternative Configurations — click anywhere on header to expand/collapse
Ranked by composite score (Selectivity 30% · Control Retention 30% · Avg MPS 20% · Turnover 10% · Coverage 5% · Direction 5%). Quick Swaps shown first regardless of score.
Quick Swaps1–2 rule changes from current gate
SIL-Driven FixScore 54
No swap-outs recommended — gate is healthy at this severity tier  ·  0 rules changed  ·  pass-all: 6
Deeper Overhauls3+ rule changes — ranked by composite score
Alt 2 — Watson-Free FCFScore 35
Eliminate the direction controversy — replace Watson 5 + PEG with FCF signals  ·  4 rules changed  ·  pass-all: 367
Alt 4 — Coverage-FirstScore 35
Prioritize data completeness — avoid gates with <65% ticker coverage  ·  4 rules changed  ·  pass-all: 266
Proposed v10 — Watson-ROIC CI → FCF Quality ScoreScore 33
User-confirmed swap: remove low-separation Watson-ROIC CI, add BF #1 FCF Quality Score  ·  3 rules changed  ·  pass-all: 508
Alt 1 — Minimal FixScore 31
Swap only the weakest rule (PEG F-grade → ROIC-FCF Gate A-grade)  ·  5 rules changed  ·  pass-all: 322
Top-4-SIL + FCF QualityScore 54
Auto: top 4 non-gate L2 metrics by sil_score + FCF Quality retained from current gate  ·  4 rules changed  ·  pass-all: 15
Top-4-SIL + RSI-Net EBITDAScore 53
Auto: top 4 non-gate L2 metrics by sil_score + RSI-Net EBITDA retained from current gate  ·  4 rules changed  ·  pass-all: 2
Top-4-SIL + ROIC-EBITDA QCScore 52
Auto: top 4 non-gate L2 metrics by sil_score + ROIC-EBITDA QC retained from current gate  ·  4 rules changed  ·  pass-all: 7
Top-4-SIL + FCF EfficiencyScore 52
Auto: top 4 non-gate L2 metrics by sil_score + FCF Efficiency retained from current gate  ·  4 rules changed  ·  pass-all: 13
Top-4-SIL + Avg EPS GrowthScore 48
Auto: top 4 non-gate L2 metrics by sil_score + Avg EPS Growth retained from current gate  ·  4 rules changed  ·  pass-all: 13
Alt 5 — Balanced Independence ⭐ RecommendedRECOMMENDEDScore 42
Best balance of MPS grade, signal independence, coverage, and direction confidence  ·  4 rules changed  ·  pass-all: 127
Alt 3 — Maximum A-GradeScore 40
Maximize average MPS score — all 5 rules A-grade, zero B/F rules  ·  4 rules changed  ·  pass-all: 387
Experimental L1Accumulate control lab sessions before promoting
Alt 6 — L1 Raw Signals 🧪 ExperimentalScore 50
Pure L1 gate — raw ratios only, control-lab directions, universe-percentile thresholds  ·  5 rules changed  ·  pass-all: 1
Alt 7 — L1+L2 Hybrid 🧪 ExperimentalScore 49
Best L1 signal anchored by top L2 quality checks — tests if raw signals add lift  ·  4 rules changed  ·  pass-all: 14
⚡ Custom Gate BuilderSelect up to 7 metrics  ·  dist weights auto-set from SIL score  ·  Run to score 5,780 tickers instantly
Data: SM CSV (Invest-Multi(4_30_23) - Secondary Metrics (70).csv) · Registry: metric_registry.csv · Generated: 2026-07-19 23:10
Top buys show tickers scoring 4+/5 rules, sorted by weighted score. "Pass-all" counts tickers passing every rule simultaneously.
Overlap analysis from METRIC_OVERLAP_MAP.md (last updated gate v5 — needs v8 review).
Coverage = % of SM CSV tickers with valid data for this metric.
Hub Take Action Gate Gate Alts