AI & Humanoid Screen

Theme health

Descriptive only; no verdict reads it. A theme leads for a few years and then hands over (the COVID winners kept dipping through late 2021 H2 and did not recover; a one-off analysis, not a committed result). "Breaking" = the theme's equal-weight basket is under its own 200-day while at least 40% of its names sit in the dip band at once; that threshold is a display choice, not a tested rule.

Theme	Names	Basket vs 200d	Basket 20d	Names above 200d	In dip band	State
AI compute	9	+40.9%	+23.9%	89%	0/9	leading
AI memory	4	+41.4%	+8.1%	100%	1/4	leading
Chip equipment	8	+24.8%	+24.5%	100%	0/8	leading
AI networking	3	+28.4%	+23.9%	100%	0/3	leading
AI power	5	+3.9%	+2.0%	60%	0/5	leading
AI platforms	6	+11.3%	+2.1%	83%	0/6	leading
Humanoid supply chain	16 (15 in basket)	+7.0%	+8.0%	67%	0/16	leading
Magnets & materials	4	-17.3%	-13.7%	25%	2/4	breaking

1. Is it on sale?%B < 0.20

%B says where price sits inside its normal trading channel. Below 0.20 means it has pulled back to the bottom of that channel — on sale. Above 1.00 is extended: too stretched to buy, and it returned 2.65 pts below simply holding.

2. Above or below the 200-day?a trade-off, not a gate

Two studies disagree, so this is not a filter the verdict column applies. 46 large caps, 15y, fwd 60d: dips above the 200-day hit 71% vs 68% below — better odds, but below-200d averaged slightly more (+7.16% vs +6.96%). The AI complex, 2023+: dips below the 200-day were the best bucket of all, +7.49 pts vs the null. The Meta trade in the box below was 11.8% below its 200-day. Above = steadier; below = bigger and lumpier. Pick per your tolerance.

3. Does it survive bad timing? 2y pos ≥ 80% AND 2y p10 > -10%

Both halves are gates, and 2y pos is often the binding one. p10 is the 10th-percentile outcome across past 2-year holds — your unlucky-but-realistic case; a −50% p10 means one in ten 2-year holds halved. These are the exact thresholds the verdict column applies, not a rule of thumb.

Semis — SOXX / SOXL / SOXS

The 3x pair moves with SOXX, so read SOXX's %B and size with SOXL/SOXS's ATR. SOXS is inverse: its %B means the opposite.

Ticker	Close	1d	%B	vs 20d	vs 200d	range	ATR	$vol/d	2y pos	2y p10	60d dips	size	msgs	Verdict
SOXX semis ETF semis_etf	588.90	+2.18%	0.90	+8.3%	+29.5%	83%	2.8%	4.0B	95% 4w	+7.4%	73% of 30 med +6% · CVaR -18%	$1,235 18%	—	neutral
SOXL semis ETF semis_etfleveraged	163.71	+6.52%	0.92	+24.0%	+39.4%	49%	7.5%	7.9B	76% 4w	-52.2%	63% of 30 med +9% · CVaR -57%	—	—	leveraged · not rated
SOXS semis ETF semis_etfleveragedinverse	29.71	-6.45%	0.15	-24.5%	-85.4%	0%	12.6%	2.6B	0% 4w	-98.7%	17% of 36 med -21% · CVaR -65%	—	—	leveraged · not rated

What is moving SOXX

The ten holdings behind SOXX, their fund weight, and how much of the day each one contributed (fund weight × its move, so together they explain about 61% of the fund).

Weight above its own 20-day100%

Weight that rose today77%

Top-10 contribution today+0.94%

Largest moverAVGO +0.25% · 18% of gross movement

Tiles are the nightly snapshot, as of 2026-10-02. Refresh live re-prices the rows; the tiles and the chart only update when all ten come back for the same session.

SOXX 20-day realized vol 38% (annualized) · 5-day drawdown +0.0% · median holding vs its 20-day +8.9% — the median keeps one or two large holdings from masking the rest.

Weighted daily return of the top ten (renormalised to 100%), last 20 sessions · most recent on the right

Last 5 sessions — return: -1.4%, +1.5%, +0.4%, +1.3%, +1.5% · weight rising: 37%, 63%, 66%, 80%, 77%

Ticker	Fund wt	1d	Contrib	5d	20d	vs 20d
NVDA	9.43%	+1.34%	+0.126%	+3.9%	+2.5%	above 20d
MU	8.91%	-2.05%	-0.183%	-0.7%	+12.2%	above 20d
AMD	8.23%	+2.95%	+0.243%	+0.5%	+39.0%	above 20d
AVGO	7.48%	+3.35%	+0.250%	+0.7%	-0.4%	above 20d
INTC	5.09%	-0.56%	-0.028%	-3.0%	+30.2%	above 20d
MRVL	4.66%	+1.57%	+0.073%	+4.0%	+30.4%	above 20d
TSM	4.65%	+2.96%	+0.138%	+4.9%	+13.7%	above 20d
AMAT	4.59%	+2.03%	+0.093%	+11.3%	+23.9%	above 20d
LRCX	4.27%	+2.17%	+0.093%	+10.2%	+18.9%	above 20d
KLAC	4.12%	+3.27%	+0.135%	+10.1%	+19.6%	above 20d

How to use this for SOXL vs SOXS. SOXX %B 0.90 sits in the middle, where the measured edge is zero either way.

Breadth is context, not a trigger. Reproduce every number here with scripts/soxx_breadth_study.py (8 years of SOXX, entry at the next open). Broad strength has no edge: top-10 weight above its 20-day > 80% was +0.04 pts vs the null at 20 days (n=727; +0.00 at 5d, −0.03 at 1d). Weakness in the holdings (breadth < 20%, or their composite %B < 0.20) pointed the same way as SOXX's own dip signal but smaller (about +0.7 to +0.9 pts vs +1.3) and rests on a few hundred overlapping observations, so treat it as noise-level: it adds nothing you cannot read off SOXX's own %B. Use this table to see why SOXX moved, broad or one name, and take the direction call from SOXX's %B. SOXL and SOXS are daily-reset products and are not rated on this page.

Mega caps

META, GOOGL, MSFT, AAPL, AMZN, NFLX — tracked every day whether or not they signal.

Ticker	Close	1d	%B	vs 20d	vs 200d	range	ATR	$vol/d	2y pos	2y p10	60d dips	size	msgs	Verdict
META platform ndx100ai_platformmegacap	728.08	+0.30%	0.67	+4.7%	+16.0%	80%	3.5%	10.5B	79% 4w	-28.0%	57% of 30 med +3% · CVaR -25%	$1,002 14%	—	neutral
GOOGL platform ndx100ai_platformmegacap	343.50	+1.56%	0.54	+0.3%	+1.5%	65%	2.6%	8.3B	90% 4w	+0.0%	71% of 31 med +5% · CVaR -9%	$1,335 19%	—	neutral
MSFT platform ndx100ai_platformmegacap	517.53	+0.92%	0.98	+3.2%	+19.9%	89%	2.2%	11.1B	96% 4w	+10.0%	70% of 27 med +7% · CVaR -13%	$1,400 20% cap	—	neutral
AAPL megacap ndx100megacap	333.69	+1.02%	0.56	+0.5%	+15.5%	92%	2.1%	12.9B	99% 4w	+16.3%	70% of 27 med +6% · CVaR -17%	$1,400 20% cap	—	neutral
AMZN megacap ndx100megacap	251.52	+1.33%	0.49	-0.0%	+4.2%	62%	2.2%	8.5B	79% 4w	-25.3%	73% of 30 med +6% · CVaR -22%	$1,400 20% cap	—	neutral
NFLX megacap ndx100megacap	67.06	-1.16%	0.07	-8.8%	-20.2%	0%	2.9%	2.5B	77% 4w	-39.1%	74% of 31 med +7% · CVaR -37%	$1,187 17%	7	DIP · FAILS HOLD

Buy zone

%B below 0.2, liquid, and passes the 1–3 year hold gate (≥80% of rolling 2-year windows positive with a 10th percentile above -10%).

Ticker	Close	1d	%B	vs 20d	vs 200d	range	ATR	$vol/d	2y pos	2y p10	60d dips	size	msgs	Verdict
CTAS ndx100	193.02	-1.32%	-0.01	-2.6%	+3.0%	57%	2.0%	389M	98% 4w	+22.0%	67% of 30 med +9% · CVaR -15%	$1,400 20% cap	0	BUY ZONE
ADP ndx100	257.68	-2.38%	0.08	-3.5%	+9.7%	72%	2.3%	574M	93% 4w	+3.9%	67% of 30 med +6% · CVaR -17%	$1,400 20% cap	0	BUY ZONE
VRSK ndx100	163.88	-2.67%	0.09	-5.7%	-13.3%	9%	3.3%	241M	83% 4w	-9.8%	58% of 31 med +2% · CVaR -15%	$1,062 15%	0	BUY ZONE
WMT ndx100	104.26	+0.00%	0.10	-2.6%	-11.6%	13%	2.1%	2.4B	98% 4w	+7.7%	68% of 31 med +7% · CVaR -13%	$1,400 20% cap	1	BUY ZONE
VRTX ndx100	504.73	-0.40%	0.12	-2.7%	+6.6%	66%	2.4%	559M	92% 4w	+1.7%	60% of 30 med +3% · CVaR -12%	$1,400 20% cap	0	BUY ZONE
AXON ndx100	413.35	-2.10%	0.14	-9.3%	-16.8%	16%	5.5%	421M	98% 4w	+21.0%	59% of 32 med +20% · CVaR -28%	$642 9%	—	BUY ZONE
PAYX ndx100	98.94	-1.88%	0.15	-10.2%	-3.2%	35%	3.1%	321M	88% 4w	-2.6%	66% of 32 med +5% · CVaR -17%	$1,135 16%	—	BUY ZONE
PCAR ndx100	109.68	-0.24%	0.18	-5.7%	-8.8%	40%	2.4%	348M	98% 4w	+8.1%	61% of 31 med +6% · CVaR -17%	$1,400 20% cap	—	BUY ZONE

Catalyst spikes today

A move of 5%+ on 2×+ the 20-day average volume. This is a reaction, not a setup — something happened, and the rule does not know what or which direction it resolves.

Ticker	Close	1d	%B	vs 20d	vs 200d	range	ATR	$vol/d	2y pos	2y p10	60d dips	size	msgs	Verdict
WDC memory ndx100ai_memory	415.29	-10.22%	0.08	-7.6%	+3.9%	48%	7.0%	3.2B	53% 4w	-43.5%	48% of 29 med -2% · CVaR -28%	$502 7%	16	DIP · FAILS HOLD SPIKE -10.2% · 3.6x
STX memory ndx100ai_memory	848.99	-10.21%	0.39	-2.6%	+30.7%	72%	6.6%	3.7B	80% 4w	-12.9%	68% of 31 med +12% · CVaR -24%	$533 8%	7	neutral SPIKE -10.2% · 3.6x
ALGM humanoid humanoid_disclosed	39.53	+8.66%	1.14	+11.1%	-1.8%	36%	4.7%	87M	—	—	56% of 18 med +2% · CVaR -33%	$753 11%	0	dip · unmeasured SPIKE +8.7% · 2.4x

Near the band / neutral

Dips that fail the hold gate, plus names with no measured edge either way.

Ticker	Close	1d	%B	vs 20d	vs 200d	range	ATR	$vol/d	2y pos	2y p10	60d dips	size	msgs	Verdict
ALNY ndx100	219.72	-4.96%	-0.18	-11.2%	-27.5%	5%	4.8%	370M	80% 4w	-8.5%	53% of 32 med +4% · CVaR -23%	$732 10%	0	DIP · FAILS HOLD
KHC ndx100	22.19	-1.20%	-0.08	-7.6%	-4.6%	25%	2.7%	354M	37% 4w	-58.1%	40% of 35 med -1% · CVaR -17%	$1,283 18%	0	DIP · FAILS HOLD
PDD ndx100	75.38	-1.46%	-0.06	-3.9%	-20.2%	3%	2.4%	507M	63% 4w	-43.0%	54% of 24 med +5% · CVaR -35%	$1,400 20% cap	0	DIP · FAILS HOLD
REGN ndx100	735.20	+0.05%	0.02	-6.1%	+0.1%	61%	2.9%	498M	63% 4w	-31.3%	47% of 30 med -0% · CVaR -25%	$1,189 17%	1	DIP · FAILS HOLD
NFLX megacap ndx100megacap	67.06	-1.16%	0.07	-8.8%	-20.2%	0%	2.9%	2.5B	77% 4w	-39.1%	74% of 31 med +7% · CVaR -37%	$1,187 17%	7	DIP · FAILS HOLD
WDC memory ndx100ai_memory	415.29	-10.22%	0.08	-7.6%	+3.9%	48%	7.0%	3.2B	53% 4w	-43.5%	48% of 29 med -2% · CVaR -28%	$502 7%	16	DIP · FAILS HOLD SPIKE -10.2% · 3.6x
MDLZ ndx100	58.19	+0.74%	0.09	-3.7%	-0.6%	56%	2.0%	464M	79% 4w	-7.8%	59% of 32 med +3% · CVaR -11%	$1,400 20% cap	0	DIP · FAILS HOLD
KDP ndx100	30.37	-1.04%	0.12	-2.7%	+4.7%	67%	2.7%	337M	70% 4w	-9.3%	55% of 29 med +1% · CVaR -10%	$1,282 18%	—	DIP · FAILS HOLD
TTD ndx100	11.95	-1.24%	0.13	-11.1%	-47.1%	0%	4.8%	268M	70% 4w	-47.5%	57% of 30 med +11% · CVaR -40%	$732 10%	—	DIP · FAILS HOLD
PEPearnings in 3 sessions ndx100	125.89	+0.23%	0.14	-4.6%	-12.9%	1%	1.8%	1.0B	78% 4w	-11.2%	58% of 31 med +2% · CVaR -8%	$1,400 20% cap	—	DIP · FAILS HOLD
MELI ndx100	1,696.56	+0.68%	0.14	-6.4%	-7.7%	18%	3.3%	810M	78% 4w	-23.9%	57% of 30 med +10% · CVaR -30%	$1,074 15%	—	DIP · FAILS HOLD
ALB materials humanoid_materials	104.59	-0.42%	0.17	-8.1%	-32.3%	14%	4.3%	265M	49% 4w	-62.1%	56% of 32 med +2% · CVaR -27%	$806 12%	—	DIP · FAILS HOLD
GILD ndx100	144.74	-1.87%	0.19	-2.5%	+7.0%	82%	2.4%	779M	77% 4w	-8.6%	72% of 32 med +3% · CVaR -13%	$1,400 20% cap	—	DIP · FAILS HOLD
CDW ndx100	133.29	-1.87%	0.20	-6.7%	+2.1%	60%	4.4%	224M	79% 4w	-31.1%	69% of 32 med +7% · CVaR -17%	$787 11%	—	neutral
CSGP ndx100	27.38	-1.23%	0.21	-5.8%	-31.7%	1%	4.1%	183M	62% 4w	-22.9%	58% of 31 med +6% · CVaR -24%	$863 12%	—	neutral
CPRT ndx100	27.22	-0.26%	0.21	-7.7%	-18.7%	0%	3.1%	279M	86% 4w	-16.8%	62% of 32 med +9% · CVaR -17%	$1,120 16%	—	neutral
CMCSA ndx100	21.57	-0.60%	0.22	-7.6%	-18.0%	0%	3.0%	655M	57% 4w	-27.0%	47% of 32 med -0% · CVaR -19%	$1,175 17%	—	neutral
BKNG ndx100	159.02	-0.79%	0.22	-5.6%	-12.6%	9%	3.8%	1.1B	84% 4w	-4.9%	75% of 32 med +4% · CVaR -19%	$927 13%	—	neutral
TTWO ndx100	202.73	-0.44%	0.23	-3.0%	-9.7%	18%	3.2%	495M	76% 4w	-24.9%	50% of 30 med +3% · CVaR -15%	$1,086 16%	—	neutral
ROP ndx100	354.32	-2.03%	0.23	-4.8%	-3.5%	20%	2.8%	279M	85% 4w	-15.9%	64% of 33 med +3% · CVaR -13%	$1,259 18%	—	neutral
WDAY ndx100	186.14	-0.33%	0.24	-2.0%	+18.4%	55%	4.1%	572M	67% 4w	-28.7%	70% of 33 med +8% · CVaR -34%	$850 12%	—	neutral
FANG ndx100	184.71	-0.43%	0.25	-4.6%	+0.9%	65%	2.8%	381M	68% 4w	-48.2%	50% of 30 med +3% · CVaR -34%	$1,240 18%	—	neutral
ADBE ndx100	237.69	-1.49%	0.27	-3.8%	-8.5%	27%	3.9%	1.2B	63% 4w	-43.5%	45% of 29 med -2% · CVaR -23%	$908 13%	—	neutral
TMUS ndx100	163.64	+1.18%	0.27	-4.2%	-13.6%	3%	2.7%	761M	94% 4w	+8.5%	70% of 33 med +7% · CVaR -14%	$1,297 19%	—	neutral
INTU ndx100	281.08	-0.60%	0.28	-6.6%	-28.2%	6%	4.5%	1.1B	84% 4w	-11.3%	67% of 30 med +9% · CVaR -32%	$782 11%	—	neutral

Extended

%B above 1.00 — the stall zone, −2.65 pts vs the null at 60 days. Not a short signal; a not-today signal.

Ticker	Close	1d	%B	vs 20d	vs 200d	range	ATR	$vol/d	2y pos	2y p10	60d dips	size	msgs	Verdict
LIN ndx100	479.48	+2.14%	1.01	+2.6%	-0.8%	59%	1.7%	922M	100% 4w	+17.7%	74% of 31 med +6% · CVaR -8%	$1,400 20% cap	—	extended
TSM compute ai_computesoxx_top10	472.78	+2.96%	1.01	+7.3%	+22.7%	98%	2.2%	4.5B	83% 4w	-15.9%	74% of 31 med +10% · CVaR -18%	$1,400 20% cap	—	extended
AMAT equipment ndx100ai_equipmentsoxx_top10	540.04	+2.03%	1.01	+15.2%	+26.5%	65%	3.6%	3.2B	92% 4w	+1.6%	70% of 30 med +17% · CVaR -17%	$968 14%	—	extended
CSCO ndx100	112.20	+3.56%	1.01	+3.5%	+15.7%	73%	2.4%	2.0B	82% 4w	-3.2%	66% of 29 med +5% · CVaR -14%	$1,400 20% cap	—	extended
MCHP ndx100	81.32	+3.59%	1.02	+8.7%	+4.0%	62%	3.5%	651M	76% 4w	-16.4%	56% of 32 med +7% · CVaR -22%	$999 14%	—	extended
KLAC equipment ndx100ai_equipmentsoxx_top10	206.89	+3.27%	1.03	+12.2%	+16.6%	54%	3.7%	1.8B	100% 4w	+31.3%	80% of 30 med +8% · CVaR -13%	$948 14%	—	extended
ENTG equipment ai_equipment	166.47	+5.04%	1.05	+15.0%	+26.1%	85%	4.2%	294M	73% 4w	-20.8%	64% of 33 med +9% · CVaR -20%	$842 12%	—	extended
ADI ndx100	417.15	+3.10%	1.05	+9.8%	+16.6%	88%	2.7%	1.2B	98% 4w	+15.2%	61% of 33 med +4% · CVaR -14%	$1,294 18%	—	extended
COHR equipment ai_equipment	337.04	+5.59%	1.08	+13.0%	+16.6%	72%	6.4%	1.6B	68% 4w	-43.4%	52% of 29 med +4% · CVaR -26%	$549 8%	—	extended
CIEN network ai_network	391.34	+3.22%	1.10	+11.8%	+0.0%	50%	5.6%	757M	76% 4w	-15.6%	63% of 30 med +8% · CVaR -20%	$622 9%	—	extended
TER equipment ndx100ai_equipment	449.04	+8.00%	1.10	+17.9%	+34.1%	90%	4.6%	913M	75% 4w	-19.1%	61% of 28 med +9% · CVaR -30%	$768 11%	—	extended
PWR power ai_power	676.56	+2.11%	1.11	+6.1%	+11.7%	71%	3.2%	582M	93% 4w	+4.6%	73% of 30 med +7% · CVaR -12%	$1,100 16%	—	extended
TXN ndx100	293.80	+4.44%	1.12	+8.9%	+18.9%	80%	2.8%	1.5B	88% 4w	-1.7%	66% of 32 med +4% · CVaR -14%	$1,263 18%	—	extended
LITE network ndx100ai_network	1,085.42	+3.79%	1.12	+15.3%	+45.6%	100%	6.1%	3.7B	66% 4w	-46.0%	61% of 33 med +2% · CVaR -24%	$574 8%	—	extended
SNPS ndx100	489.90	-0.13%	1.13	+19.6%	+10.1%	73%	3.9%	666M	88% 4w	-8.6%	74% of 31 med +7% · CVaR -22%	$900 13%	—	extended

Does the dip rule hold up as a quarterly rotation?

Buy the dip names at each quarter-end, hold to the next, versus the same number of names drawn at random from the same list (2000 draws), after 0.20% costs. Thresholds were written before each run. Neither variant cleared them, so nothing here changes the verdicts above. The universe is today's AI leaders, which flatters dip entries; the mean is carried by one quarter (2026-03-31) in v1.

Test	signal qtrs	mean net excess	qtrs positive	ex best qtr	p vs random	result
v1 · dip (%B < 0.20)	23	+4.2 pts	52%	+1.0 pts	0.071	not promoted (failed: P1, P4)
v2 · dip + above 200-day	18	+3.3 pts	39%	-4.8 pts	0.259	not promoted (failed: P1, P3, P4, P5, P6)

The 1–3 year durability gate cannot be tested point-in-time on 10 years of data (needs 2016 prior sessions); it is judged forward only. Method and thresholds: docs/experiments/2026-09-24-preregistration-qr-s1-v{1,2}.md.

Is %B < 0.20 / 60 days a lucky setting?

Daily entries at the next open on the 34 AI stocks over 10 years, edge vs every session for the same names. The rule was fixed before this ran: the grid can only demote the default, never pick a different cell. Result: not demoted — it sits on a plateau. Deeper dips test a little better and every cell is positive, but the default edge is +1.31 pts over 10 years, well below the +3.47 pts measured on 2023+ alone.

edge vs null, pts	20d	40d	60d	90d
%B < 0.10	+1.24	+1.52	+1.72	+1.34
%B < 0.15	+1.13	+1.35	+1.52	+1.09
%B < 0.20	+0.98	+1.17	+1.31	+0.63
%B < 0.25	+0.85	+1.05	+1.28	+0.57
%B < 0.30	+0.77	+1.00	+1.31	+0.59

By year (default cell): 2016 +0.5% · 2017 +2.2% · 2018 +2.1% · 2019 +4.1% · 2020 +8.1% · 2021 +3.2% · 2022 +3.8% · 2023 +4.4% · 2024 +3.5% · 2025 -3.3% · 2026 +4.2%
By market: QQQ above 200 +0.72% · QQQ below 200 +2.16%
Same rule on indices since 1999 (no hand-picked names): QQQ +0.58% · SPY +0.85% · XLK +0.39% — positive on at least 2 of 3. Episodes are counted per name, and the names dip together, so the independent count is far lower than the raw one. Source: scripts/quarterly_rotation/robustness.py.

%B < 0.20 dip rule	2026-08-21 @ 549.47	+35.4%	18 days before the launch, and META was 11.8% below its 200-day
move + volume spike	2026-09-09 @ 653.17	+13.9%	the day after the launch
follow the analyst	2026-09-21 @ 741.25	+0.4%	the move was over