Every thesis ships with a published invalidation trigger. When it resolves it's marked played-out or invalidated — dated, with whether the trigger fired. Across resolved theses we compute a Brier score (forecasting accuracy) and break play-out rates out by conviction tier, so you can see whether SUPREME actually beats LOW. Strictly non-monetary.

What is a Brier score?

The mean squared error between the probability a conviction tier implies (SUPREME≈0.9 … LOW≈0.5) and the binary outcome. 0 is perfect, 0.25 is a coin flip. For reference, expert human Superforecasters score around 0.08 and the best LLMs around 0.10.

Do you publish returns or P&L?

No — never. The track record scores whether each falsifiable claim was falsified, not how a trade did. There are no returns, no P&L, no positions, no sizing anywhere on the site.

What happens when a thesis is wrong?

It's marked invalidated, dated, and kept on the public record — with whether the published trigger fired first. Being wrong in public, on the record, is the point: it's what makes the score trustworthy.

Track record · we keep score in public

Every thesis, on the clock.

Anyone can sound confident. orbyd publishes the exact condition that would prove each thesis wrong, then resolves it in public — played out, or invalidated. No returns, no P&L, ever; just whether the falsifiable claim was falsified. Below: every live commitment and the clock on it.

Open commitments · 42 · soonest to resolve first

INTC LOW catalyst due

Invalidates if Daily close below $102.50 support (2026-06-02 level) confirms NVIDIA-PC-threat distribution top; or Q2 call shows PC CPU share loss to ARM. Bull thesis stays invalid absent a named external 18A foundry customer.
HOOD MEDIUM catalyst due

Invalidates if Weekly close below 20-EMA; OR CLARITY Act stalls/dies in committee (Novogratz cut passage odds 90%→60% Jun 1), repricing the crypto take-rate leg; OR Q2 print shows event-contract take-rate compression from Kalshi/Wintermute competition.
IQE LOW catalyst due

Invalidates if Weekly close below the 19.8p strategic-raise price (MACOM + institutional cost basis) on >1.5x avg volume = re-rate failed; OR FY2026 >20% revenue-growth guide cut in any trading update; OR Photonics revenue down half-on-half at H1 2026 interims (~Sept 2026).
AVGO MEDIUM catalyst due

Invalidates if Weekly close below the post-earnings reaction low AND below the 20-EMA (sell-the-news becomes a de-rate); OR FY27 AI guide cut below $100B; OR confirmed Google/Meta TPU-generation share loss to MRVL.
META MEDIUM catalyst due

Invalidates if Weekly close below 20-EMA on rising volume; OR Q2 ad rev <+15% YoY (vs Q4 +21%); OR Business Agent/Hatch show no paying-customer traction by Q2 print (~2026-07-29); OR AVGO/custom-silicon theme rolls over hard into SATURATED.
MSTR LOW catalyst due

Invalidates if Avoid-stance flips ONLY on all three: (1) weekly 8-K showing net BTC ACCUMULATION with zero sell-language, (2) BTC weekly close back above $84K, (3) MSTR weekly close above its 20-EMA. Until then every bounce is a falling-knife trap; no long, no averaging in.
PLTR MEDIUM catalyst due

Invalidates if Failure to reclaim the 200-DMA within ~2-3 weeks plus a daily close below the early-June profit-taking swing low on >1.5x avg volume; OR DIA ruling formally excludes PLTR from the contract bid; OR Q2 US commercial decel <45% YoY (~Aug).
AXTI MEDIUM catalyst due

Invalidates if Daily close below $90 (loses rising 20-EMA/base) = pullback became distribution, abort. Or Q2 (7/29) revenue under the $34M guide, or InP backlog shrinks QoQ from the $100M record.
CRCL MEDIUM catalyst due

Invalidates if Weekly close below $77 on above-average volume (Compass Point magnet reclaimed); OR Mastercard/Nium prove logo-only with no USDC settlement-volume traction by the Q2'26 print; OR Fed accelerates cuts, crushing the ~80% reserve-yield base.
CEG LOW catalyst due

Invalidates if Weekly close below [entry redacted] (200-DMA + post-Calpine gap fill), OR FERC denies the Amazon/Susquehanna co-location ISA amendment (docket ER24-2172), OR 2026 adj-EPS guide cut below the reaffirmed $11 floor.
LITE MEDIUM catalyst due

Invalidates if Daily close back below ~$840 forfeits the 2026-06-01 $866.97 signal-bar reclaim; OR weekly close under the 20-EMA; OR a peer optical name (COHR/MRVL/AAOI) losing its 50-day while LITE diverges down — any one flips momentum to broken, exit.
VST MEDIUM catalyst due

Invalidates if Weekly close below $132 (May-2026 swing low) on >1.3x avg vol; OR failure to reclaim the 50-DMA (~$165) by end-July while the AI-power complex (CEG/TLN/NRG) rolls over; OR a hyperscaler Q2 capex guide-cut that re-rates the whole group lower.
COIN LOW catalyst due

Invalidates if Long re-arms ONLY on BTC reclaim of ~$68K AND COIN weekly close above $185 (back over Piper $180 anchor + 20-EMA), ideally with 3+ days net-positive ETF flows. BTC losing $60K opens $55K → harder no-touch. Do not enter into the knife; do not buy oversold RSI alone.
SMR LOW catalyst due

Invalidates if SK $200B-package talks close with no named NuScale allocation, or weekly close below $10 with a failed 20-EMA reclaim. RoPower FID slip past 2026-12-31 = DEAD. Engage only on a confirmed SK capital figure or a binding offtake ≥$100/MWh for ≥250 MWe.
AAOI LOW catalyst due

Invalidates if Weekly close below the 20-week EMA on rising volume (trend kill on a +400% YTD parabola), OR photonics ETF (EUV) breaks below its launch base, OR a $600M ATM takedown disclosure followed by giving back the prior month's range on volume.
TSEM MEDIUM catalyst due

Invalidates if Weekly close back below the ~$255 May-13 earnings-gap base (failed post-beat breakout — verify exact 20-EMA before sizing), OR any Q2 guide walk-back / RF-SOI inventory-reset commentary from QCOM/AVGO. Either kills the acceleration thesis.
AEHR MEDIUM catalyst due

Invalidates if retry on next decision_window
ASTS MEDIUM catalyst due

Invalidates if retry on next decision_window
CRWV LOW catalyst due

Invalidates if Weekly close below the ~$104 post-Q1 low = base failed, opens DA Davidson $100 → Bernstein $67 air pocket. Or the new $850M data-center junk bond prices wider than the 9.75% notes (credit refusing the recovery), or a second cohort guide-down.
OKLO LOW catalyst due

Invalidates if Any further insider Form 4 sale or ATM/S-3/424B filing within 2 weeks of the 2026-06-03 $13.6M disclosure; or weekly close below the 2026-05-18 post-Q1 digestion low; or DOE plutonium negotiations (opened 5/26) lapsing.
QBTS LOW catalyst due

Invalidates if Daily close back below the ~$20 May-20 pre-announcement base = government-bet gap filled and failed. OR a new ATM/shelf take-down 8-K beyond the $100M Commerce issuance. OR QTUM ETF rolls over + the quantum cohort prints lower lows together (theme→DEAD).
RGTI LOW catalyst due

Invalidates if Weekly close back below the 2026-05-22 breakout pivot, OR any ATM-issuance 8-K filed during strength (historic basket top-tell), OR QBTS closing below its 20-EMA (basket leader rolls first).
ASML MEDIUM catalyst due

Invalidates if retry on next decision_window
NBIS MEDIUM catalyst due

Invalidates if retry on next decision_window
NNE LOW catalyst due

Invalidates if Daily close below ~$24 (loses the post-5/20 NRC base; closed $26.24 on 6/03), OR any 424B/8-K disclosure that the $400M ATM is selling into rallies — either confirms catalysts are priced and dilution is absorbing the move.
PL LOW catalyst due

Invalidates if Soft/missed Q1 print tonight (rev <~$84M or weak FY27 guide) → market-sell remainder; OR daily close below $42 (loses $42.48 breakout shelf); OR SpaceX ~6/12 debut prints sell-the-news and the cluster (RKLB/ASTS) rolls over.
QUBT LOW resolves today

Invalidates if Flip to interest ONLY on a weekly close back above the ~$13-14 200-DMA on a QUBT-specific catalyst (TFLN customer 8-K or direct federal award, or rule_7 options confirmation). Hard SKIP on any 424B5/S-3 ATM filing, or if the QNT IPO drains the sector bid and QUBT loses the ~$10 shelf.
SHLS LOW resolves in 13d

Invalidates if Daily close below the rising 20-EMA / May breakout base near $9.00; or repeated failure to reclaim $10 into 2026-06-18 opex (call sweep marked to zero), confirming the leg is dead.
TSLA LOW resolves in 13d

Invalidates if Confirmed SKIP if TSLA fails to reclaim its 2026-06-02 pre-gap high within ~2 weeks, or another Optimus/Robotaxi milestone slips. Re-engage only on a reclaim of that high paired with a dated robotics catalyst (Optimus milestone or Robotaxi weekly-rides inflection).
AMD MEDIUM resolves in 20d

Invalidates if retry on next decision_window
MU MEDIUM resolves in 20d

Invalidates if retry on next decision_window
UUUU MEDIUM resolves in 21d

Invalidates if Weekly close below $16 (mid-May swing low where the rebound began) on >2x avg vol; OR ASM scheme vote fails / deal terminated at the ~late-June 2026 close; OR NdPr rolls under ~$50/kg as China relaxes export controls; OR uranium spot holds <$78 for two consecutive weeks.
SYRE MEDIUM resolves in 25d

Invalidates if SPY002 mid-2026 induction readout misses (no stat-sig efficacy vs placebo or class-discordant safety), OR weekly close below $62 offering floor on >2x 20d avg vol, OR Merck tulisokibart / Roivant-Pfizer RVT-3101 prints superior anti-TL1A Phase 3 data eroding SPY002/SPY072 profile.
EWY MEDIUM resolves in 26d

Invalidates if Weekly close below ~$190 (early-June breakout base, -11% from [entry redacted]) breaks the parabolic leg; OR TrendForce flags Q3 2026 DRAM contract prices decelerating to flat/negative QoQ (cycle peak); OR the Samsung/Hynix AI-profit-redistribution proposal advances to actual legislation.
CCJ LOW resolves in 26d

Invalidates if Weekly close below $100 (under the ~$104 May low) on expanding volume, OR uranium spot under $80/lb, OR Q2 guide cut on the Key Lake/McArthur disruption. Failure to retake $115 (lower high instead) kills the reclaim entry.
IREN MEDIUM resolves in 27d

Invalidates if Weekly close back below the 2026-05-26 Dell/MSFT breakout base on >1.5x vol; OR disclosure of a Microsoft contract delay/descope; OR a new ATM equity raise >$300M priced below spot (signals the $3.65B IG debt was insufficient).
HUT HIGH no dated catalyst

Invalidates if a daily close below the thesis-invalidation level
RIOT HIGH no dated catalyst

Invalidates if a daily close below the thesis-invalidation level
TSM HIGH no dated catalyst

Invalidates if a daily close below the thesis-invalidation level
APLD MEDIUM no dated catalyst

Invalidates if Weekly close below 20-EMA (~$45) → trim 50%; daily close below $40 (2026-05-20 lease breakout shelf) on volume → trim further; daily close below [entry redacted] (cost basis, breakout-retest thesis dead) → exit full. Any 8-K disclosing an ATM/equity raise within 14d → trim 50% immediately regardless of price.
IONQ MEDIUM no dated catalyst

Invalidates if Weekly close below 20-EMA (refresh — prior [stop redacted] stop is stale, trail up). Q2 sequential revenue decline vs Q1 $64.67M or FY guide cut from [entry redacted]–270M. Or IONQ excluded from the $2B CHIPS equity-stake awards while peers are included (unwinds the 2026-05-26 pop).
AMSC LOW no dated catalyst

Invalidates if Weekly close below $40 (loses post-earnings shelf + April base pivot; opens path to 200-DMA / $24.87 low). Also dead if next print (est. early Aug) shows 12-mo backlog contracting from ~$280M or grid orders rolling over, or grid-power-transmission theme downgrades to SATURATED/DEAD.

How we're scored

A confident model is easy. A calibrated one is the point.

When a thesis resolves, it will be recorded here as played out or invalidated, dated, with a flag for whether the published trigger actually fired. As outcomes accumulate, the calibration question gets a public answer: does conviction predict the outcome — does SUPREME beat LOW, does a regime call hold? Strictly non-monetary: no entries, no returns, no P&L — only whether the falsifiable claim was falsified.

The odds each tier stakes · published in advance

SUPREME 90%
HIGH 75%
MEDIUM 60%
LOW 50%

Each tier claims this chance of playing out. Once theses resolve, the Brier score will measure the gap between these stated odds and reality.

What an invalidation trigger is Why trust it

Common questions

How is orbyd scored?: Every thesis ships with a published invalidation trigger. When it resolves it's marked played-out or invalidated — dated, with whether the trigger fired. Across resolved theses we compute a Brier score (forecasting accuracy) and break play-out rates out by conviction tier, so you can see whether SUPREME actually beats LOW. Strictly non-monetary.
What is a Brier score?: The mean squared error between the probability a conviction tier implies (SUPREME≈0.9 … LOW≈0.5) and the binary outcome. 0 is perfect, 0.25 is a coin flip. For reference, expert human Superforecasters score around 0.08 and the best LLMs around 0.10.
Do you publish returns or P&L?: No — never. The track record scores whether each falsifiable claim was falsified, not how a trade did. There are no returns, no P&L, no positions, no sizing anywhere on the site.
What happens when a thesis is wrong?: It's marked invalidated, dated, and kept on the public record — with whether the published trigger fired first. Being wrong in public, on the record, is the point: it's what makes the score trustworthy.