← Back to scans

Will Democrats win exactly 10 seats in 2026 Virginia House of Representatives elections?

KXVAHOUSEDEM-26NOV03-10 · Elections · 2026-04-21
42%
Agent
75%
Market Price
-33.0%
Edge
30%
Confidence
Volume: 22,344
Spread: 1.0c
Days to resolution: 560
Markets in event: 7
Final Rationale
My independent estimate of 21% was anchored on a 50/50 prior for the April 21 redistricting referendum passing, but I ACCEPT the critique that today IS referendum day and the market's sustained climb to 74% carries real Bayesian information — I raise the referendum-passage prior to ~65%. I PARTIALLY ACCEPT that conditional probability of exactly 10 seats given a map explicitly designed for 10 in a favorable midterm is higher than 25-30% (revising to ~40%, though 5 competitive Harris districts still create real variance toward 9 or 11). I REJECT full convergence to the market because: (i) legal challenges to a mid-decade gerrymander are non-trivial, (ii) exact-10 is a narrow target with genuine seat-level variance, and (iii) the orderbook is thin with $0.998 spread, reducing signal quality. Recalculating: 0.65 × 0.40 + 0.35 × 0.04 ≈ 0.27, plus modest upward weight for wave dynamics and market information content → ~0.42.
Price vs. prediction
How the market moved after the agent's call. Solid blue line is the actual market price; dashed line is the agent's static forecast at $t{=}0$.
$n = 58$ follow-ups
1. Planner Opus · Fermi decomposition + tool plan
Tools chosen: article_search web_search kalshi_data kalshi_orderbook wikipedia_lookup code_execution
Sub-questions (Fermi decomposition)
  1. Will Democrats win between 9 and 11 seats (i.e., close to 10) in the 2026 Virginia U.S. House elections? (w=0.40)
  2. Will Democrats win exactly 10 seats (vs. fewer) given that Virginia's current Democratic delegation has 6 seats out of 11 total? (w=0.35)
  3. Will the 2026 midterm environment (anti-incumbent/anti-Republican wave) favor significant Democratic gains in Virginia specifically? (w=0.25)
Planner reasoning
This question asks about an exact seat count (10 out of 11) in Virginia's U.S. House delegation in 2026. Key analytical steps: 1. **Current baseline**: Virginia has 11 congressional seats. After 2024, Democrats hold approximately 6-7 seats. Winning exactly 10 means a near-total sweep, flipping roughly 3-4 Republican-held seats while losing none of their own. 2. **Reference class for exact bracket outcomes**: Exact seat count predictions are inherently low-probability because they require hitting a specific number. Even if 10 is near the median expected outcome, the probability of hitting exactly 10 vs. 9 or 11 is spread across multiple outcomes. 3. **Competitive seat analysis**: Virginia's congressional map has only a handful of truly competitive districts. Most seats lean strongly partisan. For Democrats to win 10, they'd need to sweep all marginal seats and flip deep into Republican territory — requiring an exceptional wave environment. 4. **Temporal dynamics**: Resolution is November 2027 (covering November 2026 elections). The 2026 midterm environment currently appears moderately favorable for Democrats given anti-Trump sentiment. However, 560 days remain, so sentiment could shift. Even if a wave materializes, winning 10/11 is a very specific extreme outcome. 5. **Calibration**: The probability distribution across possible outcomes (5, 6, 7, 8, 9, 10, 11 seats) means any single exact outcome has limited probability. The most likely range is 7-9 seats in a modest wave, making exactly 10 a tail event (~5-10% probability even if favorable conditions exist). 6. **Key uncertainty**: Whether redistricting or retirements change competitiveness of seats before 2026.
2. Research Parallel tool calls · legacy v2
ToolStatusTimeItemsSummary
article_search OK 0.2s -
web_search OK 60.6s -
kalshi_data OK 3.9s -
kalshi_orderbook OK 0.2s -
wikipedia_lookup OK 1.4s -
code_execution OK 0.0s -
3. Evidence Synthesis Sonnet · 15 items · legacy v2
#StrengthCredibilityDirectionSourceClaimPriced In
1 STRONG 78 ↓ DOWN web_search Virginia has 11 congressional districts; Democrats currently hold 6 seats (a 6-5 edge). Districts 1, 2, and 7 are considered the most competitive under the current map. Yes
2 STRONG 82 ↑ UP web_search A Virginia redistricting referendum appeared on the April 21, 2026 ballot; if passed, Democrats could redraw districts to favor 10 of 11 seats — an increase from the current 6. No
3 MODERATE 75 ↓ DOWN web_search The proposed Democratic gerrymander map would create five districts that supported Harris by single digits — meaning they would be genuinely competitive, not safe Democratic seats even under the new map. No
4 MODERATE 55 ↓ DOWN code_execution A binomial model assuming 4-5 competitive seats with per-seat Democratic win probability of 40-60% estimates P(exactly 10 Dem seats) at approximately 2.6%-15.6%; the model's central estimate is ~5%. No
5 STRONG 70 ↑ UP kalshi_data The Kalshi market for exactly 10 Democratic Virginia House seats is priced at 74%, a dramatic increase of +19% over 30 days but down -13% over 7 days, with a price range of 45-90% over 43 days. No
6 STRONG 80 ↑ UP web_search Democrats explicitly stated their goal is to win 10 of 11 Virginia congressional seats via the redistricting amendment; the proposed map is designed to structurally favor 10 seats for Democrats. No
7 MODERATE 78 ↓ DOWN web_search Republican Rob Wittman in District 1 was re-elected with 56.3% in 2024 — indicating a safe Republican seat that would require a very favorable wave or map change to flip. Yes
8 MODERATE 78 ↓ DOWN web_search Democrat Suhas Subramanyam won the 10th District with only 52.1% in 2024, making this one of the most vulnerable Democratic-held seats going into 2026. Yes
9 STRONG 88 NEUTRAL wikipedia_lookup The 2026 Virginia House elections are confirmed to be held on November 3, 2026, with primary elections on August 4, 2026. Yes
10 STRONG 68 ↑ UP kalshi_data The Kalshi market prices exactly 10 Democratic seats at 74%, which represents a significant divergence from the statistical model estimate of ~5%, suggesting the market is heavily pricing in a new map scenario. No
11 MODERATE 72 ↑ UP web_search The redistricting effort is explicitly framed as a Democratic national response to Republican gerrymandering, suggesting Democrats perceive the 2026 environment as both an opportunity and a necessity for aggressive action. No
12 MODERATE 62 ↑ UP kalshi_data The Kalshi generic ballot market prices Republicans winning the House popular vote at only 14%, up +10% over 30 days — indicating a moderately favorable generic ballot environment for Democrats nationally. No
13 MODERATE 58 ↑ UP kalshi_data Democrats winning any statewide Texas election is now priced at 48% (+11% over 30 days), suggesting a broadly favorable Democratic wave environment nationally. No
14 STRONG 85 ↓ DOWN web_search Virginia voted for Kamala Harris with only 52% in 2024 — a competitive state rather than a strong Democratic state — limiting the structural wave advantage that Democrats could expect even in favorable conditions. Yes
15 MODERATE 65 NEUTRAL kalshi_data The 30-day surge in the Virginia-10-seats market (+19%) coincides with the redistricting referendum vote on April 21, 2026, suggesting market participants are primarily pricing in map change rather than wave dynamics alone. No
Information Gaps
  • No data on whether the April 21, 2026 redistricting referendum passed or failed — this is the single most critical unknown for this question.
  • No information on what the final map would look like if the referendum passed, or whether it was legally challenged.
  • No polling data on individual Virginia congressional districts for 2026.
  • No information on candidate recruitment in targeted Republican districts under either the current or proposed new map.
  • No data on the referendum's vote margin or exit polling that might indicate passage/failure.
  • No information on whether courts could block a legislatively-drawn Democratic gerrymander in Virginia if the referendum passed.
  • No data on generic ballot or Virginia-specific approval ratings for Republicans in early 2026.
  • The orderbook shows yes_bid=$0.00 and no_bid=$0.00 with spread of $0.998 — suggesting possible stale orderbook data that may not reflect true market depth.
Key Uncertainties
  • Whether the April 21, 2026 redistricting referendum passed — this is binary and transforms the entire analysis. Under the current map, 10 seats is a very unlikely tail outcome; under the proposed gerrymander map, 10 seats becomes the modal/expected outcome.
  • Whether any redrawn map would survive legal challenge from Republicans or the courts before the November 2026 election.
  • The exact shape of the final redrawn map if the referendum passed, since five of the 10 targeted seats would be competitive under the proposed map.
  • The magnitude of any anti-Republican wave in Virginia specifically, which could determine whether marginal seats under a new map flip Democratic.
  • Whether Democrats could hold the competitive 10th District (Subramanyam, 52.1% in 2024) under any map scenario.
  • The large divergence between the statistical model (~5%) and the Kalshi market (74%) — this gap is almost entirely explained by the referendum, but the referendum outcome remains unknown.
  • Whether the Kalshi market is correctly calibrating the referendum's probability of passage and its downstream effects on seat outcomes.
Market Context
Price: 0.74 · 7d: -0.13 · 30d: +0.19
Volume: MODERATE · Depth: HIGH
Reliability: MEDIUM-LOW — The 74% price represents a dramatic spike likely driven by the redistricting referendum news, but the orderbook shows $0.00 bids on both sides with near-maximum spread ($0.998), suggesting the displayed depth figure (21,399) may be stale or illiquid at current price levels. The market likely repriced sharply around the April 21 referendum date. The 43-day price range of 45-90% indicates extreme volatility. The market interpretation hinges entirely on referendum outcome which has not been confirmed in the research data.
4. Independent Forecaster Opus · No market price · legacy v2 Did NOT see market price
Independent estimate: 21% (30% confidence)
base rate
22%
25% conf
evidence driven
20%
30% conf
contrarian
22%
35% conf
Spread
2pp
Low disagreement
sq1: Will Democrats win between 9 and 11 seats in the 2026 Virginia U.S. House elections?
35%
Base rate for a party winning 9+ of 11 seats in a state that voted 52% for their presidential candidate is quite low historically — maybe 5-10% under normal maps. The critical variable is the April 21, 2026 redistricting referendum. If it passed and survives legal challenge, a new map designed to favor Democrats in 10 seats makes 9-11 the modal range (maybe 50-60%). If it failed, 9-11 is a deep tail event (<5%). Given I don't know the referendum outcome, I'll estimate ~50% probability it passed (referendums in Virginia are uncertain, and gerrymander referendums often face headwinds). Weighted: 0.5 * 0.55 + 0.5 * 0.05 = 0.30. Adding some upside for midterm wave dynamics: 0.35.
sq2: Will Democrats win exactly 10 seats (vs. fewer) given the current 6-seat baseline?
20%
Exact outcomes have limited probability mass. Under current map, exactly 10 is near-impossible (~2%). Under the proposed gerrymander if referendum passed, the map targets 10 seats but 5 are competitive single-digit Harris districts — so outcomes could easily be 7, 8, 9, 10, or 11. Exact 10 under new map probability ~25-30%. Probability-weighted: 0.5 * 0.27 + 0.5 * 0.02 = 0.145. Democrats' explicit targeting of 10 seats suggests the map is calibrated for that outcome, nudging up slightly to 0.20.
sq3: Will the 2026 midterm environment favor significant Democratic gains in Virginia?
60%
Base rate for president's party losing House seats in midterms is ~85-90% of cases since 1934. Trump is the incumbent, so Democrats have structural tailwinds. Virginia is a D+2 to D+3 state that reacts strongly to national sentiment. However, 'significant gains' is subjective — modest gains are highly likely (~80%), but truly wave-level gains enabling a near-sweep are less certain (~40%). Averaging: 60%.
Show full reasoning trace
base rate: Exact seat-count outcomes in an 11-seat delegation have inherently low probability mass spread across 12 possible values. Historical base rate for a party winning 10 of 11 seats in a state with ~52% partisan lean is very low (<5%) without aggressive gerrymandering.
evidence updates: The critical piece of evidence is the April 21, 2026 Virginia redistricting referendum explicitly designed to produce a 10-seat Democratic map. If it passed and survives challenge, the probability of exactly 10 seats rises to ~25-30% (modal outcome but with 5 competitive districts creating variance). If it failed, probability drops to ~2%. I estimate roughly 45-55% the referendum passed given Democratic mobilization but also uncertainty about voter appetite for partisan gerrymandering. Midterm environment favors Democrats generally (president's party loses seats 85%+ of the time).
combination method: The three sub-questions are highly correlated — all driven by the referendum outcome and wave strength. Rather than pure weighted average, I anchor on sq2 (exact-10 conditional on baseline) as most directly relevant, using sq1 and sq3 as context. The weighted average of 0.36 overstates because sq1 covers 9-11 (broader than exact 10) and sq3 is generic wave conditions. Pulling down to ~0.22.
final: My estimate of ~22% reflects: (a) ~50% probability the redistricting referendum passed and produces a map where 10 is the target, (b) conditional on that, ~35-40% probability of exactly 10 seats given 5 competitive districts that could produce 7, 8, 9, 10, or 11, (c) ~2-3% probability of reaching 10 under the current map via a massive wave. Combined: ~0.50 * 0.38 + 0.50 * 0.03 ≈ 0.20-0.22. Confidence is low because the key input (referendum outcome) is unknown to me.
ensemble: {'ensemble_count': 3, 'perspectives': {'base_rate': {'p_yes': 0.22, 'confidence': 0.25}, 'evidence_driven': {'p_yes': 0.2, 'confidence': 0.3}, 'contrarian': {'p_yes': 0.22, 'confidence': 0.35}}, 'spread': 0.02, 'individual_p_yes': {'base_rate': 0.22, 'evidence_driven': 0.2, 'contrarian': 0.22}}
5. Devil's Advocate Sonnet · legacy v2 Market price revealed
Missing Info Reasoning Flaw Asymmetric Evidence
Challenges
  1. The forecaster assigns 50% probability to the referendum passing, but today IS April 21, 2026 — the referendum date. The market spiked to 74% with a +19% 30-day trend culminating today. This price action is strong Bayesian evidence that the referendum either passed or is expected to pass. A rational prior given the market movement should be meaningfully higher than 50% — perhaps 65-75%. The forecaster acknowledges the referendum outcome is the 'single most critical unknown' but doesn't update on the market's implicit information about it.
  2. The conditional probability of exactly 10 seats GIVEN referendum passage is estimated at 25-30%, but this may be too low. If Democrats explicitly designed the map to yield 10 seats and midterm dynamics favor Democrats (president's party loses seats ~85% of time with Trump as incumbent), the modal outcome of the designed map in a favorable environment could be closer to 35-45%. The forecaster is symmetrically spreading variance across 7-11 when the map+environment combination skews the distribution.
  3. The forecaster dismisses the market's 74% pricing by pointing to illiquid orderbook ($0.00 bids), but a 43-day price history ranging 45-90% with moderate volume indicates real trading has occurred. The stale snapshot doesn't mean the market signal is invalid — it just means this moment's orderbook is thin.
  4. The combination method pulls the forecast DOWN from a weighted average of 0.36 to 0.22 by 'anchoring on sq2.' But sq2 itself (0.20) already incorporates the referendum uncertainty. This may be double-counting the downward pressure from referendum uncertainty.
Suggested adjustment: +15pp
Two genuine reasoning flaws warrant upward adjustment: (1) The 50% referendum-passage prior ignores informational content in the market's sustained run-up to 74% on the referendum day itself — a better prior is ~65-70%. (2) Conditional probability of exactly 10 given a map explicitly designed for 10 seats in a favorable midterm may be underestimated at 25-30%; 35-40% is more defensible. Recalculating: 0.65 * 0.38 + 0.35 * 0.03 ≈ 0.26 + small upward adjustment for wave dynamics ≈ 0.35-0.38. This is still well below the market at 74%, reflecting genuine residual uncertainty about referendum outcome, legal challenges, and seat-level variance — not market conformity.
Market comparison: Forecaster: 21%, Market: 74%. The 53-point divergence is substantial. Some divergence is justified because: (a) the market may be overreacting to referendum news before confirmation, (b) legal challenges could void a gerrymander, (c) exact-10 is a narrow target with real variance even under a favorable map. However, the forecaster's 50/50 referendum prior seems too agnostic given today IS referendum day and the market has steadily climbed. A moderate upward adjustment is warranted based on reasoning gaps, but the forecaster should not fully converge to market given genuine structural uncertainty.
6. Aggregator Opus · final calibrated forecast
42% (30% confidence)
My independent estimate of 21% was anchored on a 50/50 prior for the April 21 redistricting referendum passing, but I ACCEPT the critique that today IS referendum day and the market's sustained climb to 74% carries real Bayesian information — I raise the referendum-passage prior to ~65%. I PARTIALLY ACCEPT that conditional probability of exactly 10 seats given a map explicitly designed for 10 in a favorable midterm is higher than 25-30% (revising to ~40%, though 5 competitive Harris districts still create real variance toward 9 or 11). I REJECT full convergence to the market because: (i) legal challenges to a mid-decade gerrymander are non-trivial, (ii) exact-10 is a narrow target with genuine seat-level variance, and (iii) the orderbook is thin with $0.998 spread, reducing signal quality. Recalculating: 0.65 × 0.40 + 0.35 × 0.04 ≈ 0.27, plus modest upward weight for wave dynamics and market information content → ~0.42.
7. Entry Decision Opus Trader
Side
NO
Position Size
$900
Contracts
3600
Trader Confidence
30%
Trade Rationale
The edge is very large (-33%) with the market at 75% vs forecast at 42%, pointing clearly to NO. However, forecaster confidence is low (0.30) and the Devil's Advocate flagged multiple issues including missing info and asymmetric evidence, suggesting a +0.15 upward adjustment — which would narrow the edge to ~-18% but still clearly NO. The 'exactly 10 seats' framing is inherently narrow with real variance toward 9 or 11 even under favorable conditions, supporting the NO thesis. Key risk: if today's referendum passes cleanly, the market may be pricing legitimate information about map-drawn outcomes, though 75% still seems aggressive for an exact-integer outcome 18+ months out.
Allocation Logic
Large edge warrants above-baseline consideration, but low forecaster confidence (0.30), critic flags, thin orderbook, and 560-day horizon with referendum uncertainty pull size down to $900 — slightly below baseline to respect the genuine variance in an exact-count bet.
Entry price: $0.25
Current: $0.95
Status: WON
P&L: $2520.00