Mispricing Scanner
A Bayesian engine scans prediction markets daily for mispricings. Agent A finds the same event on the other platform (LLM-validated) and compares the price — when a validated twin exists. Agent B is Claude NLP estimating probability from the question. When the engine diverges from the market by 5pp+, the contract is flagged with Kelly sizing; 3–5pp near-misses go to a free watchlist band.
Runs every morning; results post by ~10 AM ET. How it works →
Quick Answer
the Mispricing Scanner publishes a Kalshi contract only when the same event is found on the other platform and a resolution-criteria check confirms the two prices are comparable. That check has not cleared across the full scan history, so the board is currently empty — the standalone model estimate that used to fill it did not beat the market price when reviewed against settled results, and is no longer graded or published. The tool is being rebuilt for the 2026 midterms as a markets-versus-pundits tracker.
If you're asking whether Kalshi/Polymarket mispricing flags actually pay out: the scanner flags markets where its Bayesian engine diverges from the platform price by 5pp or more. HIGH CONFIDENCE requires 8pp+ and a validated same-event twin on the other platform pulling the same direction — most contracts have no such twin, so many days produce no HIGH flags at all. That scarcity is the design. Everything else lands at MEDIUM or LOW, with a free 3–5pp watchlist band of forming edges below the flag bar. The Kelly fraction shown is quarter-Kelly, sized on a cost-adjusted entry price, not the headline edge.
Caveat: a flag is a signal to investigate, not a guaranteed trade. The engine now validates cross-platform matches with an LLM same-event gate, so the old “same name, different event” pairs are filtered out — but still read both contract pages and confirm the resolution criteria before sizing.
What Is the Mispricing Scanner?
The Mispricing Scanner is a daily automated scan of Kalshi and Polymarket binary markets. It publishes a contract only when the same event is listed on the other venue and a resolution-criteria check confirms both contracts settle on the same terms, so their prices can be compared at all. Without that confirmation there is no flag — two contracts with similar names and different settlement rules are not the same market.
Kalshi anchors the primary scan because it lists the broader set of contracts our other tools already cover, not because of any difference in legal access — both venues are open to US traders. A Polymarket price shown here comes from its international order book, a separate exchange from Polymarket US with its own liquidity and settlement, so the two are not interchangeable.
How It Works
For each platform: Agent A looks for the same event on the other platform — a title pre-filter, then an LLM gate confirming both contracts resolve on identical criteria before the prices are compared (no validated twin → no cross-reference). Agent B asks Claude for an independent probability estimate. Both feed into a Bayesian weighted average. Divergences of 5pp+ are flagged and 3–5pp near-misses go to the free watchlist band; HIGH CONFIDENCE needs 8pp+ and a validated twin agreeing, which is why it is rare.
When to Use This Tool
Check the scanner in the morning once the day's scan has posted — usually by 10 AM ET. HIGH CONFIDENCE flags are the priority when there are any; otherwise work the widest divergences down. Verify the cross-platform match is the same event, check for overnight news that could explain the gap, then size with the quarter-Kelly fraction shown. This is a signal to investigate, not a guaranteed trade.
Read the Methodology
The scanner's design decisions are written up in full, including the ones that make the board publish less rather than more: how the Polymarket Mispricing Scanner works is the place to start. From there, what HIGH CONFIDENCE actually requires explains why that tier is rare by construction, and why the scanner fails closed covers what happens when the model cannot reach a confident estimate — it publishes nothing instead of guessing. If you are weighing whether any of this is tradeable at all, why most prediction market arbitrage isn't real is the honest version of the answer.
MARKET INTELLIGENCE
Find markets where the crowd got it wrong
What is this?
The crowd is often right. But not always. This scanner identifies prediction market contracts where the price seems significantly out of line with real-world data — news, historical base rates, or statistical models.
Think of it as a lie detector for market prices. When a market is way overpriced or underpriced relative to reality, this flags it. You still have to decide — but this gives you the shortlist of where to look.
Real-World Example
→ The Flag
Historical data shows government shutdowns resolve within 14 days 84% of the time. A market asks "Shutdown lasts more than 21 days" — priced at 55¢ (the crowd thinks 55% likely). That's a mispricing signal.
The scanner flags the gap: historical base rate says this should be worth about 16¢, not 55¢. You buy NO at 45¢ (inverse of YES at 55¢) and wait.
✅Action: Use this as your daily deal-finder. Look for anything flagged more than 15 points from the estimated fair value.
Bottom line: The crowd panics, overreacts, and misprices markets every day. This helps you catch it.
Full guide →Loading today's scan
Checking Bayesian engine results...
Read the fine print
Half the edge in prediction markets is knowing exactly how a contract resolves. We read the official resolution rules of the markets traders care about and flag the traps — which data print counts, the exact metric, rounding, and settlement timing.
Today's trapWill CPI Core rise more than 0.2% in October?Resolves YES if the seasonally adjusted BLS Core CPI (All Urban Consumers, All Items less Food and Energy) for October 2026 rises by MORE THAN 0.2% (strictly above, not equal to).4 traps
- Strictly above 0.2%, not at or above — The rules say 'above 0.2%,' so an exact +0.2% print (a common rounded outcome) resolves NO, which could catch traders who assume ≥0.2% triggers YES.
- Seasonally adjusted print only — BLS publishes both seasonally adjusted and unadjusted Core CPI figures; only the seasonally adjusted series is specified, and the two can differ enough to flip the outcome.
- No revision language — initial vs. revised print unclear — BLS sometimes revises CPI figures; the rules don't specify whether the first release or a later revision governs, creating settlement ambiguity if a revision crosses the 0.2% threshold.
- October 2026, not October 2025 — The resolution year is 2026 (reported ~November 2026), so traders focused on the near-term October 2025 release are tracking the wrong data point entirely.
Will the rate of CPI inflation be above 4.9% for the year ending in September 2026?Resolves YES if the BLS-reported CPI 12-month inflation rate for the period ending September 2026 exceeds 4.9% when expressed to one decimal place.3 traps
- One decimal place, not full precision — Resolution uses the BLS's officially published one-decimal-place figure (e.g., 5.0%), so a full-precision rate of, say, 4.95% rounds to 5.0% and resolves YES, while 4.94% rounds to 4.9% and resolves NO — the rounding rule is decisive near the threshold.
- "Above 4.9%" excludes exactly 4.9% — The contract requires the rate to be strictly greater than 4.9%, so a printed one-decimal-place value of exactly 4.9% resolves NO, making the effective trigger the first rounded print of 5.0% or higher.
- Initial release vs. subsequent BLS revisions — The rules cite the BLS-reported value but do not specify whether the initial release or a later revision governs; if BLS revises the figure after initial publication, it is unclear which print is used for settlement.
Will the rate of CPI inflation be above 4.7% for the year ending in September 2026?Resolves YES if the BLS-reported CPI 12-month inflation rate for the period ending September 2026 exceeds 4.7%, using the one-decimal-place value as officially published.3 traps
- One-decimal-place rounding is decisive — The contract explicitly uses the BLS's rounded one-decimal figure, so a true rate of, say, 4.74% rounds down to 4.7% and resolves NO, while 4.75% rounds up to 4.8% and resolves YES — the rounding rule can flip the outcome near the threshold.
- Strictly 'above' 4.7%, not 'at or above' — The rules require the rate to be *more than* 4.7%, meaning an exact one-decimal print of 4.7% resolves NO, making the effective threshold the next reportable increment (4.8%).
- Initial release vs. later BLS revisions — The rules don't specify whether the first (advance) print or a subsequent revised print is used; if BLS revises the September 2026 figure after initial release, it's ambiguous which print governs settlement.
Will the upper bound of the federal funds rate be above 4.25% following the Fed's Oct 28, 2026 meeting?Resolves YES if the federal funds rate upper bound published on the Fed's official website is strictly greater than 4.25% after the October 28, 2026 FOMC meeting.3 traps
- Strictly greater than, not greater-or-equal — An upper bound of exactly 4.25% resolves NO — the threshold is exclusive, so only a rate of 4.50% or higher (in standard 25 bps increments) would resolve YES.
- October 28 may not be an FOMC meeting date — If the Fed does not hold a scheduled meeting on Oct 28, 2026, there is no new rate decision to evaluate, and traders must clarify whether the contract voids/extends or resolves based on the last published rate.
- Fed's official website is the sole source — Only the rate as published on federalreserve.gov counts — CME data, press releases, or other financial data providers are irrelevant if they differ.
Will CPI Core rise more than 0.6% in October?Resolves YES if the seasonally adjusted BLS CPI-U All Items less Food and Energy (Core CPI) for October 2026 shows a month-over-month increase of strictly more than 0.6%.4 traps
- Seasonally adjusted, not unadjusted figure — The rules specify the seasonally adjusted print; the BLS releases both adjusted and unadjusted Core CPI figures, and they can differ — using the wrong series could lead to an incorrect read on resolution.
- Strictly above 0.6%, not at or above — A print of exactly 0.6% resolves NO, since the rule requires an increase 'above' 0.6%, making the boundary critical for positions near that threshold.
- Initial release vs. subsequent revisions — The rules say 'as published' but don't specify which print; if the BLS later revises the figure above or below 0.6%, it's unclear whether the initial release or a revision governs resolution.
- October 2026, not October 2025 — The resolution references October 2026 data (typically released in November 2026), which is further out than traders may assume if they conflate this with a near-term contract.
Will CPI Core rise more than 0.2% in September?Resolves YES if the seasonally adjusted BLS Core CPI (All Urban Consumers, All Items less Food and Energy) for September 2026 shows a month-over-month increase strictly greater than 0.2%.4 traps
- Strictly above 0.2%, not 0.2% itself — The rule uses 'above 0.2%,' meaning an exact 0.2% print resolves NO — a critical distinction if the release rounds to 0.2% but the unrounded figure is ≤0.2%.
- Unrounded vs. rounded print ambiguity — BLS publishes a headline rounded figure (e.g., 0.2%) but the underlying unrounded index level may differ; the rules don't specify which precision is used, so a 0.2% rounded print could be anywhere from ~0.15% to ~0.25% unrounded, affecting resolution.
- Seasonally adjusted series only — The contract specifies the seasonally adjusted figure; the unadjusted print can differ materially, and traders tracking the wrong series could misread the outcome.
- Initial release vs. subsequent revisions — BLS revises CPI data; the rules don't clarify whether resolution uses the first published print or a later revision, which could change the outcome if a revision crosses the 0.2% threshold.
Will the rate of CPI inflation be above 4.4% for the year ending in September 2026?Resolves YES if the BLS-reported CPI 12-month inflation rate for the period ending September 2026 exceeds 4.4% (strictly greater than), as measured to one decimal place.4 traps
- Strictly above 4.4%, not at or above — The rule says 'more than 4.4%', so a reading of exactly 4.4% resolves NO — traders positioned near the threshold must account for this strict inequality.
- One-decimal BLS print, not unrounded figure — Resolution uses the one-decimal place value officially reported by BLS (e.g., 4.4% or 4.5%), not the more precise underlying figure, so the rounding in BLS's release — not the raw calculation — is what determines the outcome.
- Initial release only vs. later revisions — CPI data can be subject to revision; the rules do not explicitly clarify whether the first print or a subsequent revised print governs, creating ambiguity if BLS revises the September 2026 figure after initial release.
- September 2026 ending month, not full-year average — This contract measures the 12-month change ending specifically in September 2026 (a point-in-time year-over-year reading), not an annual average CPI figure, which could diverge meaningfully from a calendar-year average.
Will the rate of CPI inflation be above 4.6% for the year ending in September 2026?Resolves YES if the BLS-reported CPI 12-month inflation rate for the period ending September 2026 exceeds 4.6% when expressed to one decimal place.3 traps
- One decimal place: 4.6% is the bar — The rule uses the one-decimal-place BLS print, so a raw figure like 4.64% rounds to 4.6% and resolves NO — only a print of 4.7% or higher resolves YES, making the rounding behavior critical near the threshold.
- "Above" 4.6% — exact threshold excluded — The rule says 'more than 4.6%', so a one-decimal print of exactly 4.6% resolves NO; traders long YES need a print of at least 4.7% (one-decimal).
- Initial release vs. subsequent revisions — The rules cite the BLS reported value but don't specify whether the initial release or a later revision governs; CPI prints are occasionally revised, and which vintage is used could flip resolution near the boundary.
Related Tools
Go Pro · 26% off your first year
Every edge the engines find, the moment they find it
Pro opens every engine on the site — the cross-market arb scanner, the Mispricing Scanner, Thee Oracle, and the silver, gold, oil and bitcoin edge models that price commodity contracts in real time.
$111 for the first year, then $150/yr. Code applies automatically. Ends Dec 31. Monthly is $14.99/mo.
Every signal graded in public, losers left on the board. See the record →
Frequently Asked Questions
Which Kalshi binary markets are mispriced right now?
None that we are willing to publish. A contract only reaches this board when the same event is found on the other platform and an LLM gate confirms both contracts resolve on identical criteria before their prices are compared. Measured across the full scan history, that validated cross-platform check has not once completed — most Kalshi contracts simply have no Polymarket twin resolving on the same criterion. We used to fill the gap with a standalone language-model probability estimate and call the difference an edge. Reviewed against settled results, that estimate did not beat the market price, so it is no longer graded and no longer published. An empty board is the honest output of that rule, not an outage.
What is the Kalshi mispricing scanner?
A daily automated scan of Kalshi and Polymarket binary markets, looking for contracts trading away from a price that can be independently corroborated. The only corroboration it now accepts is a validated same-event twin on the other platform: a title pre-filter narrows candidates, then an LLM gate confirms both contracts settle on the same criterion before any price comparison happens. No validated twin means no flag. The tool is being rebuilt for the 2026 midterms as a markets-versus-pundits tracker, which compares the live market price against named forecasters and ratings outlets instead of against a model of our own.
Do Kalshi vs Polymarket mispricing flags actually pay out?
We stopped claiming they do. The scanner's original thesis was that our probability model could out-predict a liquid market. Checked against settled outcomes by price band, the claimed win rate exceeded the actual win rate in every band — the model was not beating the market, it was disagreeing with it. Rather than retune a losing signal, the tool now grades nothing that lacks a validated cross-platform price check, and publishes nothing it will not grade. The rebuilt version inverts the claim entirely: the market price becomes the benchmark and named pundits are the comparison, which is a scoreboard rather than a trade signal.
How does the scanner engine detect mispricings?
It compares a contract's price against a corroborating price for the same event on the other venue. A title pre-filter narrows candidates, then an LLM gate confirms both contracts resolve on the same event and criterion — without that confirmation there is no cross-reference and no flag, because two contracts with similar names and different settlement rules are not the same market and their prices are not comparable. The engine previously also weighted in a standalone language-model estimate; that input no longer produces a published flag on its own.
Why is the mispricing board empty?
Because the gate that would put something on it has not cleared. A flag requires a validated same-event twin on the other platform, and across the entire scan history no scanned Kalshi contract has had one that passed the resolution-criteria check. The alternative — publishing our model's disagreement with the market as though it were an edge — is exactly what the settled record showed did not work. Showing nothing is the correct output of an honest rule, and the board will refill only if the cross-platform check starts clearing.
Is the Mispricing Scanner free to use?
The board itself is a Pro tool at $14.99 per month, though it is currently publishing nothing while the tool is rebuilt for the midterms. The free tools — EV Calculator, Probability Converter, and Combo Edge Builder — cover the core math if you want to check a single contract yourself, and the Combo Edge Builder is fully free with no leg cap.
What is the difference between the Kalshi scan and the Polymarket scan?
They swap which venue anchors the price check: the Kalshi scan looks for the corroborating price on Polymarket, and the Polymarket scan looks for it on Kalshi. Kalshi is the primary scan because it lists a broader set of US-available contracts and its markets are the ones our other tools already cover — not because of any difference in legal access. Both venues are open to US traders. Note that a Polymarket price we quote comes from its international order book, which is a separate exchange from Polymarket US and does not share its liquidity or settlement, so the two prices are not interchangeable.