Prediction Markets — MacroTerminal Research

The model book

The MacroTerminal Model Book — every fill, fee and slippage bp published Grade D · descriptiveas of 2026-10-18T12:00:22Z

ReadHistoryData

equity

$10,715

start $10,000

return

7.15%

open

resolved

win rate appears as they land

Total paper equity (cash plus positions marked to the live Polymarket book) at each daily mark, 2026-09-06 to 2026-10-18, n=35 marks. PAPER: no order is ever sent; seeded positions carry gains inherited from the price our signal logged. · available_at 2026-10-18

market	side	entry	now	unrlzd
Will Solana dip to $50 by December 31, 2026?	NO	0.62	0.94	+105
Will Solana reach $180 by December 31, 2026?	NO	0.90	0.91	+2
Will Solana reach $160 by December 31, 2026?	NO	0.89	0.86	-7
Will Solana dip to $40 by December 31, 2026?	NO	0.72	0.97	+69
Will S&P 500 (SPX) hit $6,200 (LOW) in December?	NO	0.72	0.91	+52
Will S&P 500 (SPX) hit $5,800 (LOW) in December?	NO	0.79	0.96	+44
Will S&P 500 (SPX) hit $5,200 (LOW) in December?	NO	0.90	0.97	+16
Will Solana dip to $20 by December 31, 2026?	NO	0.90	0.99	+20
Will Ethereum reach $3,000 by December 31, 2026?	NO	0.85	0.64	-51
Will Solana dip to $60 by December 31, 2026?	NO	0.43	0.92	+229
Will Bitcoin dip to $50,000 by December 31, 2026?	NO	0.69	0.93	+68
Will Bitcoin reach $95,000 by December 31, 2026?	NO	0.84	0.66	-44
Will Bitcoin reach $90,000 by December 31, 2026?	NO	0.79	0.45	-87
Will S&P 500 (SPX) close at $6,500-$7,000 in December?	NO	0.86	0.85	-1
Will S&P 500 (SPX) hit $8,200 (HIGH) in December?	NO	0.74	0.70	-11
Will S&P 500 (SPX) close at <$6,000 in December?	NO	0.89	0.97	+17
Will Ethereum dip to $1,000 by December 31, 2026?	NO	0.87	0.96	+22
Will Ethereum dip to $1,250 by December 31, 2026?	NO	0.76	0.94	+49
Will Bitcoin dip to $55,000 by December 31, 2026?	NO	0.44	0.90	+207
Will Ethereum dip to $1,500 by December 31, 2026?	NO	0.49	0.92	+174
Will Bitcoin dip to $60,000 by December 31, 2026?	NO	0.21	0.84	+600
Will Ethereum reach $3,500 by December 31, 2026?	NO	0.90	0.86	-8
Will Solana dip to $70 by December 31, 2026?	NO	0.19	0.83	+674
Will Bitcoin reach $86,000 October 12-18?	YES	0.37	0.01	-196
Will Bitcoin reach $88,000 October 12-18?	YES	0.14	0.00	-199

PAPER portfolio — no real orders are ever sent. Entries walk the REAL Polymarket order book (slippage + levels + live fee rate recorded per trade). Seeded positions are marked seed_logged: entered at the price our signal logged when it fired, with the live price at seed time recorded alongside — early mark-to-market gains are inherited from that history and labeled, never claimed as execution. Signals: our published GBM/30-day vol index fair-value divergences, fee-adjusted, $200 flat stakes, at most 60 open positions (raised from 25 on 2026-09-26; signals skipped at the old cap were not entered afterwards). The $10,000 starting cash funds about 50 stakes of $200, so cash binds before the cap; a signal that arrives when cash is below one stake is recorded as skipped for insufficient cash.

The accountability leaf on this desk is the paper NAV, and it is young. What it has is drawn; what it cannot support is said.

Total paper equity at every stored daily mark. This is the whole record of this leaf: the book was seeded on 2026-09-06. · our own build archive, 35 builds from 2026-09-06

No five-year line: the paper book has been marked daily since 2026-09-06, which is 35 marks, not five years. The record above is the whole of it and nothing is extrapolated behind it.

No analog table: no linked price for a paper book's net asset value: the book holds Polymarket binaries that resolve to zero or one, and its NAV is the sum of positions in unrelated questions; there is no traded series whose forward move scores it. Point 2 of the History contract asks for the forward move of the price this leaf is linked to, and this leaf is not linked to one; no other series' episodes are shown in its place.

No factory what-changed table: panel 'modelbook' has no rows in at all yet.

Price analogs are the part of this contract that is missing here, and the reason is printed above rather than left blank.

open positions · 29 rows

slug	question	outcome	shares	avg entry	live price	current value	unrealized pnl	price note
will-solana-dip-to-50-by-december-31-2026-from-june-8	Will Solana dip to $50 by December 31, 2026?	no	322.58	0.62	0.94	304.84	104.84	not reported
will-solana-reach-180-by-december-31-2026	Will Solana reach $180 by December 31, 2026?	no	222.22	0.90	0.91	202.33	2.33	not reported
will-solana-reach-160-by-december-31-2026	Will Solana reach $160 by December 31, 2026?	no	224.72	0.89	0.86	193.26	-6.74	not reported
will-solana-dip-to-40-by-december-31-2026-343-482	Will Solana dip to $40 by December 31, 2026?	no	277.78	0.72	0.97	269.03	69.03	not reported
spx-hit-6200-low-dec-2026	Will S&P 500 (SPX) hit $6,200 (LOW) in December?	no	278.94	0.72	0.91	252.44	52.44	not reported
spx-hit-5800-low-dec-2026	Will S&P 500 (SPX) hit $5,800 (LOW) in December?	no	253.16	0.79	0.96	244.30	44.30	not reported
spx-hit-5200-low-dec-2026	Will S&P 500 (SPX) hit $5,200 (LOW) in December?	no	222.22	0.90	0.97	216.44	16.44	not reported
will-solana-dip-to-20-by-december-31-2026-143-365	Will Solana dip to $20 by December 31, 2026?	no	222.22	0.90	0.99	220.22	20.22	not reported
will-ethereum-reach-3000-by-december-31-2026-from-june-8	Will Ethereum reach $3,000 by December 31, 2026?	no	235.29	0.85	0.64	149.41	-50.59	not reported
will-solana-dip-to-60-by-december-31-2026-249-524	Will Solana dip to $60 by December 31, 2026?	no	466.20	0.43	0.92	428.90	228.90	not reported
will-bitcoin-dip-to-50000-by-december-31-2026-454-325-222-878-949-487-451-853-52	Will Bitcoin dip to $50,000 by December 31, 2026?	no	289.86	0.69	0.93	268.12	68.12	not reported
will-bitcoin-reach-95000-by-december-31-2026-from-june-8	Will Bitcoin reach $95,000 by December 31, 2026?	no	238.10	0.84	0.66	155.95	-44.05	not reported
will-bitcoin-reach-90000-by-december-31-2026-113-862-581-343	Will Bitcoin reach $90,000 by December 31, 2026?	no	253.16	0.79	0.45	112.66	-87.34	not reported
spx-close-6500-7000-dec-2026	Will S&P 500 (SPX) close at $6,500-$7,000 in December?	no	232.56	0.86	0.85	198.84	-1.16	not reported
spx-hit-8200-high-dec-2026	Will S&P 500 (SPX) hit $8,200 (HIGH) in December?	no	270.27	0.74	0.70	189.19	-10.81	not reported
spx-close-below-6000-dec-2026	Will S&P 500 (SPX) close at <$6,000 in December?	no	224.72	0.89	0.97	217.08	17.08	not reported
will-ethereum-dip-to-1000-by-december-31-2026-273-175	Will Ethereum dip to $1,000 by December 31, 2026?	no	229.89	0.87	0.96	221.72	21.72	not reported
will-ethereum-dip-to-1250-by-december-31-2026-from-june-8	Will Ethereum dip to $1,250 by December 31, 2026?	no	263.16	0.76	0.94	248.68	48.68	not reported
will-bitcoin-dip-to-55000-by-december-31-2026-527-627-868-745-188-361-314-673-61	Will Bitcoin dip to $55,000 by December 31, 2026?	no	454.55	0.44	0.90	406.82	206.82	not reported
will-ethereum-dip-to-1500-by-december-31-2026-865-787	Will Ethereum dip to $1,500 by December 31, 2026?	no	408.16	0.49	0.92	374.08	174.08	not reported
will-bitcoin-dip-to-60k-by-december-31-2026-from-july-21	Will Bitcoin dip to $60,000 by December 31, 2026?	no	952.38	0.21	0.84	800.00	600.00	not reported
will-ethereum-reach-3500-by-december-31-2026	Will Ethereum reach $3,500 by December 31, 2026?	no	222.22	0.90	0.86	192.22	-7.78	not reported
will-solana-dip-to-70-by-december-31-2026-from-july-6	Will Solana dip to $70 by December 31, 2026?	no	1,052.63	0.19	0.83	873.68	673.68	not reported
will-bitcoin-reach-86k-october-12-18-2026	Will Bitcoin reach $86,000 October 12-18?	yes	541.25	0.37	0.01	4.06	-195.94	not reported
will-bitcoin-reach-88k-october-12-18-2026	Will Bitcoin reach $88,000 October 12-18?	yes	1,428.57	0.14	0.0005	0.71	-199.29	not reported
will-bitcoin-dip-to-78k-october-12-18-2026	Will Bitcoin dip to $78,000 October 12-18?	yes	759.44	0.26	0.01	8.73	-191.27	not reported
will-bitcoin-reach-87pt5k-in-october-2026	Will Bitcoin reach $87,500 in October?	yes	739.49	0.27	0.34	247.73	47.73	not reported
will-ethereum-reach-2500-october-12-18-2026	Will Ethereum reach $2,500 October 12-18?	yes	277.78	0.72	0.06	17.22	-182.78	not reported
will-ethereum-reach-2600-october-12-18-2026	Will Ethereum reach $2,600 October 12-18?	yes	2,333.28	0.09	0.01	14.00	-186.00	not reported

resolved positions · 11 rows

slug	question	outcome	realized pnl	won	resolved at
will-ethereum-reach-2750-by-december-31-2026-from-june-8	Will Ethereum reach $2,750 by December 31, 2026?	no	-200.00	no	2026-09-27 12:00:24
will-bitcoin-reach-85000-by-december-31-2026-from-june-8	Will Bitcoin reach $85,000 by December 31, 2026?	no	-200.00	no	2026-09-27 12:00:25
will-bitcoin-reach-86k-september-28-october-4-2026	Will Bitcoin reach $86,000 September 28-October 4?	yes	300.00	yes	2026-10-02 12:00:31
will-bitcoin-dip-to-82k-september-28-october-4-2026	Will Bitcoin dip to $82,000 September 28-October 4?	yes	-200.00	no	2026-10-05 12:04:08
will-bitcoin-reach-88k-september-28-october-4-2026	Will Bitcoin reach $88,000 September 28-October 4?	yes	-200.00	no	2026-10-05 12:04:09
will-bitcoin-reach-90k-september-28-october-4-2026	Will Bitcoin reach $90,000 September 28-October 4?	yes	-200.00	no	2026-10-05 12:04:09
will-bitcoin-reach-88k-october-5-11-2026	Will Bitcoin reach $88,000 October 5-11?	yes	-200.00	no	2026-10-12 12:00:59
will-bitcoin-dip-to-80k-october-5-11-2026	Will Bitcoin dip to $80,000 October 5-11?	yes	-200.00	no	2026-10-12 12:00:59
will-bitcoin-reach-84k-october-5-11-2026	Will Bitcoin reach $84,000 October 5-11?	no	-200.00	no	2026-10-12 12:01:00
bitcoin-above-84k-on-october-14-2026	Will the price of Bitcoin be above $84,000 on October 14?	no	74.07	yes	2026-10-15 12:01:03
will-bitcoin-dip-to-80k-october-12-18-2026	Will Bitcoin dip to $80,000 October 12-18?	yes	709.09	yes	2026-10-16 12:01:01

equity curve · 35 rows

date	cash	positions value	total	n positions
2026-09-06	5,000.00	6,482.51	11,482.51	25
2026-09-07	5,000.00	6,472.47	11,472.47	25
2026-09-08	5,000.00	6,506.14	11,506.14	25
2026-09-10	5,000.00	6,551.82	11,551.82	25
2026-09-11	5,000.00	6,478.80	11,478.80	25
2026-09-12	5,000.00	6,469.76	11,469.76	25
2026-09-13	5,000.00	6,468.34	11,468.34	25
2026-09-14	5,000.00	6,462.47	11,462.47	25
2026-09-15	5,000.00	6,493.90	11,493.90	25
2026-09-16	5,000.00	6,517.05	11,517.05	25
2026-09-17	5,000.00	6,571.03	11,571.03	25
2026-09-18	5,000.00	6,569.57	11,569.57	25
2026-09-19	5,000.00	6,583.58	11,583.58	25
2026-09-20	5,000.00	6,577.58	11,577.58	25
2026-09-27	5,000.00	6,536.03	11,536.03	23
2026-09-28	5,000.00	6,543.40	11,543.40	23
2026-09-29	5,000.00	6,510.32	11,510.32	23
2026-09-30	5,000.00	6,533.16	11,533.16	23
2026-10-01	4,600.00	6,962.96	11,562.96	25
2026-10-02	4,700.00	6,971.17	11,671.17	26
2026-10-03	4,700.00	6,651.62	11,351.62	26
2026-10-04	4,700.00	6,632.51	11,332.51	26
2026-10-05	4,700.00	6,592.98	11,292.98	23
2026-10-06	4,700.00	6,620.80	11,320.80	23
2026-10-07	4,300.00	7,021.34	11,321.34	25
2026-10-08	4,300.00	7,174.88	11,474.88	25
2026-10-10	4,100.00	6,976.70	11,076.70	26
2026-10-11	4,100.00	6,942.22	11,042.22	26
2026-10-12	4,100.00	6,687.02	10,787.02	23
2026-10-13	4,100.00	6,676.34	10,776.34	23
2026-10-14	3,300.00	7,469.46	10,769.46	27
2026-10-15	3,174.07	7,747.89	10,921.96	28
2026-10-16	3,683.16	7,446.26	11,129.42	29
2026-10-17	3,683.16	7,050.93	10,734.09	29
2026-10-18	3,683.16	7,031.53	10,714.69	29

analytics

key	value
start_total	11,482.51
latest_total	10,714.69
return_pct	7.15
max_drawdown_pct	8.20
n_snapshots	35
method	mark-to-market from daily equity snapshots (live midpoints); engine realized-cas

account

key	value
starting_balance	10,000.00
cash	3,683.16
positions_value	7,032.69
total_value	10,715.85
unrealized_plus_realized_pnl	715.85
unpriced_positions	0
unpriced_cost	0
unpriced_note	not reported

The Fed path

Fed path — the nearest meeting, and the path Grade D · descriptiveas of 2026-10-18 21:52 UTC

ReadHistoryData

cut50+

futures not published this build

cut25

futures not published this build

hike25

14%

futures not published this build

hike50+

futures not published this build

Polymarket, meeting 2026-10 · available_at 2026-10-18 21:52 UTC

The stepped chart is held for Full Access: this page carries 4 of 15 rows.

meeting	distribution
2026-10	cut25 0% · cut50+ 0% · hike25 14% · hike50+ 0%

October FOMC: Polymarket puts 86% on hold; the futures side is unavailable, so no divergence is computed

The leaf here is a probability for a dated FOMC outcome, not a price. Polymarket has been recorded on this panel since 2026-09-05 and the futures side is unavailable, so there is no five-year record of it and no price it settles into.

No five-year line: this pane's leaf is a probability for a dated meeting, not a series with five years behind it. What has been recorded of it is in the table below.

No analog table: no linked price for an FOMC outcome probability: the leaf is the crowd's probability for an FOMC outcome; series_lab holds price panels only and carries no policy-rate panel, and the futures side of this pane is unavailable. Point 2 of the History contract asks for the forward move of the price this leaf is linked to, and this leaf is not linked to one; no other series' episodes are shown in its place.

What changed since last week

leaf	then	now	change	compared with
polymarket cross › 0 › poly p	0.00	0.00	-0.001	2026-10-11
polymarket cross › 1 › poly p	0.00	0.00	unchanged	2026-10-11
polymarket cross › 10 › poly p	0.02	0.02	-0.007	2026-10-11
polymarket cross › 11 › poly p	0.01	0.01	-0.0025	2026-10-11
polymarket cross › 12 › poly p	0.32	0.34	+0.03	2026-10-11
polymarket cross › 13 › poly p	0.02	0.01	-0.006	2026-10-11
polymarket cross › 14 › poly p	0.66	0.62	-0.03	2026-10-11
polymarket cross › 2 › poly p	0.15	0.14	-0.02	2026-10-11
polymarket cross › 3 › poly p	0.00	0.00	unchanged	2026-10-11
polymarket cross › 4 › poly p	0.83	0.86	+0.03	2026-10-11

8 of 10 headline leaves moved. A repeated value can mean the upstream had not published, not that nothing happened.

Price analogs are the part of this contract that is missing here, and the reason is printed above rather than left blank.

polymarket cross · 4 rows

market title	meeting	bucket	poly p	futures p	divergence pts
Will the Fed decrease interest rates by 25 bps after the October 2026 meeting?	2026-10	cut25	0.00	not reported	not reported
Will the Fed decrease interest rates by 50+ bps after the October 2026 meeting?	2026-10	cut50+	0.00	not reported	not reported
Will the Fed increase interest rates by 25 bps after the October 2026 meeting?	2026-10	hike25	0.14	not reported	not reported
Will the Fed increase interest rates by 50+ bps after the October 2026 meeting?	2026-10	hike50+	0.00	not reported	not reported

11 rows and 4 fields withheld at this tier: absent from the page, not hidden in it.

Crowd against model

Crypto binaries — model fair value vs crowd Grade D · descriptiveas of 2026-10-18 21:52 UTC

ReadHistoryData

One point per BTC/ETH price binary, n=4 of 15; the rest are held for Full Access. Above the dashed line the crowd pays more than the model; the fee-adjusted gaps are in the table below. · available_at 2026-10-18 21:52 UTC

market	crowd	GBM (30-day vol index-σ)	gap	fee-adj
Will Ethereum reach $2,400 October 12-18?	64%	30%	-33	-31
Will the price of Bitcoin be above $80,000 on October 19?	78%	79%	+8	+7
Will the price of Bitcoin be above $82,000 on October 19?	26%	27%	-7	-5
Will Bitcoin dip to $77,500 in October?	47%	53%	+6	+4

· touch claims priced by reflection (2·N(d2)); fees per Polymarket Fee-V2 — a gap that doesn't survive fees isn't a gap.

These binaries settle on Bitcoin, so Bitcoin is the linked price. The divergence leaf itself has been recorded since 2026-09-05; the five-year line and the episodes below are the underlying's.

Five years of Bitcoin - the series the fair value of these binaries is computed on - with the high-volatility weeks shaded by the same two-state Markov filter the Regime tab draws. One state, one shading, every tab: the bands are that shared filter's, not a second state fitted for this pane. The filter puts 34 stretches of these five years in the high-volatility state, and those are the shaded ones.

The last 8 times this looked like today — and what Bitcoin did next

episode	z	level	Bitcoin +5d	Bitcoin +21d
2026-09-11	-0.25	77,276.50	+4.62%	+7.31%
2026-08-21	-0.29	78,126.63	-0.37%	+3.92%
2026-01-14	-0.39	96,852.91	-7.14%	-31.85%
2025-11-06	-0.07	101,447.93	-2.51%	-11.93%
2025-10-16	0.48	106,463.30	+4.30%	-10.93%
2025-03-29	0.42	82,379.98	-4.87%	+15.37%
2025-03-08	0.37	80,699.17	+2.31%	-1.93%
2024-10-01	0.49	60,631.37	-0.09%	+15.78%

z in [-0.5, 0.5) · n=49 episodes · 21-session hit rate 55% · median +5d 1.18, +21d 1.18 · grade C

Bucketed on Bitcoin's own z, not on the model-vs-crowd divergence. Episodes when this series last sat in the same trailing-365-observation z bucket, with the forward 5- and 21-session move of Bitcoin. 49 episodes at least 21 days apart; the table shows the most recent 8. A conditional distribution with its count, not a signal.

What changed since last week

leaf	then	now	change	compared with
markets › 0 › K	84,000.00	2,400.00	-8.16e+04	2026-10-11
markets › 1 › K	87,500.00	80,000.00	-7500	2026-10-11
markets › 2 › K	2,900.00	82,000.00	+7.91e+04	2026-10-11
markets › 3 › K	2,300.00	77,500.00	+7.52e+04	2026-10-11
markets › 4 › K	77,500.00	78,000.00	+500	2026-10-11
markets › 5 › K	2,600.00	84,000.00	+8.14e+04	2026-10-11
markets › 6 › K	2,800.00	1,900.00	-900	2026-10-11
markets › 7 › K	95,000.00	2,000.00	-9.3e+04	2026-10-11
markets › 8 › K	90,000.00	87,500.00	-2500	2026-10-11
markets › 9 › K	70,000.00	70,000.00	unchanged	2026-10-11

9 of 10 headline leaves moved. A repeated value can mean the upstream had not published, not that nothing happened.

spot

key	value
BTC	81,136.33
ETH	2,364.92

markets · 4 rows

question	symbol	K	T days	model	poly p	fair p	fair p iv index	divergence pts	fee adj divergence pts
Will Ethereum reach $2,400 October 12-18?	ETH	2,400.00	0.26	one-touch 2*N(d2)	0.64	0.31	0.30	-33.00	-31.40
Will the price of Bitcoin be above $80,000 on October 19?	BTC	80,000.00	0.76	terminal N(d2)	0.79	0.87	0.79	8.50	7.30
Will the price of Bitcoin be above $82,000 on October 19?	BTC	82,000.00	0.76	terminal N(d2)	0.27	0.20	0.27	-6.60	-5.20
Will Bitcoin dip to $77,500 in October?	BTC	77,500.00	13.26	one-touch 2*N(d2)	0.47	0.38	0.53	6.20	4.50

11 rows and 6 fields withheld at this tier: absent from the page, not hidden in it.

Are prediction markets calibrated? (154M resolved Kalshi trades, 2021-2026) Grade C · counted distributionas of 2026-09-06

ReadEV by sideError by yearHistoryData

trade-time Brier

0.1685

0.25 is a coin flip

calibration error

0.0072

ECE

trades scored

121,671,888

both sides of every trade

Kalshi resolved trades · grade C · available_at 2026-09-06

log loss 0.5016 (trade-time, both sides) — the proper score that punishes confident misses harder than Brier.

Trade-time Brier 0.1685 · ECE 0.0072 · 121,671,888 trades analyzed. The dashed line is perfect calibration (price == win rate); points below it are prices the crowd habitually paid too much for. · 154M resolved Kalshi trades, 2021-2026 (grade C, n per point)

price	actual win rate	trades
2.7	2.4%	15,527,762
8.0	7.4%	11,196,789
13.0	12.2%	10,382,666
18.0	17.6%	10,281,017
23.0	23.9%	10,585,305
28.1	27.9%	11,055,486
33.0	35.3%	11,745,784
38.0	37.9%	12,827,019
43.1	42.8%	13,501,720
48.0	48.0%	16,287,905
53.0	52.9%	15,854,010
58.0	58.5%	13,242,620
63.0	62.9%	12,601,610
68.0	65.7%	11,630,980
73.0	73.1%	10,914,749
78.0	77.2%	10,537,856
83.0	83.7%	10,193,288
88.1	88.9%	10,559,501
93.1	93.6%	11,384,540
97.8	98.0%	13,033,081

trade-time Brier 0.1685 · ECE 0.0072 · 121,671,888 trades analyzed

· Across 121,671,888 resolved trades (both sides scored), Kalshi prices are remarkably well calibrated at trade time: ECE 0.7%, trade-time Brier 0.1685 vs the 0.25 coin-flip baseline.

· Longshot bias is real and asymmetric: takers buying 1-20c contracts average -1.3c EV per contract on the YES side and -1.1c on the NO side — the lottery-ticket buyer funds the market.

· The mirror image: takers of 81-99c favorites average -0.7c (YES) and -0.2c (NO) per contract — being boring pays roughly its keep.

· Longshots still pull volume: 1-20c contracts took 30.5% of taker contract volume in the latest quarter.

The AI Forecasts board publishes our resolvable bets with base rates and 3-pass reasoning; every resolution is Brier-scored in public against the base-rate benchmark.

The weekly Depth report asks who is actually behind each price — concentration, whales-vs-price divergences, flow. The Calibration report scores the market itself against resolutions with Venn-ABERS bands.

Expected value in cents per contract of taking YES or NO at each price bucket, over every resolved trade.

ev by side · 21 rows

price bucket	ev yes	n yes	ev no	n no
-4-0c	not reported	0	18.18	44
1-5c	-0.90	6,244,579	-0.82	2,742,169
6-10c	-1.47	5,132,151	-1.22	1,409,075
11-15c	-1.68	4,757,257	-1.43	1,215,293
16-20c	-1.26	4,732,423	-1.51	1,167,190
21-25c	0.41	4,801,333	-0.73	1,158,627
26-30c	-1.54	5,042,834	-0.89	1,209,866
31-35c	1.62	4,965,403	0.26	1,283,011
36-40c	-2.02	5,313,385	-0.82	1,427,393
41-45c	-2.85	5,079,751	-0.05	1,549,041
46-50c	-2.09	5,987,029	0.12	2,195,379
51-55c	-2.17	5,559,706	0.15	2,382,683
56-60c	-1.87	4,665,405	-0.15	1,996,360
61-65c	-2.19	4,190,738	-0.17	1,812,968
66-70c	-5.00	3,525,456	-0.74	1,776,726
71-75c	-1.74	2,972,744	-0.31	1,776,642
76-80c	-3.01	2,754,783	-0.64	1,853,384
81-85c	-0.54	2,360,581	-0.16	1,940,645
86-90c	-0.68	2,323,104	0.01	2,163,746
91-95c	-0.79	2,206,723	-0.30	2,542,570
96-99c	-0.94	2,086,536	-0.23	3,367,155

Mean absolute deviation between price and realised frequency, by year and by month — whether the crowd is getting better.

calibration mad by year · 6 rows

year	mad cents
2021	0.59
2022	1.92
2023	2.00
2024	4.47
2025	2.18
2026	1.05

calibration mad by month · 51 rows

month	mad cents	n
2021-08	1.45	2,282
2021-10	0.52	3,034
2021-11	0.39	2,012
2021-12	0.06	2,462
2022-01	0.90	5,906
2022-04	2.93	4,280
2022-05	1.99	127,214
2022-06	1.96	224,796
2022-07	2.45	229,908
2022-08	1.12	297,818
2022-09	2.02	249,188
2022-10	1.80	208,634
2022-11	2.46	168,694
2022-12	2.06	124,122
2023-01	2.73	53,088
2023-02	2.88	100,578
2023-03	1.23	351,430
2023-04	1.71	271,242
2023-05	2.52	463,642
2023-06	1.35	421,682
2023-07	2.79	443,192
2023-08	2.22	244,042
2023-09	1.59	207,136
2023-10	1.52	316,192
2023-11	2.01	191,146
2023-12	2.43	218,992
2024-01	3.01	385,032
2024-02	1.63	372,168
2024-03	1.88	353,356
2024-04	1.63	337,132
2024-05	1.31	241,464
2024-06	2.11	232,672
2024-07	1.98	249,528
2024-08	1.61	220,996
2024-09	3.67	217,104
2024-10	12.41	870,024
2024-11	5.73	5,123,450
2024-12	0.92	2,016,926
2025-01	0.94	2,427,836
2025-02	2.35	3,364,986
2025-03	4.12	5,529,812
2025-04	3.44	3,930,924
2025-05	2.45	4,726,954
2025-06	2.94	5,838,492
2025-07	1.85	5,694,832
2025-08	1.59	5,908,696
2025-09	2.58	13,549,064
2025-10	2.70	19,697,290
2025-11	1.12	15,550,418
2025-12	1.95	54,292,896
2026-01	1.05	86,603,532

The leaf is how well the Kalshi crowd is calibrated, measured over resolved trades. Its own multi-year record exists and is drawn below.

The pane's own leaf over 13 months, 2021-08 to 2022-11: mean absolute distance in cents between the price the crowd paid and the rate those trades actually won. There are NO regime bands on this chart and that is deliberate - there is no regime state for a calibration curve, and shading it with a market state fitted to something else would assert a relationship this pane has not measured.

Point 1 carries no regime bands here, for two independent reasons and neither is an omission. FIRST, a calibration curve has no regime state: shading it with a market state fitted to something else would assert a relationship this pane has not measured. SECOND, it could not be shaded even if it had one - this leaf is MONTHLY, so five years of it is 60 points at most and this build holds 13, against charts.MIN_POINTS['dateline'] of 60. Below that floor the line is drawn by stepline, which takes no shading at all. The line above is the pane's own leaf over 13 months, 2021-08 to 2022-11, and it is real.

No analog table: no linked price for a calibration curve: a calibration error in cents is not linked to any traded price - it is a property of the crowd across thousands of unrelated markets. Point 2 of the History contract asks for the forward move of the price this leaf is linked to, and this leaf is not linked to one; no other series' episodes are shown in its place.

What changed since last week

leaf	then	now	change	compared with
brier trade time	0.17	0.17	unchanged	2026-10-11
ece	0.01	0.01	unchanged	2026-10-11
log loss	0.50	0.50	unchanged	2026-10-11
longshot volume share latest	0.31	0.31	unchanged	2026-10-11
n resolved markets	3,722,314.00	3,722,314.00	unchanged	2026-10-11
n trades analyzed	121,671,888.00	121,671,888.00	unchanged	2026-10-11

0 of 6 headline leaves moved. A repeated value can mean the upstream had not published, not that nothing happened.

Price analogs are the part of this contract that is missing here, and the reason is printed above rather than left blank.

calibration · 5 rows

price	win rate	n
2.70	0.02	15,527,762
8.00	0.07	11,196,789
13.00	0.12	10,382,666
18.00	0.18	10,281,017
23.00	0.24	10,585,305

ev by side · 6 rows

price bucket	ev yes	n yes	ev no	n no
-4-0c	not reported	0	18.18	44
1-5c	-0.90	6,244,579	-0.82	2,742,169
6-10c	-1.47	5,132,151	-1.22	1,409,075
11-15c	-1.68	4,757,257	-1.43	1,215,293
16-20c	-1.26	4,732,423	-1.51	1,167,190
21-25c	0.41	4,801,333	-0.73	1,158,627

longshot volume share by quarter · 5 rows

quarter	share	contracts
2021-Q2	0.00	5
2021-Q3	0.27	3,700,853
2021-Q4	0.24	6,047,822
2022-Q1	0.29	7,442,620
2022-Q2	0.37	18,979,098

calibration mad by year · 2 rows

year	mad cents
2021	0.59
2022	1.92

calibration mad by month · 13 rows

month	mad cents	n
2021-08	1.45	2,282
2021-10	0.52	3,034
2021-11	0.39	2,012
2021-12	0.06	2,462
2022-01	0.90	5,906
2022-04	2.93	4,280
2022-05	1.99	127,214
2022-06	1.96	224,796
2022-07	2.45	229,908
2022-08	1.12	297,818
2022-09	2.02	249,188
2022-10	1.80	208,634
2022-11	2.46	168,694

scalars

field	value
dataset	/
n trades analyzed	121,671,888
n resolved markets	3,722,314
brier trade time	0.17
ece	0.01
log loss	0.50

90 rows and 5 fields withheld at this tier: absent from the page, not hidden in it.

The board through time

Crowd convergence — GEOPOLITICS Grade D · descriptiveas of 2026-10-18 21:47 UTC

ReadMONETARYHistoryData

yes	market	vol	ends
12%	Strait of Hormuz traffic returns to normal by December 31?	$15.1M	2027-01-01
12%	US military action against Cuba by...? — US strike on Cuba by December 31?	$7.6M	2027-01-01
12%	Iran leadership change by...? — Iran leadership change by December 31?	$27.6M	2027-07-01
87%	Iran leader end of 2026? — Will Mojtaba Khamenei be head of state in Iran end of 2026?	$40.3M	2026-12-31

yes	market	vol	ends
86%	Fed Decision in October? — Will there be no change in Fed interest rates after the October 2026 meeting?	$45.6M	2026-10-29

How much money has stood behind this board at every stored build, and why its level carries no linked price.

Total volume across every contract the board tracked on that build, in millions of dollars. A jump is as often a contract entering the board as money arriving, which is why the count of tracked contracts sits in the Data tab beside it. · our own build archive, 44 builds from 2026-09-04

No five-year line: the board archive begins 2026-09-04 and holds 44 builds. Nothing older than that exists for this leaf, here or upstream.

No analog table: no linked price for the crowd's price across a board of unrelated questions: each contract resolves to zero or one on its own question and the modules on this board span politics, the Fed, crypto and sport; there is no single traded series whose forward move scores the board's level. Point 2 of the History contract asks for the forward move of the price this leaf is linked to, and this leaf is not linked to one; no other series' episodes are shown in its place.

What changed since last week

leaf	then	now	change	compared with
rows › 0 › score	0.87	0.88	+0.009	2026-10-11
rows › 1 › score	0.86	0.87	+0.002	2026-10-11
rows › 10 › score	0.76	0.76	+0.009	2026-10-11
rows › 11 › score	0.75	0.76	+0.007	2026-10-11
rows › 2 › score	0.86	0.86	+0.002	2026-10-11
rows › 3 › score	0.85	0.86	+0.017	2026-10-11
rows › 4 › score	0.84	0.86	+0.016	2026-10-11
rows › 5 › score	0.83	0.84	+0.01	2026-10-11
rows › 6 › score	0.83	0.84	+0.009	2026-10-11
rows › 7 › score	0.83	0.83	+0.005	2026-10-11

10 of 10 headline leaves moved. A repeated value can mean the upstream had not published, not that nothing happened.

Price analogs are the part of this contract that is missing here, and the reason is printed above rather than left blank.

rows · 5 rows

title	yes	module	volume	end	tag	url	score
Strait of Hormuz traffic returns to normal by December 31?	12	geopolitics	15,061,783	2027-01-01	geopolitics	https://polymarket.com/event/strait-of-hormuz-traffic-returns-to-normal-by-decem	0.88
US military action against Cuba by...? — US strike on Cuba by December 31?	12	geopolitics	7,590,930	2027-01-01	geopolitics	https://polymarket.com/event/us-strike-on-cuba-by	0.87
Fed Decision in October? — Will there be no change in Fed interest rates after t	86	monetary	45,551,910	2026-10-29	fed	https://polymarket.com/event/fed-decision-in-october-20260617190323537	0.86
Iran leadership change by...? — Iran leadership change by December 31?	12	geopolitics	27,553,953	2027-07-01	geopolitics	https://polymarket.com/event/iran-leadership-change-by	0.86
Iran leader end of 2026? — Will Mojtaba Khamenei be head of state in Iran end of	87	geopolitics	40,252,593	2026-12-31	geopolitics	https://polymarket.com/event/iran-leader-end-of-2026	0.86

15 rows and 2 fields withheld at this tier: absent from the page, not hidden in it.

Implied odds through time Grade D · descriptiveas of 2026-10-18 21:47 UTC

ReadHistoryData

Implied odds of the most persistently tracked contracts, at every stored build. Each track is keyed by the market URL, so a contract that moves position on the board keeps its own line. · our own build archive, 44 builds from 2026-09-04

63 contracts have at least two stored observations. The archive begins 2026-09-04, which is the whole record and the reason these tracks are short.

The geopolitics lane's longest track is not drawn against VIX yet. The tape is cached and aligned to the board dates, but this track carries 44 stored observations and the house floor for a dated line is 60 (charts.MIN_POINTS). Below that the line is not drawn at all rather than drawn and disbelieved, so this chart appears once the archive, which began 2026-09-04, reaches 60 builds.

The economy lane's longest track is not drawn against VIX yet. The tape is cached and aligned to the board dates, but this track carries 35 stored observations and the house floor for a dated line is 60 (charts.MIN_POINTS). Below that the line is not drawn at all rather than drawn and disbelieved, so this chart appears once the archive, which began 2026-09-04, reaches 60 builds.

The inflation lane's longest track is not drawn against WTI yet. The tape is cached and aligned to the board dates, but this track carries 30 stored observations and the house floor for a dated line is 60 (charts.MIN_POINTS). Below that the line is not drawn at all rather than drawn and disbelieved, so this chart appears once the archive, which began 2026-09-05, reaches 60 builds.

The fed lane is on this board and is NOT drawn against a tape series, because the series it would need is the two-year yield, which is the series these contracts settle into and the one series_lab carries no panel for. No other instrument is shown in its place.

The interest-rates lane is on this board and is NOT drawn against a tape series, because the series it would need is the two-year yield, which series_lab carries no panel for. No other instrument is shown in its place.

The tariffs lane is on this board and is NOT drawn against a tape series, because the series it would need is any single instrument - a tariff contract's exposure is spread across the dollar, the affected exporter's index and the goods themselves. No other instrument is shown in its place.

The odds track with the longest record on the board, and why point 2 of the History contract cannot be answered for it.

The most persistently tracked contract on the board — Will the U.S. invade Iran before 2027? — at every stored build. · our own build archive, 44 builds from 2026-09-04

No five-year line: the board archive begins 2026-09-04 and holds 44 builds. This leaf is that archive and nothing older exists to draw.

No analog table: no linked price for an implied probability on the board: the board's contracts resolve to zero or one on their own questions, and the same track mixes lanes (a Fed meeting, a strait, an election) that settle into different instruments; the reprice study beside this pane is where a linked price IS available, because it conditions on the move rather than on the level. Point 2 of the History contract asks for the forward move of the price this leaf is linked to, and this leaf is not linked to one; no other series' episodes are shown in its place.

What changed since last week

leaf	then	now	change	compared with
rows › 0 › score	0.87	0.88	+0.009	2026-10-11
rows › 1 › score	0.86	0.87	+0.002	2026-10-11
rows › 10 › score	0.76	0.76	+0.009	2026-10-11
rows › 11 › score	0.75	0.76	+0.007	2026-10-11
rows › 2 › score	0.86	0.86	+0.002	2026-10-11
rows › 3 › score	0.85	0.86	+0.017	2026-10-11
rows › 4 › score	0.84	0.86	+0.016	2026-10-11
rows › 5 › score	0.83	0.84	+0.01	2026-10-11
rows › 6 › score	0.83	0.84	+0.009	2026-10-11
rows › 7 › score	0.83	0.83	+0.005	2026-10-11

10 of 10 headline leaves moved. A repeated value can mean the upstream had not published, not that nothing happened.

Price analogs are the part of this contract that is missing here, and the reason is printed above rather than left blank.

tracks · 20 rows

market	tag	points	first	last
Will the U.S. invade Iran before 2027?	geopolitics	44	14.00	16.00
US military action against Cuba by...? — US strike on Cuba by December 31?	geopolitics	44	14.00	12.00
Iran leader end of 2026? — Will Mojtaba Khamenei be head of state in Iran end of	geopolitics	44	84.00	87.00
Strait of Hormuz traffic returns to normal by December 31?	geopolitics	44	26.00	12.00
Russia x Ukraine ceasefire agreement by...? — Russia x Ukraine ceasefire agreeme	geopolitics	44	22.00	14.00
Will Hamas agree to disarm by...? — Will Hamas agree to disarm by December 31?	geopolitics	42	22.00	11.00
Largest Company end of December 2026? — Will NVIDIA be the largest company in th	economy	35	80.00	78.00
Prime Minister of Israel after the next election? — Will Benjamin Netanyahu be t	geopolitics	30	28.00	30.00
Will ground beef hit __ in 2026? — Will ground beef hit $10 per pound in 2026?	inflation	30	12.00	10.00
What will the Fed rate be at the end of 2026? — Will the upper bound of the targ	fed	30	10.00	11.00
NYSE marketwide circuit breaker before 2027?	economy	29	12.00	10.00
Another Fed rate hike in 2026?	fed	27	84.00	78.00
Which companies will the US take a stake in? — Will the US federal government ta	economy	26	14.00	14.00
NATO x Russia military clash by...? — NATO x Russia military clash by December 3	geopolitics	26	32.00	26.00
China Annual GDP Growth 2026 — Will China’s 2026 annual GDP growth (Y/Y) be betw	economy	22	90.00	90.00
Fed Decision in October? — Will there be no change in Fed interest rates after t	fed	22	34.00	86.00
How many Fed rate hikes in 2026? — Will no Fed rate hikes happen in 2026?	fed	21	22.00	22.00
Bank of Japan Decision in October? — No change in Bank of Japan’s interest rates	economy	21	88.00	12.00
Which countries will Trump make new trade deals with before 2027? — U.S. agrees	tariffs	16	10.00	10.00
Bank of England decision in November? — Bank of England increases interest rates	interest-rates	16	86.00	90.00

scalars

field	value
builds	44
tracked contracts	63

Depth and concentration through time Grade D · descriptiveas of 2026-10-18 21:47 UTC

ReadHistoryData

Total volume across every contract on the tracked board, at each stored build. This is how much money stands behind the board as a whole, not the depth of any one order book. · our own build archive, 44 builds from 2026-09-04

Herfindahl index of volume shares across the board (0-10,000: 1,500 is competitive, 2,500 concentrated) with the largest single contract's share beside it. A board whose HHI rises while volume is flat is the same money crowding into fewer questions.

board volume

$307m

20 contracts tracked

HHI

1,397

2,500 is a concentrated board

largest contract

24%

of tracked volume

This is board-level concentration of volume, not order-book depth. We do not store the book, so nothing here claims to measure how much size a given contract would absorb; the holder-level question — whether a price is a crowd or five wallets — is the weekly Depth report, which scans the book live.

How concentrated the board's volume has been at every stored build.

The Herfindahl index of volume shares across every tracked contract, build by build. 2,500 is the conventional line for a concentrated market; this is VOLUME concentration across the board, not order-book depth in any one contract. · our own build archive, 44 builds from 2026-09-04

No five-year line: the board archive begins 2026-09-04 and holds 44 builds, which is the whole record of this leaf.

No analog table: no linked price for a Herfindahl index of board volume: concentration is a property of how attention is spread across unrelated questions, and no traded instrument settles it; there is no series whose forward move scores an HHI. Point 2 of the History contract asks for the forward move of the price this leaf is linked to, and this leaf is not linked to one; no other series' episodes are shown in its place.

What changed since last week

leaf	then	now	change	compared with
rows › 0 › score	0.87	0.88	+0.009	2026-10-11
rows › 1 › score	0.86	0.87	+0.002	2026-10-11
rows › 10 › score	0.76	0.76	+0.009	2026-10-11
rows › 11 › score	0.75	0.76	+0.007	2026-10-11
rows › 2 › score	0.86	0.86	+0.002	2026-10-11
rows › 3 › score	0.85	0.86	+0.017	2026-10-11
rows › 4 › score	0.84	0.86	+0.016	2026-10-11
rows › 5 › score	0.83	0.84	+0.01	2026-10-11
rows › 6 › score	0.83	0.84	+0.009	2026-10-11
rows › 7 › score	0.83	0.83	+0.005	2026-10-11

10 of 10 headline leaves moved. A repeated value can mean the upstream had not published, not that nothing happened.

Price analogs are the part of this contract that is missing here, and the reason is printed above rather than left blank.

rows · 44 rows

date	n markets	volume usd	hhi	top share	top3 share
2026-09-04	12	140,351,455.00	3,044.40	46.15	81.51
2026-09-05	20	185,763,530.00	2,133.30	34.92	75.16
2026-09-06	20	185,865,295.00	2,133.10	34.90	75.17
2026-09-07	20	187,200,100.00	2,120.40	34.68	75.02
2026-09-08	20	187,028,953.00	2,134.10	34.76	75.28
2026-09-09	20	188,201,455.00	2,121.70	34.57	75.09
2026-09-10	20	190,077,338.00	2,095.60	34.39	74.56
2026-09-11	20	177,673,091.00	2,050.70	36.94	66.40
2026-09-12	20	158,571,180.00	2,502.80	41.53	73.65
2026-09-13	20	161,407,795.00	2,423.30	40.84	72.48
2026-09-14	20	195,960,176.00	2,002.50	33.74	72.96
2026-09-15	20	371,316,171.00	2,932.80	48.73	77.21
2026-09-16	20	188,533,459.00	2,183.40	35.26	76.23
2026-09-17	20	188,894,509.00	2,184.00	35.27	76.22
2026-09-18	20	197,044,179.00	2,033.30	33.99	73.31
2026-09-19	20	197,802,268.00	2,022.90	33.90	73.10
2026-09-20	20	198,623,069.00	2,027.50	33.95	73.18
2026-09-21	20	199,618,178.00	2,019.70	33.91	73.01
2026-09-22	20	202,700,630.00	1,991.50	33.73	72.32
2026-09-23	20	208,784,338.00	1,907.10	32.83	70.39
2026-09-24	20	213,033,986.00	1,850.40	32.26	69.12
2026-09-25	20	199,771,613.00	2,073.00	34.51	73.89
2026-09-26	20	218,226,488.00	1,813.60	31.96	68.08
2026-09-27	20	212,995,212.00	1,905.50	32.76	69.85
2026-09-28	20	216,132,295.00	1,867.00	32.36	69.06
2026-09-29	20	203,237,903.00	2,085.30	34.55	74.14
2026-09-30	20	211,567,613.00	1,951.20	33.23	71.58
2026-10-01	20	231,724,491.00	1,730.50	30.55	65.72
2026-10-02	20	221,506,342.00	1,719.60	32.09	62.08
2026-10-03	20	220,141,357.00	1,753.10	32.43	62.62
2026-10-04	20	221,906,267.00	1,742.20	32.27	62.28
2026-10-05	20	222,614,595.00	1,742.00	32.29	62.23
2026-10-06	20	228,690,218.00	1,684.50	31.59	60.96
2026-10-07	20	230,116,422.00	1,688.30	31.53	61.31
2026-10-08	20	233,808,892.00	1,671.00	31.18	61.44
2026-10-10	20	232,506,991.00	1,710.70	31.47	62.36
2026-10-11	20	233,193,287.00	1,706.20	31.41	62.32
2026-10-12	20	284,042,180.00	1,433.70	25.99	56.25
2026-10-13	20	250,363,648.00	1,557.90	29.55	59.58
2026-10-14	20	297,011,650.00	1,385.70	24.93	54.04
2026-10-15	20	301,307,891.00	1,376.90	24.59	54.03
2026-10-16	20	306,196,436.00	1,370.50	24.30	54.22
2026-10-17	20	308,845,505.00	1,361.70	24.12	54.08
2026-10-18	20	306,975,395.00	1,397.20	24.30	54.93

When a contract reprices Grade D · descriptiveas of 2026-10-18 21:47 UTC

ReadHistoryData

Each point is a tracked contract that moved at least 10 points between two stored builds (x) and what WTI did over the next 5 sessions (y). n = 15 events on 12 distinct dates: events on one date share one forward window, so the independent count is the second number.

Each point is a tracked contract that moved at least 10 points between two stored builds (x) and what VIX did over the next 5 sessions (y). n = 15 events on 12 distinct dates: events on one date share one forward window, so the independent count is the second number.

n = 15 scored events on 12 distinct dates; any mean or sign share is computed over the dates, not the events.

The question this pane asks: when a tracked contract reprices by 10 points between builds, what did crude and the VIX do over the following 5 sessions? Geopolitics is the lane worth watching, and in the stored window it has produced 0 such moves — the count is the finding, and the table below carries every tagged lane so the mechanism is visible rather than asserted.

contract	lane	odds	move	WTI 5d	VIX 5d	on
Fed rate hike in 2026?	fed	78→90	+12	+0.17%	-1.03	2026-09-11
How many Fed rate hikes in 2026? — Will no Fed rate	fed	22→10	-12	+0.17%	-1.03	2026-09-11
Fed decisions (Jul–Oct) — Will the Fed decide differ	fed	74→84	+10	+0.17%	-1.03	2026-09-12
Fed rate hike by...? — Fed Rate Hike by September 20	fed	78→88	+10	-5.32%	-2.23	2026-09-14
US recession by end of 2026?	economy	10→23	+13	-9.91%	-2.99	2026-09-15
Bank of Japan Decision in October? — No change in Ba	economy	87→21	-66	-9.88%	-2.53	2026-09-16
US recession by end of 2026?	economy	23→12	-11	-9.88%	-2.53	2026-09-16
US-Canada diplomatic agreement to lower tariffs by..	tariffs	20→10	-10	-7.10%	+0.23	2026-09-17
What will the Fed rate be at the end of 2026? — Will	fed	16→28	+12	-7.10%	+0.23	2026-09-17
Bank of Japan Decision in October? — No change in Ba	economy	21→82	+61	-15.98%	+0.06	2026-09-18
Bank of Japan Decision in October? — No change in Ba	economy	82→16	-66	-15.98%	+0.06	2026-09-19
Core PCE YoY - August 2026 — Will Core PCE YoY be 3.	inflation	13→24	+11	+4.07%	+1.16	2026-09-23
Interest Rates: October 2026 — Will the ECB anno	interest-rates	86→76	-10	-3.26%	-0.55	2026-09-28
Interest Rates: October 2026 — Will the ECB anno	interest-rates	78→90	+12	-2.22%	-1.26	2026-09-30
Fed Decision in October? — Will there be no change i	fed	30→74	+44	-1.51%	-0.98	2026-10-01
Fed Decision in October? — Will there be no change i	fed	80→68	-12	not yet	not yet	2026-10-14
What will the Fed rate be at the end of 2026? — Will	fed	11→24	+13	not yet	not yet	2026-10-14
Fed Decision in October? — Will there be no change i	fed	72→86	+14	not yet	not yet	2026-10-16
Japan Core-Core CPI YoY in 2026 — Will Japan's core-	inflation	78→89	+11	not yet	not yet	2026-10-17

19 events in 44 stored builds since 2026-09-04. Forward responses are WTI and the VIX over 5 sessions. WTI: the 5-session window has not closed: the series ends 2026-10-14; VIX: the 5-session window has not closed: the series ends 2026-10-15. No aggregate is published: the event-study floor is 15 events and this is 15, so what stands here is a count and a mechanism, not a claim.

A reprice is a claim about the world changing. This is every one of them the archive holds, scored against crude.

Five years of WTI crude - the series the forward response these reprices are scored against is computed on - with the high-volatility weeks shaded by the same two-state Markov filter the Regime tab draws. One state, one shading, every tab: the bands are that shared filter's, not a second state fitted for this pane. The filter puts 7 stretches of these five years in the high-volatility state, and those are the shaded ones.

The last 8 times this looked like today — and what WTI crude did next

episode	z	level	WTI crude +5d	WTI crude +21d
2026-10-01	1.40	74.00	-1.51%	not in the price record
2026-09-30	0.34	90.00	-2.22%	not in the price record
2026-09-28	-0.40	76.00	-3.26%	not in the price record
2026-09-23	0.30	24.00	+4.07%	not in the price record
2026-09-19	-2.25	16.00	-15.98%	not in the price record
2026-09-18	1.96	82.00	-15.98%	not in the price record
2026-09-17	-0.40	10.00	-7.10%	not in the price record
2026-09-17	0.34	28.00	-7.10%	not in the price record

a reprice of at least 10 probability points between two builds · n=15 episodes · 21-session hit rate not computable · median +5d -5.32, +21d -2.51 · grade C

Episodes are reprices of this desk's OWN tracked contracts, not z buckets of a price: the z column is each move against the distribution of every build-on-build move in the archive (mean +1.9, sd 30.1 over 19 moves), and the level column is the odds the contract repriced TO. The forward columns are WTI. THE 21-SESSION COLUMN IS OPEN on 10 of the 15 scored episodes: the board archive begins 2026-09-04 and WTI has not yet printed 21 sessions after them. Those cells say so rather than showing a zero. At FIVE sessions, which has closed, 4 of 15 episodes saw crude higher; against an unconditional base rate of 52.3% of all overlapping 5-session windows over the last five years (n=1,255, 2021-09-28 to 2026-10-14). NO CONDITIONAL RATE IS PUBLISHED FROM IT: 15 episodes is below the pre-registered floor of 20, so the tally stands and no percentage is computed from it.

What changed since last week

leaf	then	now	change	compared with
rows › 0 › score	0.87	0.88	+0.009	2026-10-11
rows › 1 › score	0.86	0.87	+0.002	2026-10-11
rows › 10 › score	0.76	0.76	+0.009	2026-10-11
rows › 11 › score	0.75	0.76	+0.007	2026-10-11
rows › 2 › score	0.86	0.86	+0.002	2026-10-11
rows › 3 › score	0.85	0.86	+0.017	2026-10-11
rows › 4 › score	0.84	0.86	+0.016	2026-10-11
rows › 5 › score	0.83	0.84	+0.01	2026-10-11
rows › 6 › score	0.83	0.84	+0.009	2026-10-11
rows › 7 › score	0.83	0.83	+0.005	2026-10-11

10 of 10 headline leaves moved. A repeated value can mean the upstream had not published, not that nothing happened.

rows · 19 rows

date	prior date	tag	title	from	to	move pts	WTI	WTI why	VIX
2026-09-11	2026-09-10	fed	Fed rate hike in 2026?	78.00	90.00	12.00	0.17	not reported	-1.03
2026-09-11	2026-09-10	fed	How many Fed rate hikes in 2026? — Will no Fed rate hikes happen in 2026?	22.00	10.00	-12.00	0.17	not reported	-1.03
2026-09-12	2026-09-10	fed	Fed decisions (Jul–Oct) — Will the Fed decide differently in the next three deci	74.00	84.00	10.00	0.17	not reported	-1.03
2026-09-14	2026-09-13	fed	Fed rate hike by...? — Fed Rate Hike by September 2026 Meeting?	78.00	88.00	10.00	-5.32	not reported	-2.23
2026-09-15	2026-09-14	economy	US recession by end of 2026?	10.00	23.00	13.00	-9.91	not reported	-2.99
2026-09-16	2026-09-15	economy	Bank of Japan Decision in October? — No change in Bank of Japan’s interest rates	87.00	21.00	-66.00	-9.88	not reported	-2.53
2026-09-16	2026-09-15	economy	US recession by end of 2026?	23.00	12.00	-11.00	-9.88	not reported	-2.53
2026-09-17	2026-09-16	tariffs	US-Canada diplomatic agreement to lower tariffs by...? — US-Canada diplomatic ag	20.00	10.00	-10.00	-7.10	not reported	0.23
2026-09-17	2026-09-16	fed	What will the Fed rate be at the end of 2026? — Will the upper bound of the targ	16.00	28.00	12.00	-7.10	not reported	0.23
2026-09-18	2026-09-17	economy	Bank of Japan Decision in October? — No change in Bank of Japan’s interest rates	21.00	82.00	61.00	-15.98	not reported	0.06
2026-09-19	2026-09-18	economy	Bank of Japan Decision in October? — No change in Bank of Japan’s interest rates	82.00	16.00	-66.00	-15.98	not reported	0.06
2026-09-23	2026-09-22	inflation	Core PCE YoY - August 2026 — Will Core PCE YoY be 3.1% in August?	13.00	24.00	11.00	4.07	not reported	1.16
2026-09-28	2026-09-09	interest-rates	Interest Rates: October 2026 — Will the ECB announce no change at the Octobe	86.00	76.00	-10.00	-3.26	not reported	-0.55
2026-09-30	2026-09-29	interest-rates	Interest Rates: October 2026 — Will the ECB announce no change at the Octobe	78.00	90.00	12.00	-2.22	not reported	-1.26
2026-10-01	2026-09-28	fed	Fed Decision in October? — Will there be no change in Fed interest rates after t	30.00	74.00	44.00	-1.51	not reported	-0.98
2026-10-14	2026-10-13	fed	Fed Decision in October? — Will there be no change in Fed interest rates after t	80.00	68.00	-12.00	not reported	the 5-session window has not closed: the series ends 2026-10-14	not reported
2026-10-14	2026-10-13	fed	What will the Fed rate be at the end of 2026? — Will the upper bound of the targ	11.00	24.00	13.00	not reported	the 5-session window has not closed: the series ends 2026-10-14	not reported
2026-10-16	2026-10-15	fed	Fed Decision in October? — Will there be no change in Fed interest rates after t	72.00	86.00	14.00	not reported	the 5-session window has not closed: the series ends 2026-10-14	not reported
2026-10-17	2026-09-20	inflation	Japan Core-Core CPI YoY in 2026 — Will Japan's core-core CPI increase by between	78.00	89.00	11.00	not reported	the 5-session window has not closed: the series ends 2026-10-14	not reported

aggregate · 2 rows

key	n	n dates	unit	mean	sign consistency	basis
WTI	15	12	%	-5.56	0.75	distinct dates
VIX	15	12	pts	-0.92	0.67	distinct dates

scalars

field	value
threshold pts	10
horizon days	5
n events	19
n geopolitics	0

Deeper cuts

Through time — level, distribution, seasonality and range Grade C · counted distributionas of 2026-10-19 11:47 UTC

ReadHistoryResidual checkData

3 series shown on this desk. Baa credit spread is the most stretched here, at the 2th percentile of its own history.

VIXNasdaq vol (VXN)Baa credit spread

level

16.46

pct · as of 2026-10-15

percentile

of 9,296 obs since 1990

percentile, 5y

of 1,287 obs

vs 13w mean

+1.08

level minus its own quarter

vs 52w mean

-1.43

level minus its own year

year on year

-4.32

same week last year

TrendDistributionSeasonalityRangeRegime

MSTL with periods 5 and 52 on 1920 weekly observations from 1990-01-05. The trend is drawn over the level and the remainder under it; nothing here is extrapolated. The trend explains 67% of the variance the remainder does not (Hyndman's trend strength); the seasonal component explains 16%.

What the trend and the seasonal do not account for, on the same dates. A remainder that trends is a decomposition that has missed something, which is why it is drawn rather than described.

Harvey–Jaeger local linear trend on the quarterly average level, 1990-03-31 to 2026-09-30 (147 quarters), smoothed: each quarter's estimate uses the quarters after it.

No cycle is drawn: the implied period is 1.5 years, pinned at the 1.5–12-year bound, so the data do not locate a cycle inside it (best period 1.5 y, damping 0.59). The trend above is the trend-only model, which the data prefer.

The whole history as a distribution, with today marked. Median 17.56 over 9,296 observations.

The same record read cumulatively: today sits at the 43 percentile of the full history (n=9,296) and the 38 of the last five years (n=1,287). A level extreme against forty years and ordinary against five is a different fact from one that is extreme against both.

The spread of monthly means is no larger than the noise — this series has no seasonal worth trading. Kruskal-Wallis across calendar months; the corner figure is the average number of years behind each bar.

The MSTL seasonal component itself, at periods 5 and 52. Drawn rather than summarised because a seasonal that changes shape year to year is not one a reader can plan against, and the chart shows that where a single average would hide it.

Seasonal diagnostic: The STL seasonal component's own mean at each calendar month, across 37 years, against the year-to-year standard deviation at that same month (ratio 0.62). The year-to-year noise at these calendar months is as large as the mean seasonal effect itself, so the shape should be read as unstable, not as a repeating pattern.

month	market holidays	Crude prints	Gas prints	option expiries	quad-witchings
Jan	19	45	43	10	0
Feb	10	40	41	10	0
Mar	3	45	45	10	10
Apr	7	42	42	10	0
May	10	43	43	10	0
Jun	4	45	45	10	10
Jul	10	44	43	10	0
Aug	0	45	45	10	0
Sep	10	42	43	10	10
Oct	0	44	44	10	0
Nov	10	44	43	10	0
Dec	10	43	44	10	10

Event days per calendar month, 2016–2025. Every column is derived from a published rule, so it was knowable years ahead: the whole table is stamped available_at 1900-01-01, never the build date. Dropped, because they are announced rather than derived and the schedule loaded here does not cover the window: FOMC decisions, CPI prints.

The high-minus-low width of the trailing 88-observation window (the same 63-day horizon as the band above), against the last 1,287 such windows over five years. Today's window sits at the 3 percentile of its own five-year range history; the 10th-to-90th of that history is 7.37 to 26.63 (level). A description of how wide the market has recently traded, not a target.

Where this has historically gone over 63 trading days: 10th to 90th percentile of 9,208 realised moves, applied to today. A base rate for sizing, not a forecast.

downside (10th)

8.99

-7.47

median path

15.86

50th percentile

upside (90th)

24.10

+7.64

Markov-filtered mean

-0.131

per week, state-weighted

The band above is unconditional: it does not know what state we are in. The filtered mean beside it does — it is the two-state Markov model's mean weighted by today's filtered probability (4 of the high-volatility state). The two disagree when the current state is unusual, which is the point of printing both.

state

low volatility

since 2026-06-19

P(high vol) now

filtered, this week

persisted

weeks (126 days)

P(exit in 4w)

11.1%

2 of 18 spells this old

spells on record

172

86 completed in this state

Two-state Markov-switching model with switching variance, fitted on 1300 weekly change in level. The line is the FILTERED probability of the high-volatility state — a statement about weeks that have happened, not a forecast. Exit counts are empirical spell counts, not the model's expected durations.

The same weeks on the level: shaded stretches are the ones the filter puts in the high-volatility state. Mean -0.155 per week at 1.676 standard deviation in the calm state against +0.402 at 5.715 in the volatile one.

Markov-switching AR(1) (MarkovAutoregression(k_regimes=2, order=1, switching_ar=False, switching_variance=True), 779 periods since 2011-11-18): low volatility now, filtered p(high) 0.06; AR(1) -0.119; sd 5.678 high against 1.626 low. The two Markov filters put the same state on 95% of 260 common periods; the MarkovRegression reads low volatility now. The filtered probability is about periods that have happened.

level

22.89

pct · as of 2026-10-15

percentile

of 6,464 obs since 2001

percentile, 5y

of 1,255 obs

vs 13w mean

+0.91

level minus its own quarter

vs 52w mean

-0.94

level minus its own year

year on year

-2.08

same week last year

TrendDistributionSeasonalityRangeRegime

MSTL with periods 5 and 52 on 1342 weekly observations from 2001-02-02. The trend is drawn over the level and the remainder under it; nothing here is extrapolated. The trend explains 81% of the variance the remainder does not (Hyndman's trend strength); the seasonal component explains 16%.

What the trend and the seasonal do not account for, on the same dates. A remainder that trends is a decomposition that has missed something, which is why it is drawn rather than described.

Harvey–Jaeger local linear trend on the quarterly average level, 2001-03-31 to 2026-09-30 (103 quarters), smoothed: each quarter's estimate uses the quarters after it.

No cycle is drawn: the implied period is 1.5 years, pinned at the 1.5–12-year bound, so the data do not locate a cycle inside it; the cycle does not earn its parameters: BIC 653.2 with it against 653.1 for the trend alone (best period 1.5 y, damping 0.56). The trend above is the trend-only model, which the data prefer.

The whole history as a distribution, with today marked. Median 21.23 over 6,464 observations.

The same record read cumulatively: today sits at the 58 percentile of the full history (n=6,464) and the 54 of the last five years (n=1,255). A level extreme against forty years and ordinary against five is a different fact from one that is extreme against both.

Seasonal diagnostic: The STL seasonal component's own mean at each calendar month, across 26 years, against the year-to-year standard deviation at that same month (ratio 0.57). The year-to-year noise at these calendar months is as large as the mean seasonal effect itself, so the shape should be read as unstable, not as a repeating pattern.

month	market holidays	Crude prints	Gas prints	option expiries	quad-witchings
Jan	19	45	43	10	0
Feb	10	40	41	10	0
Mar	3	45	45	10	10
Apr	7	42	42	10	0
May	10	43	43	10	0
Jun	4	45	45	10	10
Jul	10	44	43	10	0
Aug	0	45	45	10	0
Sep	10	42	43	10	10
Oct	0	44	44	10	0
Nov	10	44	43	10	0
Dec	10	43	44	10	10

The high-minus-low width of the trailing 88-observation window (the same 63-day horizon as the band above), against the last 1,255 such windows over five years. Today's window sits at the 46 percentile of its own five-year range history; the 10th-to-90th of that history is 7.15 to 21.51 (level). A description of how wide the market has recently traded, not a target.

Where this has historically gone over 63 trading days: 10th to 90th percentile of 6,376 realised moves, applied to today. A base rate for sizing, not a forecast.

downside (10th)

13.15

-9.74

median path

21.99

50th percentile

upside (90th)

31.43

+8.54

Markov-filtered mean

-0.126

per week, state-weighted

state

low volatility

since 2026-07-24

P(high vol) now

filtered, this week

persisted

weeks (91 days)

P(exit in 4w)

22.7%

5 of 22 spells this old

spells on record

123

61 completed in this state

The same weeks on the level: shaded stretches are the ones the filter puts in the high-volatility state. Mean -0.153 per week at 1.990 standard deviation in the calm state against +0.467 at 5.681 in the volatile one.

Markov-switching AR(1) (MarkovAutoregression(k_regimes=2, order=1, switching_ar=False, switching_variance=True), 779 periods since 2011-11-18): low volatility now, filtered p(high) 0.06; AR(1) -0.134; sd 5.110 high against 1.919 low. The two Markov filters put the same state on 97% of 260 common periods; the MarkovRegression reads low volatility now. The filtered probability is about periods that have happened.

level

1.44

pct · as of 2026-10-15

percentile

of 10,197 obs since 1986

percentile, 5y

of 1,245 obs

vs 13w mean

-0.10

level minus its own quarter

vs 52w mean

-0.21

level minus its own year

year on year

-0.26

same week last year

TrendDistributionSeasonalityRangeRegime

MSTL with periods 5 and 52 on 2129 weekly observations from 1986-01-03. The trend is drawn over the level and the remainder under it; nothing here is extrapolated. The trend explains 91% of the variance the remainder does not (Hyndman's trend strength); the seasonal component explains 16%.

What the trend and the seasonal do not account for, on the same dates. A remainder that trends is a decomposition that has missed something, which is why it is drawn rather than described.

Harvey–Jaeger local linear trend on the quarterly average level, 1986-12-31 to 2026-09-30 (160 quarters), smoothed: each quarter's estimate uses the quarters after it.

No cycle is drawn: the cycle does not earn its parameters: BIC 118.8 with it against 108.2 for the trend alone (best period 3.4 y, damping 0.85). The trend above is the trend-only model, which the data prefer. The trend-only model assigns no variance to the irregular, so its trend coincides with the quarterly level: at this cadence the model finds nothing to separate from the path itself.

The whole history as a distribution, with today marked. Median 2.13 over 10,197 observations.

The same record read cumulatively: today sits at the 2 percentile of the full history (n=10,197) and the 5 of the last five years (n=1,245). A level extreme against forty years and ordinary against five is a different fact from one that is extreme against both.

Seasonal diagnostic: The STL seasonal component's own mean at each calendar month, across 41 years, against the year-to-year standard deviation at that same month (ratio 0.48). The year-to-year noise at these calendar months is as large as the mean seasonal effect itself, so the shape should be read as unstable, not as a repeating pattern.

month	market holidays	Crude prints	Gas prints	option expiries	quad-witchings
Jan	19	45	43	10	0
Feb	10	40	41	10	0
Mar	3	45	45	10	10
Apr	7	42	42	10	0
May	10	43	43	10	0
Jun	4	45	45	10	10
Jul	10	44	43	10	0
Aug	0	45	45	10	0
Sep	10	42	43	10	10
Oct	0	44	44	10	0
Nov	10	44	43	10	0
Dec	10	43	44	10	10

The high-minus-low width of the trailing 88-observation window (the same 63-day horizon as the band above), against the last 1,245 such windows over five years. Today's window sits at the 35 percentile of its own five-year range history; the 10th-to-90th of that history is 0.21 to 0.61 (level). A description of how wide the market has recently traded, not a target.

Where this has historically gone over 63 trading days: 10th to 90th percentile of 10,109 realised moves, applied to today. A base rate for sizing, not a forecast.

downside (10th)

1.02

-0.42

median path

1.40

50th percentile

upside (90th)

1.89

+0.45

Markov-filtered mean

-0.004

per week, state-weighted

The band above is unconditional: it does not know what state we are in. The filtered mean beside it does — it is the two-state Markov model's mean weighted by today's filtered probability (0.8 of the high-volatility state). The two disagree when the current state is unusual, which is the point of printing both.

state

low volatility

since 2025-04-18

P(high vol) now

0.8

filtered, this week

persisted

weeks (553 days)

P(exit in 4w)

0.0%

0 of 4 spells this old

spells on record

41 completed in this state

The same weeks on the level: shaded stretches are the ones the filter puts in the high-volatility state. Mean -0.004 per week at 0.049 standard deviation in the calm state against +0.014 at 0.177 in the volatile one.

Markov-switching AR(1) (MarkovAutoregression(k_regimes=2, order=1, switching_ar=False, switching_variance=True), 779 periods since 2011-11-18): low volatility now, filtered p(high) 0.00; AR(1) +0.135; sd 0.198 high against 0.049 low. The two Markov filters put the same state on 99% of 260 common periods; the MarkovRegression reads low volatility now. The filtered probability is about periods that have happened.

VIXNasdaq vol (VXN)Baa credit spread

VIX · last 16.46 as of 2026-10-15 · 9,296 observations from 1990-01-02

Five years of VIX with the high-volatility weeks shaded, from the same two-state filter the Regime tab draws. One state, one shading, every tab.

The last 8 times this looked like today — and what S&P 500 did next

episode	z	level	S&P 500 +5d	S&P 500 +21d
2026-09-10	-0.13	17.84	+0.61%	+2.90%
2026-07-29	0.30	20.66	+5.57%	+5.67%
2026-07-08	-0.47	16.90	+1.20%	+3.04%
2026-06-11	0.06	19.44	+1.44%	+2.45%
2026-05-20	-0.35	17.44	+1.18%	+0.91%
2026-04-29	-0.04	18.81	+3.21%	+5.99%
2026-04-08	0.42	21.04	+3.54%	+8.17%
2026-02-25	-0.12	17.93	-1.10%	-6.75%

z in [-0.5, 0.5) · n=342 episodes · 21-session hit rate 21% · median +5d 0.00, +21d 0.00 · grade C

Episodes when this series last sat in the same trailing-365-observation z bucket, with the forward 5- and 21-session move of S&P 500. 342 episodes at least 21 days apart; the table shows the most recent 8. A conditional distribution with its count, not a signal.

Nasdaq vol (VXN) · last 22.89 as of 2026-10-15 · 6,464 observations from 2001-02-02

Five years of Nasdaq vol (VXN) with the high-volatility weeks shaded, from the same two-state filter the Regime tab draws. One state, one shading, every tab.

The last 8 times this looked like today — and what Nasdaq 100 did next

episode	z	level	Nasdaq 100 +5d	Nasdaq 100 +21d
2026-09-14	-0.32	22.05	+4.65%	+4.95%
2026-08-24	-0.20	22.69	+1.49%	+5.89%
2026-08-03	0.26	24.77	+2.94%	+1.04%
2026-07-10	0.37	24.89	-4.13%	-0.68%
2026-05-21	0.04	22.74	+2.95%	+3.37%
2026-04-30	-0.12	21.79	+4.05%	+10.49%
2026-04-09	0.28	23.50	+4.99%	+16.56%
2026-02-25	0.28	22.94	-0.93%	-6.88%

z in [-0.5, 0.5) · n=224 episodes · 21-session hit rate 65% · median +5d 0.59, +21d 2.01 · grade C

Episodes when this series last sat in the same trailing-365-observation z bucket, with the forward 5- and 21-session move of Nasdaq 100. 224 episodes at least 21 days apart; the table shows the most recent 8. A conditional distribution with its count, not a signal.

Baa credit spread · last 1.44 as of 2026-10-15 · 10,197 observations from 1986-01-02

Five years of Baa credit spread with the high-volatility weeks shaded, from the same two-state filter the Regime tab draws. One state, one shading, every tab.

The last 8 times this looked like today — and what S&P 500 did next

episode	z	level	S&P 500 +5d	S&P 500 +21d
2026-09-11	-2.06	1.50	-0.08%	+1.96%
2024-04-10	-2.14	1.40	-2.68%	+1.04%
2024-02-22	-2.09	1.49	+0.18%	+2.89%
2023-12-06	-2.05	1.63	+3.47%	+3.06%
2023-09-21	-2.31	1.66	-0.70%	-2.44%
2018-02-01	-2.34	1.56	-8.54%	-4.63%
2018-01-11	-2.08	1.69	+1.10%	-5.35%
2017-01-25	-2.03	2.21	-0.82%	+2.85%

z in [-99.0, -2.0) · n=39 episodes · 21-session hit rate 18% · median +5d 0.00, +21d 0.00 · grade C

Episodes when this series last sat in the same trailing-365-observation z bucket, with the forward 5- and 21-session move of S&P 500. 39 episodes at least 21 days apart; the table shows the most recent 8. A conditional distribution with its count, not a signal.

What changed since last week

leaf	then	now	change	compared with
horizon days	63.00	63.00	unchanged	2026-10-11
n series	36.00	36.00	unchanged	2026-10-11
n panels	18.00	18.00	unchanged	2026-10-11

0 of 3 headline leaves moved. A repeated value can mean the upstream had not published, not that nothing happened.

ACF of the remainder · 3 rows

series	n	lags outside 95 band	first lag outside	conf95	reading	STL remainder p: Ljung-Box(24) · Jarque-Bera · ARCH-LM(4)	AutoReg (BIC lags, persistence) and its residual p, same three tests	fit seconds
VIX	260	4	1	0.12	Autocorrelation of the MSTL remainder over 24 lags, with the 95% band at ±0.122,	0.000 · 0.000 · 0.000	lags 1, persistence -0.11; 0.005 · 0.000 · 0.000	0.5
Nasdaq vol (VXN)	260	6	1	0.12	Autocorrelation of the MSTL remainder over 24 lags, with the 95% band at ±0.122,	0.000 · 0.000 · 0.000	lags 1, persistence -0.12; 0.002 · 0.000 · 0.000	0.4
Baa credit spread	260	16	1	0.12	Autocorrelation of the MSTL remainder over 24 lags, with the 95% band at ±0.122,	0.000 · 0.000 · 0.000	lags 1, 2, 3, 4, persistence +0.13; 0.208 · 0.000 · 0.000	0.5

Harvey-Jaeger style structural check: the autocorrelation of the decomposition's remainder against a 95% band. Lags outside the band mean the trend and seasonal have not taken everything systematic out of the series. This is Method content. It is not a forecast and nothing is extrapolated from it.

series · 3 rows

label	unit	kind	last	as of	first obs	n obs	ma 13w	vs 13w
VIX	pct	level	16.46	2026-10-15	1990-01-02	9,296	15.38	1.08
Nasdaq vol (VXN)	pct	level	22.89	2026-10-15	2001-02-02	6,464	21.98	0.91
Baa credit spread	pct	level	1.44	2026-10-15	1986-01-02	10,197	1.54	-0.10

scalars

field	value
horizon days	63
n series	36
statsmodels version	0.14.6
statsmodels pinned	0.14.6
statsmodels error	not reported

4 rows and 1 field withheld at this tier: absent from the page, not hidden in it.

Evidence grades. Every figure on this site carries a grade assigned by the validation layer, not by the author: D a descriptive fact computed from the record; C a historical distribution with its sample count; N a hypothesis tested and unable to beat chance under the stated control; T a tested-positive claim under the full protocol — none exists as of this build, which is why no forecast appears. Nulls are published in the null-result registry. MacroTerminal is a research publication and is not investment advice; nothing here is a recommendation to buy or sell anything. Grades and as-of dates are on every chart.

How the figures on this page are constructed is proprietary. For methodology questions, write to e@finkfi.com.

month	market holidays	Crude prints	Gas prints	option expiries	quad-witchings
Jan	19	45	43	10	0
Feb	10	40	41	10	0
Mar	3	45	45	10	10
Apr	7	42	42	10	0
May	10	43	43	10	0
Jun	4	45	45	10	10
Jul	10	44	43	10	0
Aug	0	45	45	10	0
Sep	10	42	43	10	10
Oct	0	44	44	10	0
Nov	10	44	43	10	0
Dec	10	43	44	10	10

month	market holidays	Crude prints	Gas prints	option expiries	quad-witchings
Jan	19	45	43	10	0
Feb	10	40	41	10	0
Mar	3	45	45	10	10
Apr	7	42	42	10	0
May	10	43	43	10	0
Jun	4	45	45	10	10
Jul	10	44	43	10	0
Aug	0	45	45	10	0
Sep	10	42	43	10	10
Oct	0	44	44	10	0
Nov	10	44	43	10	0
Dec	10	43	44	10	10

month	market holidays	Crude prints	Gas prints	option expiries	quad-witchings
Jan	19	45	43	10	0
Feb	10	40	41	10	0
Mar	3	45	45	10	10
Apr	7	42	42	10	0
May	10	43	43	10	0
Jun	4	45	45	10	10
Jul	10	44	43	10	0
Aug	0	45	45	10	0
Sep	10	42	43	10	10
Oct	0	44	44	10	0
Nov	10	44	43	10	0
Dec	10	43	44	10	10

month	market holidays	Crude prints	Gas prints	option expiries	quad-witchings
Jan	19	45	43	10	0
Feb	10	40	41	10	0
Mar	3	45	45	10	10
Apr	7	42	42	10	0
May	10	43	43	10	0
Jun	4	45	45	10	10
Jul	10	44	43	10	0
Aug	0	45	45	10	0
Sep	10	42	43	10	10
Oct	0	44	44	10	0
Nov	10	44	43	10	0
Dec	10	43	44	10	10

month	market holidays	Crude prints	Gas prints	option expiries	quad-witchings
Jan	19	45	43	10	0
Feb	10	40	41	10	0
Mar	3	45	45	10	10
Apr	7	42	42	10	0
May	10	43	43	10	0
Jun	4	45	45	10	10
Jul	10	44	43	10	0
Aug	0	45	45	10	0
Sep	10	42	43	10	10
Oct	0	44	44	10	0
Nov	10	44	43	10	0
Dec	10	43	44	10	10

month	market holidays	Crude prints	Gas prints	option expiries	quad-witchings
Jan	19	45	43	10	0
Feb	10	40	41	10	0
Mar	3	45	45	10	10
Apr	7	42	42	10	0
May	10	43	43	10	0
Jun	4	45	45	10	10
Jul	10	44	43	10	0
Aug	0	45	45	10	0
Sep	10	42	43	10	10
Oct	0	44	44	10	0
Nov	10	44	43	10	0
Dec	10	43	44	10	10

month	market holidays	Crude prints	Gas prints	option expiries	quad-witchings
Jan	19	45	43	10	0
Feb	10	40	41	10	0
Mar	3	45	45	10	10
Apr	7	42	42	10	0
May	10	43	43	10	0
Jun	4	45	45	10	10
Jul	10	44	43	10	0
Aug	0	45	45	10	0
Sep	10	42	43	10	10
Oct	0	44	44	10	0
Nov	10	44	43	10	0
Dec	10	43	44	10	10

month	market holidays	Crude prints	Gas prints	option expiries	quad-witchings
Jan	19	45	43	10	0
Feb	10	40	41	10	0
Mar	3	45	45	10	10
Apr	7	42	42	10	0
May	10	43	43	10	0
Jun	4	45	45	10	10
Jul	10	44	43	10	0
Aug	0	45	45	10	0
Sep	10	42	43	10	10
Oct	0	44	44	10	0
Nov	10	44	43	10	0
Dec	10	43	44	10	10

month	market holidays	Crude prints	Gas prints	option expiries	quad-witchings
Jan	19	45	43	10	0
Feb	10	40	41	10	0
Mar	3	45	45	10	10
Apr	7	42	42	10	0
May	10	43	43	10	0
Jun	4	45	45	10	10
Jul	10	44	43	10	0
Aug	0	45	45	10	0
Sep	10	42	43	10	10
Oct	0	44	44	10	0
Nov	10	44	43	10	0
Dec	10	43	44	10	10