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 — 50.8/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
80
30% weight
Ctrl Retention (recall)
7
12/165 (7%)
Avg MPS
67
20% weight
Turnover
50
47% 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
13
≥4/5 rules · in control
Avg Raw Return
+68.81%
return_pct, unweighted mean
Win Rate
92.3%
% beating SPY (excess>0)
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| RSI-Net EBITDA | C 60 | 194.850 higher | 48.5% | 66 | KEEP18 ★★★★☆ |
| FCF Efficiency | C 52 | 0.060 lower | 44.6% | 70 | KEEP78 ★★★★☆ |
| ROIC-EBITDA QC | B 61 | 126.010 higher | 43.9% | 65 | KEEP38 ★★★★☆ |
| Avg EPS Growth | B 66 | 39.650 higher | 69.6% | 68 | KEEP78 ★★★★☆ |
| FCF Quality | D 39 | 0.230 lower | 30.8% | 65 | KEEP38 ★★★★☆ |
| Avg MPS: 55.7 | MAX 334 | ||||
TIGHT14 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
14
0.24% of scored
Score 4+/5
119
2.1% of scored
Max Score
334
total dist points
Score Distribution
5/514 (0.2%)
4/5105 (1.8%)
3/5250 (4.3%)
2/5463 (8.0%)
1/51,050 (18.2%)
0/53,898 (67.4%)
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.
● 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.
| Rule | Signal Family | What it measures |
|---|---|---|
| RSI-Net EBITDA | RSI-Net EBITDA | RSI-Net EBITDA — see METRIC_FORMULAS.md |
| FCF Efficiency | FCF Efficiency | FCF yield relative to price — operational cash generation filter |
| ROIC-EBITDA QC | ROIC-EBITDA QC | ROIC-EBITDA QC — see METRIC_FORMULAS.md |
| Avg EPS Growth | Avg EPS Growth | Avg EPS Growth — see METRIC_FORMULAS.md |
| FCF Quality | FCF Quality | FCF Quality — see METRIC_FORMULAS.md |
✓ No HIGH overlaps detected between rules in this gate.
Portfolio Turnover Impact
47%
of held positions would be TRIM/SELL under this gateHIGH TURNOVER
ADD MORE27 positions
ALAB, AMD, AMSC, ARGX, ASML, BE, BWAY, CIEN +19 more
HOLD17 positions
ALGM, ANET, AVGO, CCJ, CLS, COCO, FTNT, GSAT +9 more
TRIM10 positions
AMAT, AMZN, CRS, FIX, HWM, IESC, KLAC, LGND +2 more
SELL29 positions
AGX, APH, APP, BLBD, CAT, DE, EME, ENVA +21 more
Top Buy Candidates (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | RSI-Net EBITDA | FCF Efficiency | ROIC-EBITDA QC | Avg EPS Growth | FCF Quality |
|---|---|---|---|---|---|---|---|---|
| CORT | #1/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| PTGX | #2/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| PLTR | #4/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| CDNA | #6/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| BLFS | #11/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| OSS | #12/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| ASND | #13/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| FORM | #14/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| ALM | #15/5780 | 4/5 | 269 | ✓ | ✓ | ✗ | ✓ | ✓ |
| DKNG | #16/5780 | 4/5 | 269 | ✓ | ✓ | ✗ | ✓ | ✓ |
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 51
▼
No swap-outs recommended — gate is healthy at this severity tier · 0 rules changed · pass-all: 14
Composite Gate Score — 50.8/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
80
30% weight
Ctrl Retention (recall)
7
12/165 (7%)
Avg MPS
67
20% weight
Turnover
50
47% 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
13
≥4/5 rules · in control
Avg Raw Return
+68.81%
return_pct, unweighted mean
Win Rate
92.3%
% beating SPY (excess>0)
Changed From Current Gate
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| RSI-Net EBITDA | C 60 | 194.850 higher | 48.5% | 66 | KEEP18 ★★★★☆ |
| FCF Efficiency | C 52 | 0.060 lower | 44.6% | 70 | KEEP78 ★★★★☆ |
| ROIC-EBITDA QC | B 61 | 126.010 higher | 43.9% | 65 | KEEP38 ★★★★☆ |
| Avg EPS Growth | B 66 | 39.650 higher | 69.6% | 68 | KEEP78 ★★★★☆ |
| FCF Quality | D 39 | 0.230 lower | 30.8% | 65 | KEEP38 ★★★★☆ |
| Avg MPS: 55.7 | MAX 334 | ||||
TIGHT14 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
14
0.24% of scored
Score 4+/5
119
2.1% of scored
Max Score
334
total dist points
Score Distribution
5/514 (0.2%)
4/5105 (1.8%)
3/5250 (4.3%)
2/5463 (8.0%)
1/51,050 (18.2%)
0/53,898 (67.4%)
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.
● 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.
Upside
- SIL Advisor finds no actionable swap at this tier — current gate composition is stable
Restrictiveness: Same as current gate — no change recommended
Liberal risk: N/A
Downside / Risk
- No swap-outs recommended — gate is healthy at this severity tier
Signal Independence Grade
A
Overlap
Same as current gate (no swap applied)
| Rule | Signal Family | What it measures |
|---|---|---|
| RSI-Net EBITDA | RSI-Net EBITDA | RSI-Net EBITDA — see METRIC_FORMULAS.md |
| FCF Efficiency | FCF Efficiency | FCF yield relative to price — operational cash generation filter |
| ROIC-EBITDA QC | ROIC-EBITDA QC | ROIC-EBITDA QC — see METRIC_FORMULAS.md |
| Avg EPS Growth | Avg EPS Growth | Avg EPS Growth — see METRIC_FORMULAS.md |
| FCF Quality | FCF Quality | FCF Quality — see METRIC_FORMULAS.md |
✓ No HIGH overlaps detected between rules in this gate.
Portfolio Turnover Impact
47%
of held positions would be TRIM/SELL under this gateHIGH TURNOVER
ADD MORE27 positions
ALAB, AMD, AMSC, ARGX, ASML, BE, BWAY, CIEN +19 more
HOLD17 positions
ALGM, ANET, AVGO, CCJ, CLS, COCO, FTNT, GSAT +9 more
TRIM10 positions
AMAT, AMZN, CRS, FIX, HWM, IESC, KLAC, LGND +2 more
SELL29 positions
AGX, APH, APP, BLBD, CAT, DE, EME, ENVA +21 more
Top Buy Candidates Under This Gate (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | RSI-Net EBITDA | FCF Efficiency | ROIC-EBITDA QC | Avg EPS Growth | FCF Quality |
|---|---|---|---|---|---|---|---|---|
| CORT | #1/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| PTGX | #2/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| PLTR | #4/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| CDNA | #6/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| BLFS | #11/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| OSS | #12/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| ASND | #13/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| FORM | #14/5780 | 5/5 | 334 | ✓ | ✓ | ✓ | ✓ | ✓ |
| ALM | #15/5780 | 4/5 | 269 | ✓ | ✓ | ✗ | ✓ | ✓ |
| DKNG | #16/5780 | 4/5 | 269 | ✓ | ✓ | ✗ | ✓ | ✓ |
Vs. Current Gate
| Metric | Current | This Alt | Δ |
|---|---|---|---|
| Avg Gate MPS | 55.7 | 55.7 | 0.0 |
| Pass-all count | 14 | 14 | 0 |
| Score 4+/5 count | 119 | 119 | 0 |
| MAX_WS | 334 | 334 | 0 |
Deeper Overhauls3+ rule changes — ranked by composite score
Alt 2 — Watson-Free FCFScore 34
▼
Eliminate the direction controversy — replace Watson 5 + PEG with FCF signals · 4 rules changed · pass-all: 351
Composite Gate Score — 34.2/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
0
30% weight
Ctrl Retention (recall)
30
49/165 (30%)
Avg MPS
54
20% weight
Turnover
90
22% TRIM/SELL
Coverage
25
46% avg
Dir Health
85
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
135
≥4/5 rules · in control
Avg Raw Return
+16.25%
return_pct, unweighted mean
Win Rate
36.3%
% beating SPY (excess>0)
Changed From Current Gate
✕ RSI-Net EBITDA (C-grade, dist=66) → ✓ Weighted FCF Efficiency (D-grade, dist=48)
✕ ROIC-EBITDA QC (B-grade, dist=65) → ✓ P/S v P/C Multiple (B-grade, dist=57)
✕ Avg EPS Growth (B-grade, dist=68) → ✓ ROIC-FCF Quality Gate (C-grade, dist=42)
✕ FCF Quality (D-grade, dist=65) → ✓ (none)
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| FCF Efficency | C 52 | 0.060 lower | 44.6% | 70 | KEEP78 ★★★★☆ |
| Weighted FCF Efficiency | D 33 | 1.700 lower | 61.2% | 48 | CANDIDATE35 ★★★☆☆ |
| P/S v P/C Multiple | B 70 | 12.450 lower | 40.0% | 57 | CANDIDATE50 ★★★☆☆ |
| ROIC-FCF Quality Gate DIR_LOCK | C 56 | 0.120 lower | 38.4% | 42 | CANDIDATE58 ★★★☆☆ |
| Avg MPS: 52.8 | MAX 217 | ||||
UNUSABLE351 pass all rules — gate does not function as a filter. Hundreds passing means the rules have no discriminating power at current thresholds. Do not use this configuration without significant tightening.
Tickers Scored
4,800
of 5,780 in SM CSV
Pass All Rules
351
7.31% of scored
Score 4+/5
351
7.3% of scored
Max Score
217
total dist points
Score Distribution
4/4351 (7.3%)
3/41,105 (23.0%)
2/41,133 (23.6%)
1/41,956 (40.8%)
0/41,235 (25.7%)
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.
● 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.
Upside
- Eliminates Watson 5 direction controversy entirely (21 consecutive opposing)
- FCF Efficency (A, MPS 94.47) is the top-ranked metric by MPS — strongest available signal
- All rules have confirmed lower-wins directions (except ROIC-FCF Gate flag)
- Highest average MPS of FCF-focused alternatives
Restrictiveness: Likely more restrictive — two high-signal FCF gates vs one
Liberal risk: Medium — FCF signals correlated, gate may let through FCF-fakers simultaneously
Downside / Risk
- 3 of 5 rules are FCF-family metrics — gate loses diversity of signal type
- FCF Efficency and Wtd FCF Efficiency share thematic overlap (both FCF efficiency ratios)
- ROIC-FCF Gate direction lock conflict persists
- Coverage gap: FCF Efficency only 47.1% of tickers have valid data
- If FCF signals are collectively wrong in a cycle, gate has little non-FCF backstop
Signal Independence Grade
B
Overlap
No HIGH overlaps. FCF family fills 2 of 5 slots — gate has 4 effective signal dimensions, not 5. One DIR_LOCK on ROIC-FCF Gate.
| Rule | Signal Family | What it measures |
|---|---|---|
| FCF Efficency | FCF Efficiency | FCF Yield / EV_EBITDA — raw FCF quality |
| Wtd FCF Efficiency | FCF Efficiency | ⚠ Same family as FCF Eff — thematic overlap |
| P/S v P/C Multiple | Valuation | Pure price-ratio — independent ✓ |
| ROIC-FCF Quality Gate | ROIC Quality | ROIC+FCF composite — direction lock ⚠ |
MEDIUM · FCF Efficency (31) × Wtd FCF Efficiency (42)
Both are FCF-ratio variants — col31 uses FCF Yield/EV_EBITDA, col42 is different formula. Thematic overlap.
Portfolio Turnover Impact
22%
of held positions would be TRIM/SELL under this gate
ADD MORE41 positions
ALAB, ALGM, AMAT, AMD, AMSC, AMZN, ARGX, AVGO +33 more
HOLD24 positions
AGX, ANET, APH, ASML, CLS, FTNT, GEV, HWM +16 more
TRIM15 positions
APP, BLBD, CAT, EME, ENVA, GOOG, ITRN, MLI +7 more
SELL3 positions
FIX, MCK, WDC
Top Buy Candidates Under This Gate (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | FCF Efficency | Weighted FCF E | P/S v P/C Mult | ROIC-FCF Quali |
|---|---|---|---|---|---|---|---|
| CORT | #1/5780 | 4/4 | 217 | ✓ | ✓ | ✓ | ✓ |
| PTGX | #2/5780 | 4/4 | 217 | ✓ | ✓ | ✓ | ✓ |
| OSS | #4/5780 | 4/4 | 217 | ✓ | ✓ | ✓ | ✓ |
| ALM | #5/5780 | 4/4 | 217 | ✓ | ✓ | ✓ | ✓ |
| ANIK | #6/5780 | 4/4 | 217 | ✓ | ✓ | ✓ | ✓ |
| ARM | #7/5780 | 4/4 | 217 | ✓ | ✓ | ✓ | ✓ |
| FSLY | #8/5780 | 4/4 | 217 | ✓ | ✓ | ✓ | ✓ |
| OMDA | #9/5780 | 4/4 | 217 | ✓ | ✓ | ✓ | ✓ |
| SMWB | #10/5780 | 4/4 | 217 | ✓ | ✓ | ✓ | ✓ |
| U | #11/5780 | 4/4 | 217 | ✓ | ✓ | ✓ | ✓ |
Vs. Current Gate
| Metric | Current | This Alt | Δ |
|---|---|---|---|
| Avg Gate MPS | 55.7 | 52.8 | -2.8 |
| Pass-all count | 14 | 351 | 337 |
| Score 4+/5 count | 119 | 351 | 232 |
| MAX_WS | 334 | 217 | -117 |
Alt 4 — Coverage-FirstScore 34
▼
Prioritize data completeness — avoid gates with <65% ticker coverage · 4 rules changed · pass-all: 253
Composite Gate Score — 34.1/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
0
30% weight
Ctrl Retention (recall)
27
44/165 (27%)
Avg MPS
59
20% weight
Turnover
75
29% TRIM/SELL
Coverage
50
60% avg
Dir Health
85
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
103
≥4/5 rules · in control
Avg Raw Return
+16.97%
return_pct, unweighted mean
Win Rate
42.7%
% beating SPY (excess>0)
Changed From Current Gate
✕ RSI-Net EBITDA (C-grade, dist=66) → ✓ P/S v P/C Multiple (B-grade, dist=57)
✕ FCF Efficiency (C-grade, dist=70) → ✓ Weighted FCF Efficiency (D-grade, dist=48)
✕ ROIC-EBITDA QC (B-grade, dist=65) → ✓ CARC (C-grade, dist=63)
✕ FCF Quality (D-grade, dist=65) → ✓ (none)
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| P/S v P/C Multiple | B 70 | 12.450 lower | 40.0% | 57 | CANDIDATE50 ★★★☆☆ |
| Weighted FCF Efficiency | D 33 | 1.700 lower | 61.2% | 48 | CANDIDATE35 ★★★☆☆ |
| Avg. EPS Growth | B 66 | 39.650 higher | 69.6% | 68 | KEEP78 ★★★★☆ |
| CARC DIR_LOCK | C 48 | 0.350 lower | 68.4% | 63 | CANDIDATE38 ★★★★☆ |
| Avg MPS: 54.3 | MAX 236 | ||||
UNUSABLE253 pass all rules — gate does not function as a filter. Hundreds passing means the rules have no discriminating power at current thresholds. Do not use this configuration without significant tightening.
Tickers Scored
5,183
of 5,780 in SM CSV
Pass All Rules
253
4.88% of scored
Score 4+/5
253
4.9% of scored
Max Score
236
total dist points
Score Distribution
4/4253 (4.9%)
3/4817 (15.8%)
2/41,420 (27.4%)
1/41,853 (35.8%)
0/41,437 (27.7%)
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.
● 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.
Upside
- Highest overall ticker coverage — all 5 rules ≥65% (vs Watson 5 at 42.6%, PEG at 30.7%)
- CARC has 76.3% coverage — second only to P/S v P/C (83.7%)
- More tickers get scored, reducing blind spots from N/A data
- Avg EPS Growth (71.0% coverage) now upgraded to B-grade (MPS 66.72) — adds meaningful growth dimension
Restrictiveness: Less restrictive — lower-grade metrics have wider thresholds
Liberal risk: Medium-High — CARC direction uncertainty + EPS Growth gaming risk
Downside / Risk
- CARC dropped to D-grade (MPS 32.30) — significant weakening since last assessment
- CARC direction lock conflict (locked=lower, SM CSV raw=higher) — flagged INVESTIGATE in SIL
- Avg EPS Growth only D ranked by return score — directional confidence mixed
- No pure FCF signal — gate may miss quality FCF compounders
- Growth (EPS Growth) + Quality (QVS) could be gamed by one-time earnings spikes
Signal Independence Grade
A-
Overlap
5 distinct signal families — best family diversity of all alternatives. No HIGH overlaps. Minor direction lock on CARC. Each rule covers a genuinely different dimension.
| Rule | Signal Family | What it measures |
|---|---|---|
| P/S v P/C Multiple | Valuation | Pure price-ratio — independent ✓ |
| Wtd FCF Efficiency | FCF Efficiency | FCF+ROIC efficiency ratio — independent ✓ |
| Avg. EPS Growth | Earnings Growth | Trailing EPS growth — unique growth dimension ✓ |
| CARC | Capital Efficiency | Capital allocation quality — direction lock ⚠ |
✓ No HIGH overlaps detected between rules in this gate.
Portfolio Turnover Impact
29%
of held positions would be TRIM/SELL under this gate
ADD MORE43 positions
ALAB, ALGM, AMAT, AMD, AMSC, AMZN, ARGX, AVGO +35 more
HOLD16 positions
APH, APP, ASML, CAT, CCJ, GSAT, HWM, IESC +8 more
TRIM15 positions
AGX, ANET, FIX, FTNT, GEV, GOOG, IDCC, INOD +7 more
SELL9 positions
BLBD, EME, ENVA, ITRN, MCK, MLI, NXT, SEZL +1 more
Top Buy Candidates Under This Gate (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | P/S v P/C Mult | Weighted FCF E | Avg. EPS Growt | CARC |
|---|---|---|---|---|---|---|---|
| CORT | #1/5780 | 4/4 | 236 | ✓ | ✓ | ✓ | ✓ |
| PTGX | #2/5780 | 4/4 | 236 | ✓ | ✓ | ✓ | ✓ |
| PLTR | #4/5780 | 4/4 | 236 | ✓ | ✓ | ✓ | ✓ |
| CDNA | #6/5780 | 4/4 | 236 | ✓ | ✓ | ✓ | ✓ |
| BLFS | #8/5780 | 4/4 | 236 | ✓ | ✓ | ✓ | ✓ |
| OSS | #9/5780 | 4/4 | 236 | ✓ | ✓ | ✓ | ✓ |
| ASND | #10/5780 | 4/4 | 236 | ✓ | ✓ | ✓ | ✓ |
| FORM | #11/5780 | 4/4 | 236 | ✓ | ✓ | ✓ | ✓ |
| ALM | #12/5780 | 4/4 | 236 | ✓ | ✓ | ✓ | ✓ |
| ANIK | #13/5780 | 4/4 | 236 | ✓ | ✓ | ✓ | ✓ |
Vs. Current Gate
| Metric | Current | This Alt | Δ |
|---|---|---|---|
| Avg Gate MPS | 55.7 | 54.3 | -1.4 |
| Pass-all count | 14 | 253 | 239 |
| Score 4+/5 count | 119 | 253 | 134 |
| MAX_WS | 334 | 236 | -98 |
Proposed v10 — Watson-ROIC CI → FCF Quality ScoreScore 32
▼
User-confirmed swap: remove low-separation Watson-ROIC CI, add BF #1 FCF Quality Score · 3 rules changed · pass-all: 485
Composite Gate Score — 32.5/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
0
30% weight
Ctrl Retention (recall)
21
34/165 (21%)
Avg MPS
63
20% weight
Turnover
75
29% TRIM/SELL
Coverage
25
37% 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
76
≥4/5 rules · in control
Avg Raw Return
+20.21%
return_pct, unweighted mean
Win Rate
44.7%
% beating SPY (excess>0)
Changed From Current Gate
✕ RSI-Net EBITDA (C-grade, dist=66) → ✓ FCF-EBITDA Convergence Score (B-grade, dist=59)
✕ ROIC-EBITDA QC (B-grade, dist=65) → ✓ P/S v P/C Multiple (B-grade, dist=57)
✕ Avg EPS Growth (B-grade, dist=68) → ✓ (none)
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| FCF Efficency | C 52 | 0.060 lower | 44.6% | 70 | KEEP78 ★★★★☆ |
| FCF-EBITDA Convergence Score | B 63 | 2.210 lower | 30.9% | 59 | CANDIDATE64 ★★★☆☆ |
| P/S v P/C Multiple | B 70 | 12.450 lower | 40.0% | 57 | CANDIDATE50 ★★★☆☆ |
| FCF Quality Score | D 39 | 0.230 lower | 30.8% | 65 | KEEP38 ★★★★☆ |
| Avg MPS: 56.1 | MAX 251 | ||||
UNUSABLE485 pass all rules — gate does not function as a filter. Hundreds passing means the rules have no discriminating power at current thresholds. Do not use this configuration without significant tightening.
Tickers Scored
4,800
of 5,780 in SM CSV
Pass All Rules
485
10.10% of scored
Score 4+/5
485
10.1% of scored
Max Score
251
total dist points
Score Distribution
4/4485 (10.1%)
3/4330 (6.9%)
2/41,556 (32.4%)
1/41,222 (25.5%)
0/42,187 (45.6%)
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.
● 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.
Upside
- Removes weakest gate metric by SIL score (Watson-ROIC CI, 37/100)
- FCF Quality Score is BF #1 combo partner — strongest empirical backing
- FCF Quality Score direction confirmed lower (ctrl validated, 53 sessions)
- No HIGH overlap with remaining gate metrics
- P/S v P/C retained — provides independent valuation signal
Restrictiveness: Similar to current — FCF Quality Score adds a real FCF quality filter
Liberal risk: Low-Medium — FCF Quality Score threshold may be strict
Downside / Risk
- Gate becomes more FCF-concentrated (FCF Eff + FCF-EBITDA Conv + FCF Quality Score)
- FCF Quality Score SIL score (55) lower than FCF-EBITDA Conv (63) — mid-tier confidence
- P/S v P/C still SWAP_OUT candidate (sil=24) — future swap needed
Signal Independence Grade
B
Overlap
FCF cluster exists (FCF Eff + FCF-EBITDA Conv + FCF Quality Score) but no direct formula overlap. P/S v P/C and QVS remain independent signals.
| Rule | Signal Family | What it measures |
|---|---|---|
| FCF Efficency | FCF Efficiency | FCF/Revenue ratio — core FCF signal |
| FCF-EBITDA Convergence Score | FCF Convergence | FCF vs EBITDA alignment — FCF family |
| P/S v P/C Multiple | Valuation | Price-ratio spread — independent signal ✓ |
| FCF Quality Score | FCF Quality | FCF composite quality — FCF family |
✓ No HIGH overlaps detected between rules in this gate.
Portfolio Turnover Impact
29%
of held positions would be TRIM/SELL under this gate
ADD MORE51 positions
ALAB, ALGM, AMAT, AMD, AMSC, AMZN, ANET, ARGX +43 more
HOLD8 positions
APH, CAT, CLS, FIX, MNST, MOD, RDDT, VIK
TRIM16 positions
AGX, APP, DE, ENVA, GOOG, IDCC, IDR, MCK +8 more
SELL8 positions
BLBD, EME, ITRN, MLI, NXT, SEZL, STRL, WTS
Top Buy Candidates Under This Gate (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | FCF Efficency | FCF-EBITDA Con | P/S v P/C Mult | FCF Quality Sc |
|---|---|---|---|---|---|---|---|
| CORT | #1/5780 | 4/4 | 251 | ✓ | ✓ | ✓ | ✓ |
| PTGX | #2/5780 | 4/4 | 251 | ✓ | ✓ | ✓ | ✓ |
| PLTR | #4/5780 | 4/4 | 251 | ✓ | ✓ | ✓ | ✓ |
| CDNA | #6/5780 | 4/4 | 251 | ✓ | ✓ | ✓ | ✓ |
| BLFS | #9/5780 | 4/4 | 251 | ✓ | ✓ | ✓ | ✓ |
| OSS | #10/5780 | 4/4 | 251 | ✓ | ✓ | ✓ | ✓ |
| ASND | #11/5780 | 4/4 | 251 | ✓ | ✓ | ✓ | ✓ |
| FORM | #12/5780 | 4/4 | 251 | ✓ | ✓ | ✓ | ✓ |
| ALM | #13/5780 | 4/4 | 251 | ✓ | ✓ | ✓ | ✓ |
| ANIK | #14/5780 | 4/4 | 251 | ✓ | ✓ | ✓ | ✓ |
Vs. Current Gate
| Metric | Current | This Alt | Δ |
|---|---|---|---|
| Avg Gate MPS | 55.7 | 56.1 | +0.5 |
| Pass-all count | 14 | 485 | 471 |
| Score 4+/5 count | 119 | 485 | 366 |
| MAX_WS | 334 | 251 | -83 |
Alt 1 — Minimal FixScore 29
▼
Swap only the weakest rule (PEG F-grade → ROIC-FCF Gate A-grade) · 5 rules changed · pass-all: 317
Composite Gate Score — 29.2/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
0
30% weight
Ctrl Retention (recall)
32
52/165 (32%)
Avg MPS
40
20% weight
Turnover
75
28% TRIM/SELL
Coverage
25
45% avg
Dir Health
60
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
144
≥4/5 rules · in control
Avg Raw Return
+14.81%
return_pct, unweighted mean
Win Rate
36.1%
% beating SPY (excess>0)
Changed From Current Gate
✕ RSI-Net EBITDA (C-grade, dist=66) → ✓ Weighted FCF Efficiency (D-grade, dist=48)
✕ FCF Efficiency (C-grade, dist=70) → ✓ SM Watson 5 (F-grade, dist=14)
✕ ROIC-EBITDA QC (B-grade, dist=65) → ✓ P/S v P/C Multiple (B-grade, dist=57)
✕ Avg EPS Growth (B-grade, dist=68) → ✓ ROIC-FCF Quality Gate (C-grade, dist=42)
✕ FCF Quality (D-grade, dist=65) → ✓ (none)
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| Weighted FCF Efficiency | D 33 | 1.700 lower | 61.2% | 48 | CANDIDATE35 ★★★☆☆ |
| SM Watson 5 AT_RISK | F 10 | 51.050 lower | 40.6% | 14 | SKIP20 ★☆☆☆☆ |
| P/S v P/C Multiple | B 70 | 12.450 lower | 40.0% | 57 | CANDIDATE50 ★★★☆☆ |
| ROIC-FCF Quality Gate DIR_LOCK | C 56 | 0.120 lower | 38.4% | 42 | CANDIDATE58 ★★★☆☆ |
| Avg MPS: 42.2 | MAX 161 | ||||
UNUSABLE317 pass all rules — gate does not function as a filter. Hundreds passing means the rules have no discriminating power at current thresholds. Do not use this configuration without significant tightening.
Tickers Scored
4,800
of 5,780 in SM CSV
Pass All Rules
317
6.60% of scored
Score 4+/5
317
6.6% of scored
Max Score
161
total dist points
Score Distribution
4/4317 (6.6%)
3/41,367 (28.5%)
2/41,727 (36.0%)
1/41,184 (24.7%)
0/41,185 (24.7%)
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.
● 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.
Upside
- Surgical change — only 1 rule swapped, all other gate knowledge preserved
- ROIC-FCF Quality Gate (A, MPS 81) replaces PEG Adj Hybrid (F, MPS 23)
- Average gate MPS jumps from 68.6 → 74.3
Restrictiveness: Similar to current — Watson 5 + QVS combination is strict
Liberal risk: Low — Watson 5 threshold (51.94) acts as broad filter
Downside / Risk
- SM Watson 5 direction AT_RISK (21 consecutive opposing) remains unresolved
- HIGH overlap between Wtd FCF Eff and Watson 5 persists (col42 inside Watson 5)
- ROIC-FCF Gate has a direction lock conflict (locked=lower, SM CSV raw=higher)
- Effective signal independence still ~3-4 of 5 rules due to Watson 5 absorption
Signal Independence Grade
C
Overlap
HIGH overlap persists — Wtd FCF Eff (col42) is a direct input inside Watson 5 (col53). Two rules double-counting the same FCF signal. Direction flags on 2 of 5 rules.
| Rule | Signal Family | What it measures |
|---|---|---|
| SM Watson 5 | Super Metric | ⚠ Already contains Wtd FCF Eff internally — 5-factor blend |
| Wtd FCF Efficiency | FCF Efficiency | ⚠ Redundant — col42 is inside Watson 5 |
| P/S v P/C Multiple | Valuation | Price-ratio spread — independent signal ✓ |
| ROIC-FCF Quality Gate | ROIC Quality | ROIC+FCF composite gate — direction lock ⚠ |
HIGH · Wtd FCF Eff (42) × SM Watson 5 (53)
col42 is a direct input to Watson 5 — double-counts FCF efficiency signal
Portfolio Turnover Impact
28%
of held positions would be TRIM/SELL under this gate
ADD MORE35 positions
ALGM, AMD, AMSC, AMZN, ARGX, BE, BWAY, CCJ +27 more
HOLD25 positions
AGX, ALAB, AMAT, APH, AVGO, CAT, CRDO, ENVA +17 more
TRIM20 positions
ANET, APP, ASML, BLBD, CLS, EME, FTNT, GOOG +12 more
SELL3 positions
FIX, MCK, WDC
Top Buy Candidates Under This Gate (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | Weighted FCF E | SM Watson 5 | P/S v P/C Mult | ROIC-FCF Quali |
|---|---|---|---|---|---|---|---|
| CORT | #1/5780 | 4/4 | 161 | ✓ | ✓ | ✓ | ✓ |
| PTGX | #2/5780 | 4/4 | 161 | ✓ | ✓ | ✓ | ✓ |
| OSS | #4/5780 | 4/4 | 161 | ✓ | ✓ | ✓ | ✓ |
| ALM | #5/5780 | 4/4 | 161 | ✓ | ✓ | ✓ | ✓ |
| ANIK | #6/5780 | 4/4 | 161 | ✓ | ✓ | ✓ | ✓ |
| ARM | #7/5780 | 4/4 | 161 | ✓ | ✓ | ✓ | ✓ |
| FSLY | #8/5780 | 4/4 | 161 | ✓ | ✓ | ✓ | ✓ |
| OMDA | #9/5780 | 4/4 | 161 | ✓ | ✓ | ✓ | ✓ |
| SMWB | #10/5780 | 4/4 | 161 | ✓ | ✓ | ✓ | ✓ |
| U | #11/5780 | 4/4 | 161 | ✓ | ✓ | ✓ | ✓ |
Vs. Current Gate
| Metric | Current | This Alt | Δ |
|---|---|---|---|
| Avg Gate MPS | 55.7 | 42.2 | -13.5 |
| Pass-all count | 14 | 317 | 303 |
| Score 4+/5 count | 119 | 317 | 198 |
| MAX_WS | 334 | 161 | -173 |
Top-4-SIL + FCF QualityScore 53
▼
Auto: top 4 non-gate L2 metrics by sil_score + FCF Quality retained from current gate · 4 rules changed · pass-all: 18
Composite Gate Score — 52.9/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
80
30% weight
Ctrl Retention (recall)
2
4/165 (2%)
Avg MPS
72
20% weight
Turnover
75
39% TRIM/SELL
Coverage
25
37% 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
4
≥4/5 rules · in control
Avg Raw Return
+69.29%
return_pct, unweighted mean
Win Rate
100.0%
% beating SPY (excess>0)
Changed From Current Gate
✕ RSI-Net EBITDA (C-grade, dist=66) → ✓ EPS-ROA PE Score (B-grade, dist=82)
✕ FCF Efficiency (C-grade, dist=70) → ✓ Quality Value Score (C-grade, dist=74)
✕ ROIC-EBITDA QC (B-grade, dist=65) → ✓ ROIC/Ebitda Spread (A-grade, dist=70)
✕ Avg EPS Growth (B-grade, dist=68) → ✓ SM Watson 3 (C-grade, dist=70)
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| EPS-ROA PE Score | B 67 | 29.510 higher | 41.2% | 82 | ADD90 ★★★★★ |
| Quality Value Score | C 57 | 0.030 lower | 20.0% | 74 | ADD84 ★★★★☆ |
| ROIC/Ebitda Spread | A 76 | 18.040 higher | 48.5% | 70 | CANDIDATE94 ★★★★☆ |
| SM Watson 3 | C 46 | 27.830 higher | 44.6% | 70 | CANDIDATE58 ★★★★☆ |
| FCF Quality | D 39 | 0.230 lower | 30.8% | 65 | KEEP38 ★★★★☆ |
| Avg MPS: 57.0 | MAX 361 | ||||
TIGHT18 pass all rules — gate is working. Even 0 is normal. Gated Rank differentiates within this set.
Tickers Scored
4,204
of 5,780 in SM CSV
Pass All Rules
18
0.43% of scored
Score 4+/5
58
1.4% of scored
Max Score
361
total dist points
Score Distribution
5/518 (0.4%)
4/540 (1.0%)
3/5312 (7.4%)
2/5768 (18.3%)
1/52,195 (52.2%)
0/52,447 (58.2%)
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.
● 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.
Upside
- 4 highest-SIL non-gate metrics injected.
- FCF Quality retained as continuity anchor.
Restrictiveness: Unknown — depends on threshold interaction of 4 new rules
Liberal risk: Medium-High — majority of gate replaced
Downside / Risk
- Deep overhaul — 4 rules changed.
- Auto-generated — validate pass-all + overlap.
Signal Independence Grade
?
Overlap
Phase B auto-generated. Check overlap grid.
| Rule | Signal Family | What it measures |
|---|
✓ No HIGH overlaps detected between rules in this gate.
Portfolio Turnover Impact
39%
of held positions would be TRIM/SELL under this gateHIGH TURNOVER
ADD MORE28 positions
ALAB, AMAT, AMD, ANET, APP, ASML, AVGO, CCJ +20 more
HOLD23 positions
AMSC, APH, ARGX, BE, CIEN, COCO, CRS, DASH +15 more
TRIM20 positions
AGX, ALGM, AMZN, BWAY, CAT, DE, EME, IDCC +12 more
SELL12 positions
BLBD, ENVA, ITRN, MLI, MPTI, NXT, P, RSI +4 more
Top Buy Candidates Under This Gate (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | EPS-ROA PE Sco | Quality Value | ROIC/Ebitda Sp | SM Watson 3 | FCF Quality |
|---|---|---|---|---|---|---|---|---|
| PLTR | #2/5780 | 5/5 | 361 | ✓ | ✓ | ✓ | ✓ | ✓ |
| TGTX | #10/5780 | 5/5 | 361 | ✓ | ✓ | ✓ | ✓ | ✓ |
| LQDA | #14/5780 | 5/5 | 361 | ✓ | ✓ | ✓ | ✓ | ✓ |
| NP | #15/5780 | 5/5 | 361 | ✓ | ✓ | ✓ | ✓ | ✓ |
| FICO | #18/5780 | 5/5 | 361 | ✓ | ✓ | ✓ | ✓ | ✓ |
| SNDK | #19/5780 | 4/5 | 296 | ✓ | ✓ | ✓ | ✓ | ✗ |
| ARM | #22/5780 | 4/5 | 291 | ✓ | ✓ | ✗ | ✓ | ✓ |
| HNGE | #23/5780 | 4/5 | 291 | ✓ | ✓ | ✓ | ✗ | ✓ |
| CAI | #24/5780 | 4/5 | 291 | ✓ | ✓ | ✗ | ✓ | ✓ |
| BLLN | #28/5780 | 4/5 | 291 | ✓ | ✓ | ✗ | ✓ | ✓ |
Vs. Current Gate
| Metric | Current | This Alt | Δ |
|---|---|---|---|
| Avg Gate MPS | 55.7 | 57.0 | +1.4 |
| Pass-all count | 14 | 18 | 4 |
| Score 4+/5 count | 119 | 58 | +-61 |
| MAX_WS | 334 | 361 | +27 |
Top-4-SIL + RSI-Net EBITDAScore 52
▼
Auto: top 4 non-gate L2 metrics by sil_score + RSI-Net EBITDA retained from current gate · 4 rules changed · pass-all: 10
Composite Gate Score — 52.3/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
95
30% weight
Ctrl Retention (recall)
2
3/165 (2%)
Avg MPS
72
20% weight
Turnover
25
52% TRIM/SELL
Coverage
25
41% 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
3
≥4/5 rules · in control
Avg Raw Return
+72.87%
return_pct, unweighted mean
Win Rate
100.0%
% beating SPY (excess>0)
Changed From Current Gate
✕ FCF Efficiency (C-grade, dist=70) → ✓ EPS-ROA PE Score (B-grade, dist=82)
✕ ROIC-EBITDA QC (B-grade, dist=65) → ✓ Quality Value Score (C-grade, dist=74)
✕ Avg EPS Growth (B-grade, dist=68) → ✓ ROIC/Ebitda Spread (A-grade, dist=70)
✕ FCF Quality (D-grade, dist=65) → ✓ SM Watson 3 (C-grade, dist=70)
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| EPS-ROA PE Score | B 67 | 29.510 higher | 41.2% | 82 | ADD90 ★★★★★ |
| Quality Value Score | C 57 | 0.030 lower | 20.0% | 74 | ADD84 ★★★★☆ |
| ROIC/Ebitda Spread | A 76 | 18.040 higher | 48.5% | 70 | CANDIDATE94 ★★★★☆ |
| SM Watson 3 | C 46 | 27.830 higher | 44.6% | 70 | CANDIDATE58 ★★★★☆ |
| RSI-Net EBITDA | C 60 | 194.850 higher | 48.5% | 66 | KEEP18 ★★★★☆ |
| Avg MPS: 61.1 | MAX 362 | ||||
TIGHT10 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
10
0.17% of scored
Score 4+/5
34
0.6% of scored
Max Score
362
total dist points
Score Distribution
5/510 (0.2%)
4/524 (0.4%)
3/5102 (1.8%)
2/5573 (9.9%)
1/52,557 (44.2%)
0/52,514 (43.5%)
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.
● 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.
Upside
- 4 highest-SIL non-gate metrics injected.
- RSI-Net EBITDA retained as continuity anchor.
Restrictiveness: Unknown — depends on threshold interaction of 4 new rules
Liberal risk: Medium-High — majority of gate replaced
Downside / Risk
- Deep overhaul — 4 rules changed.
- Auto-generated — validate pass-all + overlap.
Signal Independence Grade
?
Overlap
Phase B auto-generated. Check overlap grid.
| Rule | Signal Family | What it measures |
|---|
✓ No HIGH overlaps detected between rules in this gate.
Portfolio Turnover Impact
52%
of held positions would be TRIM/SELL under this gateHIGH TURNOVER
ADD MORE20 positions
ALAB, AMAT, AMD, ANET, APP, ASML, CCJ, CRDO +12 more
HOLD20 positions
AMSC, ARGX, AVGO, BE, CIEN, CLS, DASH, FTNT +12 more
TRIM26 positions
AGX, APH, BWAY, COCO, CRS, DE, EME, FIX +18 more
SELL17 positions
ALGM, AMZN, BLBD, CAT, ENVA, ITRN, MCK, MLI +9 more
Top Buy Candidates Under This Gate (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | EPS-ROA PE Sco | Quality Value | ROIC/Ebitda Sp | SM Watson 3 | RSI-Net EBITDA |
|---|---|---|---|---|---|---|---|---|
| PLTR | #2/5780 | 5/5 | 362 | ✓ | ✓ | ✓ | ✓ | ✓ |
| TGTX | #8/5780 | 5/5 | 362 | ✓ | ✓ | ✓ | ✓ | ✓ |
| NP | #10/5780 | 5/5 | 362 | ✓ | ✓ | ✓ | ✓ | ✓ |
| SNDK | #15/5780 | 4/5 | 296 | ✓ | ✓ | ✓ | ✓ | ✗ |
| LQDA | #16/5780 | 4/5 | 296 | ✓ | ✓ | ✓ | ✓ | ✗ |
| FICO | #20/5780 | 4/5 | 296 | ✓ | ✓ | ✓ | ✓ | ✗ |
| ARM | #22/5780 | 4/5 | 292 | ✓ | ✓ | ✗ | ✓ | ✓ |
| HNGE | #23/5780 | 4/5 | 292 | ✓ | ✓ | ✓ | ✗ | ✓ |
| CAI | #24/5780 | 4/5 | 292 | ✓ | ✓ | ✗ | ✓ | ✓ |
| BLLN | #28/5780 | 4/5 | 292 | ✓ | ✓ | ✗ | ✓ | ✓ |
Vs. Current Gate
| Metric | Current | This Alt | Δ |
|---|---|---|---|
| Avg Gate MPS | 55.7 | 61.1 | +5.4 |
| Pass-all count | 14 | 10 | +-4 |
| Score 4+/5 count | 119 | 34 | +-85 |
| MAX_WS | 334 | 362 | +28 |
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: 9
Composite Gate Score — 51.9/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
95
30% weight
Ctrl Retention (recall)
1
1/165 (1%)
Avg MPS
72
20% weight
Turnover
25
55% TRIM/SELL
Coverage
25
40% 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
1
≥4/5 rules · in control
Avg Raw Return
+128.20%
return_pct, unweighted mean
Win Rate
100.0%
% beating SPY (excess>0)
Changed From Current Gate
✕ RSI-Net EBITDA (C-grade, dist=66) → ✓ EPS-ROA PE Score (B-grade, dist=82)
✕ FCF Efficiency (C-grade, dist=70) → ✓ Quality Value Score (C-grade, dist=74)
✕ Avg EPS Growth (B-grade, dist=68) → ✓ ROIC/Ebitda Spread (A-grade, dist=70)
✕ FCF Quality (D-grade, dist=65) → ✓ SM Watson 3 (C-grade, dist=70)
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| EPS-ROA PE Score | B 67 | 29.510 higher | 41.2% | 82 | ADD90 ★★★★★ |
| Quality Value Score | C 57 | 0.030 lower | 20.0% | 74 | ADD84 ★★★★☆ |
| ROIC/Ebitda Spread | A 76 | 18.040 higher | 48.5% | 70 | CANDIDATE94 ★★★★☆ |
| SM Watson 3 | C 46 | 27.830 higher | 44.6% | 70 | CANDIDATE58 ★★★★☆ |
| ROIC-EBITDA QC | B 61 | 126.010 higher | 43.9% | 65 | KEEP38 ★★★★☆ |
| Avg MPS: 61.4 | MAX 361 | ||||
TIGHT9 pass all rules — gate is working. Even 0 is normal. Gated Rank differentiates within this set.
Tickers Scored
4,204
of 5,780 in SM CSV
Pass All Rules
9
0.21% of scored
Score 4+/5
29
0.7% of scored
Max Score
361
total dist points
Score Distribution
5/59 (0.2%)
4/520 (0.5%)
3/569 (1.6%)
2/5474 (11.3%)
1/52,659 (63.2%)
0/52,549 (60.6%)
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.
● 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.
Upside
- 4 highest-SIL non-gate metrics injected.
- ROIC-EBITDA QC retained as continuity anchor.
Restrictiveness: Unknown — depends on threshold interaction of 4 new rules
Liberal risk: Medium-High — majority of gate replaced
Downside / Risk
- Deep overhaul — 4 rules changed.
- Auto-generated — validate pass-all + overlap.
Signal Independence Grade
?
Overlap
Phase B auto-generated. Check overlap grid.
| Rule | Signal Family | What it measures |
|---|
✓ No HIGH overlaps detected between rules in this gate.
Portfolio Turnover Impact
55%
of held positions would be TRIM/SELL under this gateHIGH TURNOVER
ADD MORE18 positions
ALAB, AMAT, ANET, APP, ASML, CRDO, FTNT, INOD +10 more
HOLD19 positions
AGX, AMD, AMSC, ARGX, AVGO, CCJ, CLS, COCO +11 more
TRIM25 positions
APH, BE, CIEN, CRS, DASH, DE, EME, FIX +17 more
SELL21 positions
ALGM, AMZN, BLBD, BWAY, CAT, ENVA, ITRN, MCK +13 more
Top Buy Candidates Under This Gate (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | EPS-ROA PE Sco | Quality Value | ROIC/Ebitda Sp | SM Watson 3 | ROIC-EBITDA QC |
|---|---|---|---|---|---|---|---|---|
| PLTR | #2/5780 | 5/5 | 361 | ✓ | ✓ | ✓ | ✓ | ✓ |
| SNDK | #9/5780 | 5/5 | 361 | ✓ | ✓ | ✓ | ✓ | ✓ |
| TGTX | #13/5780 | 4/5 | 296 | ✓ | ✓ | ✓ | ✓ | ✗ |
| LQDA | #15/5780 | 4/5 | 296 | ✓ | ✓ | ✓ | ✓ | ✗ |
| NP | #16/5780 | 4/5 | 296 | ✓ | ✓ | ✓ | ✓ | — |
| FICO | #20/5780 | 4/5 | 296 | ✓ | ✓ | ✓ | ✓ | — |
| ARM | #22/5780 | 4/5 | 291 | ✓ | ✓ | ✗ | ✓ | ✓ |
| HNGE | #23/5780 | 4/5 | 291 | ✓ | ✓ | ✓ | ✗ | ✓ |
| APPF | #24/5780 | 4/5 | 291 | ✓ | ✓ | ✓ | ✗ | ✓ |
| NVEC | #28/5780 | 4/5 | 279 | — | ✓ | ✓ | ✓ | ✓ |
Vs. Current Gate
| Metric | Current | This Alt | Δ |
|---|---|---|---|
| Avg Gate MPS | 55.7 | 61.4 | +5.7 |
| Pass-all count | 14 | 9 | +-5 |
| Score 4+/5 count | 119 | 29 | +-90 |
| MAX_WS | 334 | 361 | +27 |
Top-4-SIL + FCF EfficiencyScore 51
▼
Auto: top 4 non-gate L2 metrics by sil_score + FCF Efficiency retained from current gate · 4 rules changed · pass-all: 15
Composite Gate Score — 50.8/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
80
30% weight
Ctrl Retention (recall)
3
5/165 (3%)
Avg MPS
73
20% weight
Turnover
50
42% TRIM/SELL
Coverage
25
40% 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
5
≥4/5 rules · in control
Avg Raw Return
+63.26%
return_pct, unweighted mean
Win Rate
100.0%
% beating SPY (excess>0)
Changed From Current Gate
✕ RSI-Net EBITDA (C-grade, dist=66) → ✓ EPS-ROA PE Score (B-grade, dist=82)
✕ ROIC-EBITDA QC (B-grade, dist=65) → ✓ Quality Value Score (C-grade, dist=74)
✕ Avg EPS Growth (B-grade, dist=68) → ✓ ROIC/Ebitda Spread (A-grade, dist=70)
✕ FCF Quality (D-grade, dist=65) → ✓ SM Watson 3 (C-grade, dist=70)
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| EPS-ROA PE Score | B 67 | 29.510 higher | 41.2% | 82 | ADD90 ★★★★★ |
| Quality Value Score | C 57 | 0.030 lower | 20.0% | 74 | ADD84 ★★★★☆ |
| ROIC/Ebitda Spread | A 76 | 18.040 higher | 48.5% | 70 | CANDIDATE94 ★★★★☆ |
| SM Watson 3 | C 46 | 27.830 higher | 44.6% | 70 | CANDIDATE58 ★★★★☆ |
| FCF Efficiency | C 52 | 0.060 lower | 44.6% | 70 | KEEP78 ★★★★☆ |
| Avg MPS: 59.6 | MAX 366 | ||||
TIGHT15 pass all rules — gate is working. Even 0 is normal. Gated Rank differentiates within this set.
Tickers Scored
4,204
of 5,780 in SM CSV
Pass All Rules
15
0.36% of scored
Score 4+/5
50
1.2% of scored
Max Score
366
total dist points
Score Distribution
5/515 (0.4%)
4/535 (0.8%)
3/5326 (7.8%)
2/5518 (12.3%)
1/52,398 (57.0%)
0/52,488 (59.2%)
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.
● 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.
Upside
- 4 highest-SIL non-gate metrics injected.
- FCF Efficiency retained as continuity anchor.
Restrictiveness: Unknown — depends on threshold interaction of 4 new rules
Liberal risk: Medium-High — majority of gate replaced
Downside / Risk
- Deep overhaul — 4 rules changed.
- Auto-generated — validate pass-all + overlap.
Signal Independence Grade
?
Overlap
Phase B auto-generated. Check overlap grid.
| Rule | Signal Family | What it measures |
|---|
✓ No HIGH overlaps detected between rules in this gate.
Portfolio Turnover Impact
42%
of held positions would be TRIM/SELL under this gateHIGH TURNOVER
ADD MORE26 positions
ALAB, AMAT, AMD, ANET, APP, ASML, AVGO, CCJ +18 more
HOLD22 positions
AMSC, ARGX, BE, CIEN, COCO, CRS, DASH, GEV +14 more
TRIM21 positions
AGX, ALGM, AMZN, APH, BWAY, DE, EME, FIX +13 more
SELL14 positions
BLBD, CAT, ENVA, ITRN, MCK, MLI, MPTI, NXT +6 more
Top Buy Candidates Under This Gate (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | EPS-ROA PE Sco | Quality Value | ROIC/Ebitda Sp | SM Watson 3 | FCF Efficiency |
|---|---|---|---|---|---|---|---|---|
| PLTR | #2/5780 | 5/5 | 366 | ✓ | ✓ | ✓ | ✓ | ✓ |
| TGTX | #10/5780 | 5/5 | 366 | ✓ | ✓ | ✓ | ✓ | ✓ |
| LQDA | #12/5780 | 5/5 | 366 | ✓ | ✓ | ✓ | ✓ | ✓ |
| NP | #13/5780 | 5/5 | 366 | ✓ | ✓ | ✓ | ✓ | ✓ |
| ARM | #17/5780 | 4/5 | 296 | ✓ | ✓ | ✗ | ✓ | ✓ |
| HNGE | #18/5780 | 4/5 | 296 | ✓ | ✓ | ✓ | ✗ | ✓ |
| CAI | #19/5780 | 4/5 | 296 | ✓ | ✓ | ✗ | ✓ | ✓ |
| BLLN | #23/5780 | 4/5 | 296 | ✓ | ✓ | ✗ | ✓ | ✓ |
| KRMN | #25/5780 | 4/5 | 296 | ✓ | ✓ | ✗ | ✓ | ✓ |
| SNDK | #32/5780 | 4/5 | 296 | ✓ | ✓ | ✓ | ✓ | ✗ |
Vs. Current Gate
| Metric | Current | This Alt | Δ |
|---|---|---|---|
| Avg Gate MPS | 55.7 | 59.6 | +3.9 |
| Pass-all count | 14 | 15 | 1 |
| Score 4+/5 count | 119 | 50 | +-69 |
| MAX_WS | 334 | 366 | +32 |
Top-4-SIL + Avg EPS GrowthScore 50
▼
Auto: top 4 non-gate L2 metrics by sil_score + Avg EPS Growth retained from current gate · 4 rules changed · pass-all: 15
Composite Gate Score — 50.5/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
80
30% weight
Ctrl Retention (recall)
2
4/165 (2%)
Avg MPS
73
20% weight
Turnover
50
49% TRIM/SELL
Coverage
25
45% 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
4
≥4/5 rules · in control
Avg Raw Return
+69.29%
return_pct, unweighted mean
Win Rate
100.0%
% beating SPY (excess>0)
Changed From Current Gate
✕ RSI-Net EBITDA (C-grade, dist=66) → ✓ EPS-ROA PE Score (B-grade, dist=82)
✕ FCF Efficiency (C-grade, dist=70) → ✓ Quality Value Score (C-grade, dist=74)
✕ ROIC-EBITDA QC (B-grade, dist=65) → ✓ ROIC/Ebitda Spread (A-grade, dist=70)
✕ FCF Quality (D-grade, dist=65) → ✓ SM Watson 3 (C-grade, dist=70)
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| EPS-ROA PE Score | B 67 | 29.510 higher | 41.2% | 82 | ADD90 ★★★★★ |
| Quality Value Score | C 57 | 0.030 lower | 20.0% | 74 | ADD84 ★★★★☆ |
| ROIC/Ebitda Spread | A 76 | 18.040 higher | 48.5% | 70 | CANDIDATE94 ★★★★☆ |
| SM Watson 3 | C 46 | 27.830 higher | 44.6% | 70 | CANDIDATE58 ★★★★☆ |
| Avg EPS Growth | B 66 | 39.650 higher | 69.6% | 68 | KEEP78 ★★★★☆ |
| Avg MPS: 62.4 | MAX 364 | ||||
TIGHT15 pass all rules — gate is working. Even 0 is normal. Gated Rank differentiates within this set.
Tickers Scored
4,640
of 5,780 in SM CSV
Pass All Rules
15
0.32% of scored
Score 4+/5
38
0.8% of scored
Max Score
364
total dist points
Score Distribution
5/515 (0.3%)
4/523 (0.5%)
3/5171 (3.7%)
2/5944 (20.3%)
1/52,345 (50.5%)
0/52,282 (49.2%)
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.
● 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.
Upside
- 4 highest-SIL non-gate metrics injected.
- Avg EPS Growth retained as continuity anchor.
Restrictiveness: Unknown — depends on threshold interaction of 4 new rules
Liberal risk: Medium-High — majority of gate replaced
Downside / Risk
- Deep overhaul — 4 rules changed.
- Auto-generated — validate pass-all + overlap.
Signal Independence Grade
?
Overlap
Phase B auto-generated. Check overlap grid.
| Rule | Signal Family | What it measures |
|---|
✓ No HIGH overlaps detected between rules in this gate.
Portfolio Turnover Impact
49%
of held positions would be TRIM/SELL under this gateHIGH TURNOVER
ADD MORE21 positions
ALAB, AMAT, AMD, ANET, APP, ASML, AVGO, CLS +13 more
HOLD21 positions
BE, CCJ, CIEN, DASH, FIX, FTNT, GOOG, INOD +13 more
TRIM25 positions
AGX, ALGM, AMSC, APH, ARGX, BWAY, COCO, CRS +17 more
SELL16 positions
AMZN, BLBD, CAT, ENVA, ITRN, MCK, MLI, MPTI +8 more
Top Buy Candidates Under This Gate (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | EPS-ROA PE Sco | Quality Value | ROIC/Ebitda Sp | SM Watson 3 | Avg EPS Growth |
|---|---|---|---|---|---|---|---|---|
| PLTR | #2/5780 | 5/5 | 364 | ✓ | ✓ | ✓ | ✓ | ✓ |
| TGTX | #10/5780 | 5/5 | 364 | ✓ | ✓ | ✓ | ✓ | ✓ |
| SNDK | #13/5780 | 5/5 | 364 | ✓ | ✓ | ✓ | ✓ | ✓ |
| LQDA | #14/5780 | 5/5 | 364 | ✓ | ✓ | ✓ | ✓ | ✓ |
| NP | #17/5780 | 4/5 | 296 | ✓ | ✓ | ✓ | ✓ | ✗ |
| FICO | #20/5780 | 4/5 | 296 | ✓ | ✓ | ✓ | ✓ | ✗ |
| CAI | #22/5780 | 4/5 | 294 | ✓ | ✓ | ✗ | ✓ | ✓ |
| BLLN | #26/5780 | 4/5 | 294 | ✓ | ✓ | ✗ | ✓ | ✓ |
| KRMN | #28/5780 | 4/5 | 294 | ✓ | ✓ | ✗ | ✓ | ✓ |
| PLBY | #31/5780 | 4/5 | 294 | ✓ | ✓ | ✗ | ✓ | ✓ |
Vs. Current Gate
| Metric | Current | This Alt | Δ |
|---|---|---|---|
| Avg Gate MPS | 55.7 | 62.4 | +6.7 |
| Pass-all count | 14 | 15 | 1 |
| Score 4+/5 count | 119 | 38 | +-81 |
| MAX_WS | 334 | 364 | +30 |
Alt 5 — Balanced Independence ⭐ RecommendedRECOMMENDEDScore 42
▼
Best balance of MPS grade, signal independence, coverage, and direction confidence · 4 rules changed · pass-all: 135
Composite Gate Score — 42.2/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
20
30% weight
Ctrl Retention (recall)
36
60/165 (36%)
Avg MPS
58
20% weight
Turnover
75
28% TRIM/SELL
Coverage
25
37% 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
117
≥4/5 rules · in control
Avg Raw Return
+23.52%
return_pct, unweighted mean
Win Rate
51.3%
% beating SPY (excess>0)
Why This Is Recommended
- Resolves both open CRITICAL signals: direction AT_RISK (Watson 5) and F-grade weakness (PEG)
- Introduces the two highest-MPS unrepresented metrics: FCF Efficency (#1, 94.47) + FCF-EBITDA CS (#3, 91.0)
- Zero direction conflicts — all rules have confirmed winner direction from both cohort and control signals
- No HIGH overlap pairs — gate delivers 5 meaningfully independent screening signals
- Watson-ROIC CI adds ROIC-quality anchor that differentiates from pure FCF focus
- Lowest liberal-risk of all alternatives that drop Watson 5
Changed From Current Gate
✕ RSI-Net EBITDA (C-grade, dist=66) → ✓ FCF-EBITDA Convergence Score (B-grade, dist=59)
✕ ROIC-EBITDA QC (B-grade, dist=65) → ✓ P/S v P/C Multiple (B-grade, dist=57)
✕ Avg EPS Growth (B-grade, dist=68) → ✓ Watson-ROIC Confidence Index (C-grade, dist=45)
✕ FCF Quality (D-grade, dist=65) → ✓ (none)
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| FCF Efficency | C 52 | 0.060 lower | 44.6% | 70 | KEEP78 ★★★★☆ |
| FCF-EBITDA Convergence Score | B 63 | 2.210 lower | 30.9% | 59 | CANDIDATE64 ★★★☆☆ |
| P/S v P/C Multiple | B 70 | 12.450 lower | 40.0% | 57 | CANDIDATE50 ★★★☆☆ |
| Watson-ROIC Confidence Index | C 59 | 8.980 lower | 33.1% | 45 | CANDIDATE80 ★★★☆☆ |
| Avg MPS: 61.1 | MAX 231 | ||||
TOO LIBERAL135 pass all rules — gate is letting too many through. Tighten thresholds or add a stricter rule.
Tickers Scored
4,808
of 5,780 in SM CSV
Pass All Rules
135
2.81% of scored
Score 4+/5
135
2.8% of scored
Max Score
231
total dist points
Score Distribution
4/4135 (2.8%)
3/41,017 (21.2%)
2/41,605 (33.4%)
1/41,839 (38.2%)
0/41,184 (24.6%)
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.
● 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.
Upside
- No HIGH overlaps between any rule pair — most independent gate structure of all alternatives
- 4 A-grade metrics (MPS 75+), 1 C-grade — strong average MPS 84.1
- All 5 rules have direction-confirmed status (no AT_RISK, no locked conflicts)
- Watson-ROIC CI adds a ROIC×Watson quality signal not present in any other gate combination
- FCF Efficency (#1 by MPS at 94.47) finally enters the gate — currently excluded despite being top signal
- FCF-EBITDA CS (#3 by MPS at 91.0) provides the FCF-to-EBITDA quality bridge signal
- Eliminates both current gate problems: Watson 5 direction conflict + PEG F-grade
- 5 distinct signal families: Quality Composite + FCF Efficiency + FCF-EBITDA + Valuation Ratio + ROIC-Watson
Restrictiveness: Moderate to strict — FCF Efficency and FCF-EBITDA CS jointly set a high FCF quality bar
Liberal risk: Low-Medium — Watson-ROIC CI provides non-FCF quality backstop
Downside / Risk
- Watson-ROIC CI is C-grade (MPS 56.04) — weakest rule in the gate
- FCF Efficency only 47.1% ticker coverage — some tickers scored on 4/5 rules
- FCF-EBITDA CS flagged as "HIGH input overlap" in SIL due to formula chain — METRIC_OVERLAP_MAP needs v8 review
- Watson-ROIC CI has 48.6% coverage — two rules below 65% threshold
- Removing Wtd FCF Eff loses a rule that has accumulated gate history (v6-v8)
Signal Independence Grade
A
Overlap
No HIGH overlaps, no direction conflicts. FCF family fills 2 slots but col31 and col54 are distinct formulas with LOW overlap (share EV/EBITDA indirectly only). 5 meaningful signal dimensions.
| Rule | Signal Family | What it measures |
|---|---|---|
| FCF Efficency | FCF Efficiency | FCF Yield / EV_EBITDA — raw FCF quality |
| FCF-EBITDA Conv. Score | FCF-Quality Bridge | Wtd FCF Eff × PFCF/EBITDA — different formula from col31 ✓ |
| P/S v P/C Multiple | Valuation | Pure price-ratio — independent ✓ |
| Watson-ROIC CI | ROIC Confidence | ROIC×Watson confidence index — no FCF inputs ✓ |
LOW · FCF Efficency (31) × FCF-EBITDA CS (54)
col54 = col42 × col34; col31 shares col3 (EV/EBITDA) as indirect input only. Acceptable.
Portfolio Turnover Impact
28%
of held positions would be TRIM/SELL under this gate
ADD MORE43 positions
ALAB, ALGM, AMAT, AMD, AMSC, AMZN, ANET, ARGX +35 more
HOLD17 positions
APH, ASML, DE, ENVA, GEV, IESC, LLY, MOD +9 more
TRIM14 positions
AGX, APP, CAT, CLS, FIX, GOOG, IDCC, IDR +6 more
SELL9 positions
BLBD, EME, ITRN, MCK, MLI, NXT, SEZL, STRL +1 more
Top Buy Candidates Under This Gate (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | FCF Efficency | FCF-EBITDA Con | P/S v P/C Mult | Watson-ROIC Co |
|---|---|---|---|---|---|---|---|
| CORT | #1/5780 | 4/4 | 231 | ✓ | ✓ | ✓ | ✓ |
| PTGX | #2/5780 | 4/4 | 231 | ✓ | ✓ | ✓ | ✓ |
| CDNA | #4/5780 | 4/4 | 231 | ✓ | ✓ | ✓ | ✓ |
| BLFS | #6/5780 | 4/4 | 231 | ✓ | ✓ | ✓ | ✓ |
| FORM | #7/5780 | 4/4 | 231 | ✓ | ✓ | ✓ | ✓ |
| ALM | #8/5780 | 4/4 | 231 | ✓ | ✓ | ✓ | ✓ |
| ANIK | #9/5780 | 4/4 | 231 | ✓ | ✓ | ✓ | ✓ |
| ARM | #10/5780 | 4/4 | 231 | ✓ | ✓ | ✓ | ✓ |
| FSLY | #11/5780 | 4/4 | 231 | ✓ | ✓ | ✓ | ✓ |
| SHOP | #12/5780 | 4/4 | 231 | ✓ | ✓ | ✓ | ✓ |
Vs. Current Gate
| Metric | Current | This Alt | Δ |
|---|---|---|---|
| Avg Gate MPS | 55.7 | 61.1 | +5.4 |
| Pass-all count | 14 | 135 | 121 |
| Score 4+/5 count | 119 | 135 | 16 |
| MAX_WS | 334 | 231 | -103 |
Alt 3 — Maximum A-GradeScore 41
▼
Maximize average MPS score — all 5 rules A-grade, zero B/F rules · 4 rules changed · pass-all: 367
Composite Gate Score — 40.8/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
0
30% weight
Ctrl Retention (recall)
50
82/165 (50%)
Avg MPS
57
20% weight
Turnover
90
22% TRIM/SELL
Coverage
25
38% avg
Dir Health
85
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
196
≥4/5 rules · in control
Avg Raw Return
+18.60%
return_pct, unweighted mean
Win Rate
41.8%
% beating SPY (excess>0)
Changed From Current Gate
✕ RSI-Net EBITDA (C-grade, dist=66) → ✓ FCF-EBITDA Convergence Score (B-grade, dist=59)
✕ ROIC-EBITDA QC (B-grade, dist=65) → ✓ P/S v P/C Multiple (B-grade, dist=57)
✕ Avg EPS Growth (B-grade, dist=68) → ✓ ROIC-FCF Quality Gate (C-grade, dist=42)
✕ FCF Quality (D-grade, dist=65) → ✓ (none)
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| FCF Efficency | C 52 | 0.060 lower | 44.6% | 70 | KEEP78 ★★★★☆ |
| FCF-EBITDA Convergence Score | B 63 | 2.210 lower | 30.9% | 59 | CANDIDATE64 ★★★☆☆ |
| P/S v P/C Multiple | B 70 | 12.450 lower | 40.0% | 57 | CANDIDATE50 ★★★☆☆ |
| ROIC-FCF Quality Gate DIR_LOCK | C 56 | 0.120 lower | 38.4% | 42 | CANDIDATE58 ★★★☆☆ |
| Avg MPS: 60.3 | MAX 228 | ||||
UNUSABLE367 pass all rules — gate does not function as a filter. Hundreds passing means the rules have no discriminating power at current thresholds. Do not use this configuration without significant tightening.
Tickers Scored
4,800
of 5,780 in SM CSV
Pass All Rules
367
7.65% of scored
Score 4+/5
367
7.6% of scored
Max Score
228
total dist points
Score Distribution
4/4367 (7.6%)
3/41,662 (34.6%)
2/4666 (13.9%)
1/41,851 (38.6%)
0/41,234 (25.7%)
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.
● 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.
Upside
- All 5 rules are A-grade (MPS ≥ 79) — highest possible average grade combination
- Average gate MPS: 84.9 (vs 68.6 current)
- FCF-EBITDA CS and FCF Efficency are SIL's top two ranked metrics by confidence
- No B or F grade rules — eliminates two weakest current gate signals
Restrictiveness: More restrictive — two high-threshold A-grade FCF rules act as tighter joint filter
Liberal risk: Low — but if both FCF signals simultaneously fail in a market cycle, nothing else catches it
Downside / Risk
- Still FCF-heavy: FCF Efficency + FCF-EBITDA CS both trace to FCF family
- FCF Efficency (47.1%) and FCF-EBITDA CS (70.3%) combined reduce effective ticker universe
- ROIC-FCF Gate direction lock conflict still present
- SIL flags FCF-EBITDA CS as "HIGH input overlap" — may not add independent signal beyond current gate
- Removing Wtd FCF Eff loses a B-grade rule that has performed well in the gate
Signal Independence Grade
B+
Overlap
No HIGH overlaps — Wtd FCF Eff removed, eliminating the main conflict. FCF family still fills 2 of 5 slots. LOW overlap between col31 and col54 (share EV/EBITDA as indirect input only). One DIR_LOCK.
| Rule | Signal Family | What it measures |
|---|---|---|
| FCF Efficency | FCF Efficiency | FCF Yield / EV_EBITDA — raw FCF quality |
| FCF-EBITDA Conv. Score | FCF-Quality Bridge | FCF×EBITDA convergence — different angle from col31 ✓ |
| P/S v P/C Multiple | Valuation | Pure price-ratio — independent ✓ |
| ROIC-FCF Quality Gate | ROIC Quality | ROIC+FCF composite gate — direction lock ⚠ |
LOW · FCF Efficency (31) × FCF-EBITDA CS (54)
col54 = col42 × col34 (not col31). Col31 and col54 share col3 (EV/EBITDA) as an indirect input only.
Portfolio Turnover Impact
22%
of held positions would be TRIM/SELL under this gate
ADD MORE42 positions
ALAB, ALGM, AMAT, AMD, AMSC, AMZN, ANET, ARGX +34 more
HOLD23 positions
AGX, APH, ASML, CRS, DE, ENVA, GEV, HWM +15 more
TRIM16 positions
APP, BLBD, CAT, CLS, EME, FIX, GOOG, IDR +8 more
SELL2 positions
MCK, WDC
Top Buy Candidates Under This Gate (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | FCF Efficency | FCF-EBITDA Con | P/S v P/C Mult | ROIC-FCF Quali |
|---|---|---|---|---|---|---|---|
| CORT | #1/5780 | 4/4 | 228 | ✓ | ✓ | ✓ | ✓ |
| PTGX | #2/5780 | 4/4 | 228 | ✓ | ✓ | ✓ | ✓ |
| OSS | #5/5780 | 4/4 | 228 | ✓ | ✓ | ✓ | ✓ |
| ALM | #6/5780 | 4/4 | 228 | ✓ | ✓ | ✓ | ✓ |
| ANIK | #7/5780 | 4/4 | 228 | ✓ | ✓ | ✓ | ✓ |
| ARM | #8/5780 | 4/4 | 228 | ✓ | ✓ | ✓ | ✓ |
| FSLY | #9/5780 | 4/4 | 228 | ✓ | ✓ | ✓ | ✓ |
| OMDA | #10/5780 | 4/4 | 228 | ✓ | ✓ | ✓ | ✓ |
| SMWB | #11/5780 | 4/4 | 228 | ✓ | ✓ | ✓ | ✓ |
| ATRC | #12/5780 | 4/4 | 228 | ✓ | ✓ | ✓ | ✓ |
Vs. Current Gate
| Metric | Current | This Alt | Δ |
|---|---|---|---|
| Avg Gate MPS | 55.7 | 60.3 | +4.6 |
| Pass-all count | 14 | 367 | 353 |
| Score 4+/5 count | 119 | 367 | 248 |
| MAX_WS | 334 | 228 | -106 |
Experimental L1Accumulate control lab sessions before promoting
Alt 7 — L1+L2 Hybrid 🧪 ExperimentalScore 44
▼
Best L1 signal anchored by top L2 quality checks — tests if raw signals add lift · 4 rules changed · pass-all: 35
Composite Gate Score — 43.5/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
60
30% weight
Ctrl Retention (recall)
10
17/165 (10%)
Avg MPS
56
20% weight
Turnover
50
42% TRIM/SELL
Coverage
25
43% 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
48
≥4/5 rules · in control
Avg Raw Return
+18.47%
return_pct, unweighted mean
Win Rate
35.4%
% beating SPY (excess>0)
Changed From Current Gate
✕ RSI-Net EBITDA (C-grade, dist=66) → ✓ RSI (B-grade, dist=42)
✕ ROIC-EBITDA QC (B-grade, dist=65) → ✓ P/C (C-grade, dist=52)
✕ Avg EPS Growth (B-grade, dist=68) → ✓ FCF-EBITDA Convergence Score (B-grade, dist=59)
✕ FCF Quality (D-grade, dist=65) → ✓ (none)
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| RSI L1·EXP | B 62 | 42.530 lower | 96.8% | 42 | CANDIDATE ★★★☆☆ |
| P/C L1·EXP | C 60 | 3.230 lower | 0.0% | 52 | CANDIDATE ★★★☆☆ |
| FCF Efficency | C 52 | 0.060 lower | 44.6% | 70 | KEEP78 ★★★★☆ |
| FCF-EBITDA Convergence Score | B 63 | 2.210 lower | 30.9% | 59 | CANDIDATE64 ★★★☆☆ |
| Avg MPS: 59.0 | MAX 223 | ||||
MODERATE35 pass all rules — manageable. Sort by Gated Score, review top 10–15.
Tickers Scored
5,599
of 5,780 in SM CSV
Pass All Rules
35
0.63% of scored
Score 4+/5
35
0.6% of scored
Max Score
223
total dist points
Score Distribution
4/435 (0.6%)
3/4400 (7.1%)
2/41,233 (22.0%)
1/42,055 (36.7%)
0/42,057 (36.7%)
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.
● 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.
Upside
- RSI provides momentum anchor absent from all current L2 gates
- P/C (L1) is simpler and more direct than P/S v P/C Multiple (L2) — same dimension
- FCF Efficency (#1 MPS at 95.96) + FCF-EBITDA CS (#3 at 95.38) as quality anchors
- QVS (col27, A-grade) adds profitability-quality filter
- Tests whether L1 momentum signal adds lift on top of L2 quality signals
Restrictiveness: Likely moderate — RSI momentum filter may be loose at universe-percentile threshold
Liberal risk: Medium — RSI threshold needs validation; FCF quality rules provide backstop
Downside / Risk
- RSI threshold is experimental — universe percentile may not match optimal momentum zone
- P/C L1 threshold experimental — L2 P/S v P/C Multiple has validated threshold
- FCF Efficency 47.1% coverage — some tickers scored on 4/5 rules only
- FCF-EBITDA CS flagged HIGH input overlap in SIL — METRIC_OVERLAP_MAP v8 review needed
- Two experimental thresholds (L1) mixed with three validated thresholds (L2) — hard to diagnose if wrong
Signal Independence Grade
B+
Overlap
No HIGH overlaps. L1 rules (RSI, P/C) cover momentum + valuation dimensions absent from L2 rules. LOW overlap between col31 and col54 (indirect EV/EBITDA input).
| Rule | Signal Family | What it measures |
|---|---|---|
| RSI | Momentum | Price momentum — L1 raw, no formula chain ✓ |
| P/C | Price/Cash | Raw price vs cash — simpler than L2 P/S v P/C ✓ |
| FCF Efficency | FCF Efficiency | FCF Yield / EV_EBITDA — top MPS signal ✓ |
| FCF-EBITDA Conv. Score | FCF-Quality Bridge | Wtd FCF × PFCF/EBITDA — needs overlap review ⚠ |
LOW · FCF Efficency (31) × FCF-EBITDA CS (54)
col54 uses col42 internally; col31 shares EV/EBITDA as indirect input only.
Portfolio Turnover Impact
42%
of held positions would be TRIM/SELL under this gateHIGH TURNOVER
ADD MORE13 positions
ALAB, ALGM, AMSC, AVGO, COCO, GEV, HWM, KLAC +5 more
HOLD35 positions
AMAT, AMD, AMZN, ANET, ARGX, BE, CIEN, CLS +27 more
TRIM20 positions
AGX, APH, APP, ASML, BLBD, BWAY, CAT, CCJ +12 more
SELL15 positions
DE, EME, GOOG, IDCC, IDR, MCK, MLI, MNST +7 more
Top Buy Candidates Under This Gate (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | RSI | P/C | FCF Efficency | FCF-EBITDA Con |
|---|---|---|---|---|---|---|---|
| KLAR | #1/5780 | 4/4 | 223 | ✓ | ✓ | ✓ | ✓ |
| ALAR | #2/5780 | 4/4 | 223 | ✓ | ✓ | ✓ | ✓ |
| VNET | #3/5780 | 4/4 | 223 | ✓ | ✓ | ✓ | ✓ |
| UCL | #4/5780 | 4/4 | 223 | ✓ | ✓ | ✓ | ✓ |
| JBLU | #5/5780 | 4/4 | 223 | ✓ | ✓ | ✓ | ✓ |
| ALK | #6/5780 | 4/4 | 223 | ✓ | ✓ | ✓ | ✓ |
| LDI | #7/5780 | 4/4 | 223 | ✓ | ✓ | ✓ | ✓ |
| PENN | #8/5780 | 4/4 | 223 | ✓ | ✓ | ✓ | ✓ |
| CMTG | #9/5780 | 4/4 | 223 | ✓ | ✓ | ✓ | ✓ |
| SWAG | #10/5780 | 4/4 | 223 | ✓ | ✓ | ✓ | ✓ |
Vs. Current Gate
| Metric | Current | This Alt | Δ |
|---|---|---|---|
| Avg Gate MPS | 55.7 | 59.0 | +3.4 |
| Pass-all count | 14 | 35 | 21 |
| Score 4+/5 count | 119 | 35 | +-84 |
| MAX_WS | 334 | 223 | -111 |
Alt 6 — L1 Raw Signals 🧪 ExperimentalScore 15
▼
Pure L1 gate — raw ratios only, control-lab directions, universe-percentile thresholds · 5 rules changed · pass-all: 0
Composite Gate Score — 15.0/100Selectivity 30% · Control Retention 30% · MPS 20% · Turnover 10% · Coverage 5% · Direction 5%
Selectivity
0
30% weight
Ctrl Retention (recall)
0
0/165 (0%)
Avg MPS
50
20% weight
Turnover
0
77% TRIM/SELL
Coverage
0
19% 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
1
≥4/5 rules · in control
Avg Raw Return
+8.71%
return_pct, unweighted mean
Win Rate
0.0%
% beating SPY (excess>0)
Changed From Current Gate
✕ RSI-Net EBITDA (C-grade, dist=66) → ✓ RSI (B-grade, dist=42)
✕ FCF Efficiency (C-grade, dist=70) → ✓ P/C (C-grade, dist=52)
✕ ROIC-EBITDA QC (B-grade, dist=65) → ✓ P/FCF (C-grade, dist=57)
✕ Avg EPS Growth (B-grade, dist=68) → ✓ EV/EBITDA (B-grade, dist=57)
✕ FCF Quality (D-grade, dist=65) → ✓ P/S (D-grade, dist=42)
Gate Rules
| Rule | Grade | Threshold | Coverage | Dist | SIL Advisor |
|---|---|---|---|---|---|
| RSI L1·EXP | B 62 | 42.530 lower | 96.8% | 42 | CANDIDATE ★★★☆☆ |
| P/C L1·EXP | C 60 | 3.230 lower | 0.0% | 52 | CANDIDATE ★★★☆☆ |
| P/FCF L1·EXP | C 54 | 28.940 higher | 0.0% | 57 | CANDIDATE20 ★★★☆☆ |
| EV/EBITDA L1·EXP | B 64 | 20.220 higher | 0.0% | 57 | CANDIDATE ★★★☆☆ |
| P/S L1·EXP | D 34 | 0.930 lower | 0.0% | 42 | CANDIDATE20 ★★★☆☆ |
| Avg MPS: 54.5 | MAX 250 | ||||
TIGHT0 pass all rules — gate is working. Even 0 is normal. Gated Rank differentiates within this set.
Tickers Scored
5,546
of 5,780 in SM CSV
Pass All Rules
0
0.00% of scored
Score 4+/5
15
0.3% of scored
Max Score
250
total dist points
Score Distribution
5/50 (0.0%)
4/515 (0.3%)
3/5339 (6.1%)
2/51,043 (18.8%)
1/51,989 (35.9%)
0/52,394 (43.2%)
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.
● 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.
Upside
- RSI ctrl_d=0.42 (n=493) — strongest single signal in control lab across all 43 metrics
- P/C ctrl return: lower=5.06 vs higher=2.60 — strong separation (n=394)
- P/FCF ctrl_d=0.21 (n=222) — price-to-cash-flow separation confirmed
- 5 fully independent signal families — zero formula overlap possible (raw ratios)
- No direction locks or AT_RISK flags — all from control lab with n≥200
Restrictiveness: Unknown — universe-percentile thresholds untested at gate scale
Liberal risk: Unknown — validate pass-all count before considering deployment
Downside / Risk
- EXPERIMENTAL — thresholds are universe percentiles, not cohort-validated breakpoints
- MPS grades withheld — Holdings cohort (N≈23) too small; full universe scoring pending
- RSI is momentum — may be partly tautological (high RSI = already performing)
- EV/EBITDA ctrl_d=-0.02 (weak) — control lab signal thin at n=212
- P/S ctrl_d=-0.04 (weak) — included for coverage diversity, not signal strength
- No L2 compound quality check — gate may pass cheap junk without quality filter
Signal Independence Grade
A
Overlap
Pure raw ratios — zero formula overlap possible. 5 distinct market dimensions: Momentum, Price/Cash, Price/FCF, Enterprise Value, Price/Sales.
| Rule | Signal Family | What it measures |
|---|---|---|
| RSI | Momentum | Price momentum — 14-day relative strength |
| P/C | Price/Cash | Market price vs cash on hand — cheapness signal |
| P/FCF | Price/FCF | Price vs free cash flow — value signal |
| EV/EBITDA | Enterprise Value | Enterprise value vs earnings before interest/tax/etc |
| P/S | Price/Sales | Price vs revenue — catches cheap growers |
✓ No HIGH overlaps detected between rules in this gate.
Portfolio Turnover Impact
77%
of held positions would be TRIM/SELL under this gateHIGH TURNOVER
HOLD19 positions
ALAB, ALGM, AMSC, AVGO, CLS, COCO, CRS, HWM +11 more
TRIM44 positions
AGX, AMAT, AMD, ANET, APH, ARGX, ASML, BE +36 more
SELL20 positions
AMZN, APP, BLBD, DE, EME, ENVA, FIX, IDCC +12 more
Top Buy Candidates Under This Gate (4+ rules · not held · ranked by Gated Score)
| Ticker | Rank | Score | Gated Score | RSI | P/C | P/FCF | EV/EBITDA | P/S |
|---|---|---|---|---|---|---|---|---|
| PPLI | #1/5780 | 4/5 | 208 | ✓ | ✓ | ✓ | ✓ | ✗ |
| IAC | #2/5780 | 4/5 | 208 | ✓ | ✓ | ✓ | ✓ | ✗ |
| ASYS | #3/5780 | 4/5 | 208 | ✓ | ✓ | ✓ | ✓ | ✗ |
| AOUT | #4/5780 | 4/5 | 198 | ✓ | ✗ | ✓ | ✓ | ✓ |
| AAL | #5/5780 | 4/5 | 193 | ✓ | ✓ | ✓ | ✗ | ✓ |
| JBLU | #6/5780 | 4/5 | 193 | ✓ | ✓ | — | ✓ | ✓ |
| SWAG | #7/5780 | 4/5 | 193 | ✓ | ✓ | — | ✓ | ✓ |
| ARKR | #8/5780 | 4/5 | 193 | ✓ | ✓ | — | ✓ | ✓ |
| ONIT | #9/5780 | 4/5 | 193 | ✓ | ✓ | — | ✓ | ✓ |
| BALY | #10/5780 | 4/5 | 193 | ✓ | ✓ | — | ✓ | ✓ |
Vs. Current Gate
| Metric | Current | This Alt | Δ |
|---|---|---|---|
| Avg Gate MPS | 55.7 | 54.5 | -1.1 |
| Pass-all count | 14 | 0 | +-14 |
| Score 4+/5 count | 119 | 15 | +-104 |
| MAX_WS | 334 | 250 | -84 |
⚡ 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 (71).csv) · Registry: metric_registry.csv · Generated: 2026-08-23 22:02
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.
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.