Scoreboard
Every pick, graded.
Each pick names the level that would prove it wrong before the outcome is known, then resolves in public: the thesis played out, or the line was hit and the pick closed. The score is whether the call held — not what it returned. Every resolution below carries the tier it staked, so the record is recomputable rather than asserted.
Calibration · 418 scored
418 resolutions · directionalReliability
0.010
±12pp on 412 of 418
Picks resolved
419
418 scored · 185 reached · 234 closed on their line
Base rate
44%
picks reaching their case
Brier score
0.255
vs 0.246 for staking the base rate every time
The sample is 418 resolved picks. That clears the ~30-outcome line where a forecasting record stops being noise, and is nowhere near large enough to settle skill. An individual tier row with a handful of outcomes carries wide error bars, and discrimination between tiers needs a larger sample to measure precisely. The figures are published as computed and sharpen as the record extends.
What a Brier score of 0.26 means
A Brier score is the mean squared error between the probability a forecast stakes and what actually happened. Each conviction tier carries an implied probability of playing out — since 27 August 2026: SUPREME 85%, HIGH 70%, MEDIUM 55%, LOW 40%; picks staked earlier keep the v1 odds they published (90/75/60/50) — and every resolved pick is graded against the odds its tier published in advance.
Read on its own the headline number is close to uninformative, because most of it is not a property of the forecaster at all. Under the Murphy decomposition a Brier score separates into reliability (0.010), resolution (0.001) and uncertainty (0.246). That last term is fixed by the question set: binary equity picks resolving at a 44% base rate carry an irreducible 0.246, which is exactly what a forecaster scores by staking that base rate on every pick and nothing more. It is the reference this record is read against — not a floor. A Brier score's floor is 0, and 0.255 sitting above 0.246 is what the negative skill score below states as a ratio. Comparing the raw figure against scores from geopolitical or general-knowledge forecasting compares base rates, not forecasters.
The two terms that do measure this desk are reliability and resolution. Reliability is a mean-squared term: the published 0.0100 is a weighted mean of SQUARED tier gaps, so its own percentage-point reading is its square root — 10pp RMS across every scored tier — and never 0.0100 read as a gap. That aggregate is dominated by whichever tier has fewest resolutions, which is why it is reported per tier instead. Across the conviction tiers carrying a meaningful sample (412 of 418 resolutions), stated confidence has tracked realised outcomes to within 12 percentage points. The remaining 6 sit in the HIGH tier, which is 53.3 points off its stated odds — too few outcomes to read as a rate, and the reason the aggregate reliability term is not a percentage-point gap. Every tier is listed below with its own count. Resolution at 0.001 is the open question: the tiers are honest about their own odds but do not yet pull outcomes far apart from the base rate, and separating those two properties takes more resolutions than 418.
The score is recomputable rather than asserted: the odds each tier stakes are fixed in advance, every resolved call is listed below with the tier it staked, and the arithmetic runs from the published record. One caveat stated plainly — a resolved pick is scored on the tier recorded when it was graded, and the research pipeline can restate a tier afterwards, which moves the figure with no new outcome behind it. Published resolutions are never restated to improve the score.
Does staking conviction beat the base rate yet?
Not measurably, at this sample size. The Brier skill score (−0.036) asks whether the conviction tiers carry information beyond simply forecasting the 44% base rate on every pick. It currently sits at the base-rate line, which is the same finding as the low resolution term above, expressed as a ratio. It is a statement about how far 418 resolutions can separate signal from noise, not a claim in either direction.
This is the distinction between a measured record and an asserted one. Research that retains its winners and quietly retires its losers can report any accuracy it chooses, because nothing was falsifiable at the outset. A figure computed over every resolved call — including the ones that hit their trigger — is one a reader can audit and recompute, which is what makes AI equity research checkable at all, and what an invalidation trigger exists to enable. Whether the record ultimately reflects skill or luck is a question this sample size cannot yet settle, and we publish the number that says so.
The Brier score, decomposed
0.010
Reliability: the gap between the play-out rate each tier claimed and the rate it actually hit. Lower is better.
0.001
Discrimination: how far the conviction tiers pull outcomes apart from the base rate. Higher is better; near zero means the tiers don't yet separate.
0.246
The irreducible difficulty of the question itself — the variance you'd face forecasting the base rate alone, before any conviction is staked.
These three sum to the headline figure: Brier = calibration − resolution + uncertainty. The split is the honest part. A low calibration term paired with a near-zero resolution term is exactly what a skill-≈0 record looks like — confidence that tracks reality reasonably well, but conviction tiers that don't yet sort the wins from the losses. The refinement term (0.245, uncertainty minus resolution) measures the same thing from the other side: how much sharper than the base rate the forecasts have managed to be so far.
Dashed = perfect calibration. Each dot is a conviction tier; the line shows the gap between what it claimed and what happened.
Does conviction predict the outcome?
| Tier | Claimed | Actual | n |
|---|---|---|---|
| HIGH | 70% | 17% | 6 |
| MEDIUM | 55% | 43% | 121 |
| LOW | 40% | 45% | 291 |
Play-out rate by archetype
- Compounder 42% · 43
- Cyclical recovery 39% · 76
- Theme leader 47% · 30
- Special situation 42% · 118
- Earnings inflection 47% · 89
- Retail squeeze 48% · 33
- Defensive 48% · 29
Play-out rate by regime at resolution
- Risk-on 51% · 272
- Risk-off 28% · 85
- Neutral 34% · 61
419 resolved · 418 scored — one pick staked no conviction tier, so it cannot be scored for calibration
Two ways a pick resolves — played out or invalidated. Both stay on the record. A pick that has reached neither its target nor its kill line is undecided and is not scored: of 942 published picks, 185 reached their case, 234 hit their line, and 523 are still undecided. 44.5% of published picks have reached a verdict — 419 of 942. How a pick resolves →
- CRWD MEDIUM Played out
- CVI MEDIUM Played out
- NAVN MEDIUM Invalidated kill line fired
- TARS MEDIUM Invalidated kill line fired
- AMR LOW Invalidated kill line fired
- BLSH LOW Played out
- BTCS LOW Played out
- IMRN LOW Invalidated kill line fired
- MSTR LOW Played out
- MXL LOW Played out
- QRVO LOW Played out
- SDGR LOW Played out
- SID LOW Invalidated kill line fired
- UPXI LOW Played out
- ABT MEDIUM Invalidated kill line fired
- ABX MEDIUM Invalidated kill line fired
- ALM MEDIUM Invalidated kill line fired
- CTRN MEDIUM Invalidated kill line fired
- CXT MEDIUM Invalidated kill line fired
- GERN MEDIUM Invalidated kill line fired
- IVA MEDIUM Invalidated kill line fired
- MNPR MEDIUM Invalidated kill line fired
- NWL MEDIUM Invalidated kill line fired
- RELY MEDIUM Invalidated kill line fired
- XGN MEDIUM Played out
- ZIP MEDIUM Invalidated kill line fired
- ACLS LOW Invalidated kill line fired
- ACMR LOW Invalidated kill line fired
- ALMS LOW Invalidated kill line fired
- AMBQ LOW Played out
- ATHM LOW Invalidated kill line fired
- CABA LOW Invalidated kill line fired
- CAL LOW Invalidated kill line fired
- CCXI LOW Invalidated kill line fired
- CERS LOW Played out
- CROX LOW Played out
- GFI LOW Invalidated kill line fired
- HROW LOW Invalidated kill line fired
- HTLD LOW Invalidated kill line fired
- JELD LOW Invalidated kill line fired
- KGS LOW Invalidated kill line fired
- KNX LOW Invalidated kill line fired
- LAR LOW Invalidated kill line fired
- LOVE LOW Invalidated kill line fired
- LRMR LOW Invalidated kill line fired
- MAMA LOW Invalidated kill line fired
- MAZE LOW Invalidated kill line fired
- MEDP LOW Played out
- REAX LOW Invalidated kill line fired
- RPAY LOW Played out
- RZLT LOW Invalidated kill line fired
- SLS LOW Invalidated kill line fired
- STAA LOW Invalidated kill line fired
- TENB LOW Played out
- TSHA LOW Invalidated kill line fired
- BMY MEDIUM Invalidated kill line fired
- COTY MEDIUM Invalidated kill line fired
- WDAY MEDIUM Played out
- FIGS MEDIUM Invalidated kill line fired
- LMND MEDIUM Invalidated kill line fired
- PMTS MEDIUM Invalidated kill line fired
- ODD LOW Played out
- CRAI MEDIUM Invalidated kill line fired
- CRDO MEDIUM Invalidated kill line fired
- DVA MEDIUM Played out
- DYN MEDIUM Invalidated kill line fired
- HUBS MEDIUM Invalidated kill line fired
- MCS MEDIUM Invalidated kill line fired
- OWL MEDIUM Invalidated kill line fired
- USO MEDIUM Played out
- ABEO LOW Invalidated kill line fired
- APH LOW Played out
- AXTI LOW Played out
- BHC LOW Invalidated kill line fired
- BIDU LOW Invalidated kill line fired
- ELVR LOW Invalidated kill line fired
- ENOV LOW Invalidated kill line fired
- ERAS LOW Invalidated kill line fired
- GSM LOW Played out
- HOV LOW Invalidated kill line fired
- HURN LOW Invalidated kill line fired
- KMTS LOW Invalidated kill line fired
- LITE LOW Played out
- MANH LOW Invalidated kill line fired
- SRAD LOW Played out
- VSXY LOW Invalidated kill line fired
- UUUU LOW Invalidated kill line fired
- CERT MEDIUM Invalidated kill line fired
- SMTC LOW Played out
- SANM LOW Played out
- TAL LOW Played out
- XOS LOW Invalidated kill line fired
- SMRT MEDIUM Invalidated kill line fired
- SEER LOW Invalidated kill line fired
- WHD LOW Played out
- FTNT MEDIUM Played out
- PLPC MEDIUM Invalidated kill line fired
- SPXC MEDIUM Invalidated kill line fired
- TEAM MEDIUM Played out
- BMNR LOW Played out
- ESTC LOW Played out
- MAN LOW Played out
- ADBE MEDIUM Played out
- AKAM MEDIUM Invalidated kill line fired
- ALAB MEDIUM Invalidated kill line fired
- ANDG MEDIUM Played out
- AUR MEDIUM Invalidated kill line fired
- BHE MEDIUM Invalidated kill line fired
- DGII MEDIUM Invalidated kill line fired
- ENTG MEDIUM Invalidated kill line fired
- FSLR MEDIUM Invalidated kill line fired
- MEI MEDIUM Played out
- PENN MEDIUM Invalidated kill line fired
- TTMI MEDIUM Invalidated kill line fired
- ULCC MEDIUM Invalidated kill line fired
- AAON LOW Invalidated kill line fired
- AIP LOW Invalidated kill line fired
- ALNT LOW Invalidated kill line fired
- AVR LOW Invalidated kill line fired
- BKSY LOW Invalidated kill line fired
- FCEL LOW Invalidated kill line fired
- GFS LOW Invalidated kill line fired
- GTM LOW Played out
- HIMS LOW Invalidated kill line fired
- NP LOW Played out
- POWL LOW Invalidated kill line fired
- RH LOW Invalidated kill line fired
- TGTX LOW Played out
- VIR LOW Played out
- VPG LOW Invalidated kill line fired
- CRM MEDIUM Played out
- CYRX MEDIUM Played out
- FA MEDIUM Invalidated kill line fired
- FTK MEDIUM Invalidated kill line fired
- PCTY MEDIUM Played out
- MPC LOW Played out
- COHU MEDIUM Played out
- CTOS MEDIUM Invalidated kill line fired
- MIRM MEDIUM Invalidated kill line fired
- SPSC MEDIUM Played out
- WEX MEDIUM Played out
- WIX MEDIUM Played out
- CRS LOW Invalidated kill line fired
- CSCO LOW Invalidated kill line fired
- CVLG LOW Played out
- DUOT LOW Played out
- EPAM LOW Played out
- EXFY LOW Played out
- G LOW Played out
- GLUE LOW Invalidated kill line fired
- ICHR LOW Invalidated kill line fired
- IHRT LOW Invalidated kill line fired
- IQ LOW Invalidated kill line fired
- MKSI LOW Invalidated kill line fired
- OEC LOW Invalidated kill line fired
- SAH LOW Invalidated kill line fired
- TASK LOW Played out
- TH LOW Played out
- TIC LOW Played out
- TLN LOW Invalidated kill line fired
- TSAT LOW Invalidated kill line fired
- UCTT LOW Invalidated kill line fired
- CRWV MEDIUM Invalidated kill line fired
- ARM LOW Invalidated kill line fired
- INTC LOW Invalidated kill line fired
- CMCO MEDIUM Invalidated kill line fired
- JWEL LOW Invalidated kill line fired
- KC LOW Invalidated kill line fired
- VLO MEDIUM Played out
- KURA LOW Played out
- RHI LOW Played out
- RUM LOW Played out
- MRX HIGH Played out
- CGEM MEDIUM Played out
- KEYS MEDIUM Played out
- PRGS MEDIUM Played out
- PTGX MEDIUM Played out
- RAPP MEDIUM Played out
- SE MEDIUM Played out
- VG MEDIUM Played out
- ASX LOW Played out
- BCAX LOW Invalidated kill line fired
- BTE LOW Played out
- BTGO LOW Played out
- BWIN LOW Played out
- EQNR LOW Played out
- GENI LOW Played out
- GTX LOW Invalidated kill line fired
- IMRX LOW Played out
- KLC LOW Invalidated kill line fired
- MTUM LOW Played out
- NWPX LOW Invalidated kill line fired
- PBI LOW Invalidated kill line fired
- WLFC LOW Invalidated kill line fired
- WSC LOW Invalidated kill line fired
- CGC LOW Played out
- SATL LOW Played out
- PANL LOW Invalidated kill line fired
- HTZ MEDIUM Played out
- BBBY LOW Invalidated kill line fired
- DJT LOW Invalidated kill line fired
- EVC LOW Invalidated kill line fired
- ORKA MEDIUM Played out
- FBIN LOW Invalidated kill line fired
- MGM LOW Invalidated kill line fired
- TORO LOW Played out
- UMC LOW Invalidated kill line fired
- GHRS MEDIUM Played out
- SENS LOW Played out
- WEAV LOW Invalidated kill line fired
- WGS LOW Played out
- ACIW MEDIUM Invalidated kill line fired
- AMBA MEDIUM Played out
- BBAR MEDIUM Invalidated kill line fired
- CCC MEDIUM Played out
- ELF MEDIUM Played out
- HRI MEDIUM Played out
- NKTR MEDIUM Played out
- PGEN MEDIUM Played out
- RRGB MEDIUM Played out
- YETI LOW Played out
- ZBIO LOW Played out
- AAPL LOW Invalidated kill line fired
- AEIS LOW Played out
- AGX LOW Played out
- AKBA LOW Invalidated kill line fired
- AOSL LOW Played out
- ATEN LOW Invalidated kill line fired
- BRKR LOW Invalidated kill line fired
- BROS LOW Invalidated kill line fired
- CHYM LOW Played out
- COMP LOW Played out
- DDD LOW Played out
- DDOG LOW Invalidated kill line fired
- FOUR LOW Invalidated kill line fired
- FRD LOW Played out
- GGAL LOW Invalidated kill line fired
- GOLF LOW Invalidated kill line fired
- LILAK LOW Played out
- LUNR LOW Played out
- LZ LOW Invalidated kill line fired
- MDB LOW Played out
- MSFT LOW Played out
- NNE LOW Played out
- ODFL LOW Invalidated kill line fired
- OKLO LOW Played out
- ORIC LOW Played out
- PAY LOW Played out
- QURE LOW Played out
- RDW LOW Played out
- SABR LOW Played out
- SHOO LOW Played out
- SITM LOW Played out
- SVV LOW Played out
- TBI LOW Played out
- TNDM LOW Played out
- UI LOW Played out
- VECO LOW Played out
- XRX LOW Played out
- WDC LOW Invalidated kill line fired
- FLY LOW Played out
- HELP LOW Played out
- ZVRA LOW Played out
- FIG LOW Played out
- RXO MEDIUM Invalidated kill line fired
- STX LOW Played out
- MYGN LOW Invalidated kill line fired
- SMCI LOW Played out
- NXT LOW Invalidated kill line fired
- PRCH MEDIUM Played out
- RMAX MEDIUM Invalidated kill line fired
- SNDX MEDIUM Invalidated kill line fired
- VCYT MEDIUM Invalidated kill line fired
- ALHC LOW Invalidated kill line fired
- AMKR LOW Invalidated kill line fired
- CAKE LOW Played out
- CDW LOW Played out
- EVH LOW Invalidated kill line fired
- FN LOW Invalidated kill line fired
- IART LOW Invalidated kill line fired
- JACK LOW Played out
- KSS LOW Played out
- M LOW Played out
- MTRN LOW Invalidated kill line fired
- MYE LOW Played out
- NEO LOW Played out
- NOK LOW Invalidated kill line fired
- NSIT LOW Played out
- NUTX LOW Invalidated kill line fired
- ON LOW Invalidated kill line fired
- OUST LOW Played out
- PI LOW Played out
- RBLX LOW Invalidated kill line fired
- UNIT LOW Invalidated kill line fired
- VICR LOW Invalidated kill line fired
- VERU LOW Invalidated kill line fired
- MRCY MEDIUM Played out
- FROG MEDIUM Invalidated kill line fired
- TWLO MEDIUM Invalidated kill line fired
- BB MEDIUM Invalidated kill line fired
- W LOW Invalidated kill line fired
- XXI LOW Invalidated kill line fired
- ALGT HIGH Invalidated kill line fired
- AMC LOW Played out
- AFRM MEDIUM Invalidated kill line fired
- BAND LOW Invalidated kill line fired
- CLS MEDIUM Invalidated kill line fired
- CORT LOW Played out
- ENPH LOW Invalidated kill line fired
- MMYT LOW Invalidated kill line fired
- RARE LOW Invalidated kill line fired
- SANA LOW Invalidated kill line fired
- SPRY LOW Invalidated kill line fired
- PANW HIGH Invalidated kill line fired
- AGYS LOW Invalidated kill line fired
- BULL MEDIUM Played out
- PLUG LOW Played out
- HIVE LOW Invalidated kill line fired
- MARA MEDIUM Invalidated kill line fired
- BFLY MEDIUM Invalidated kill line fired
- FORM MEDIUM Invalidated kill line fired
- KMX LOW Played out
- BBY LOW Played out
- CIEN LOW Invalidated kill line fired
- CLPT LOW Invalidated kill line fired
- FWRD LOW Played out
- GCO LOW Played out
- JOBY LOW Invalidated kill line fired
- KOS LOW Played out
- LEGN LOW Invalidated kill line fired
- PDFS LOW Invalidated kill line fired
- RMBS LOW Invalidated kill line fired
- SAIL LOW Played out
- STM LOW Invalidated kill line fired
- STUB LOW Invalidated kill line fired
- TMC LOW Invalidated kill line fired
- VSH LOW Invalidated kill line fired
- WING LOW Invalidated kill line fired
- EXTR LOW Invalidated kill line fired
- PD LOW Played out
- MRVL MEDIUM Invalidated kill line fired
- KFRC LOW Played out
- NVDA MEDIUM Played out
- IMOS MEDIUM Played out
- OXM LOW Played out
- BTDR LOW Invalidated kill line fired
- FLEX LOW Invalidated kill line fired
- FPS LOW Invalidated kill line fired
- KALU LOW Invalidated kill line fired
- KEEL MEDIUM Invalidated kill line fired
- LGN LOW Invalidated kill line fired
- MTSI MEDIUM Invalidated kill line fired
- NEXA LOW Played out
- VIAV LOW Invalidated kill line fired
- PNRG LOW Played out
- PENG LOW Played out
- MTH LOW Invalidated kill line fired
- CLSK MEDIUM Invalidated kill line fired
- AESI LOW Invalidated kill line fired
- ATI MEDIUM Invalidated kill line fired
- KYMR NONE Played out
- LRCX MEDIUM Invalidated kill line fired
- ONTO HIGH Invalidated kill line fired
- TNGX MEDIUM Invalidated kill line fired
- TSM HIGH Invalidated kill line fired
- MYRG HIGH Invalidated kill line fired
- AMN LOW Played out
- AMSC LOW Invalidated kill line fired
- BTBT LOW Invalidated kill line fired
- CCJ LOW Invalidated kill line fired
- HUT LOW Invalidated kill line fired
- ALTO LOW Played out
- SXC LOW Invalidated kill line fired
- SYRE LOW Invalidated kill line fired
- FAC LOW Played out
- PSNL MEDIUM Played out
- ADPT MEDIUM Played out
- SHLS LOW Played out
- RGTI LOW Invalidated kill line fired
- CEVA MEDIUM Invalidated kill line fired
- TLRY LOW Invalidated kill line fired
- NBR LOW Invalidated kill line fired
- QUIK LOW Invalidated kill line fired
- NBIS LOW Invalidated kill line fired
- OKTA MEDIUM Invalidated kill line fired
- SNOW LOW Invalidated kill line fired
- DXCM MEDIUM Invalidated kill line fired
- HNGE LOW Played out
- MGTX MEDIUM Played out
- FIVN LOW Invalidated kill line fired
- PTEN LOW Invalidated kill line fired
- PRM MEDIUM Played out
- ALGM LOW Played out
- AUGO LOW Played out
- CDNL LOW Played out
- CECO MEDIUM Played out
- IPX LOW Invalidated kill line fired
- JBLU MEDIUM Played out
- MCHP LOW Played out
- PCT LOW Invalidated kill line fired
- STRO LOW Played out
- TER MEDIUM Played out
- ZETA LOW Invalidated kill line fired
- BLZE MEDIUM Played out
- OPEN LOW Played out
- RVMD MEDIUM Played out
- TBLA LOW Played out
- DIOD LOW Played out
- MRAM LOW Played out
- POWI MEDIUM Played out
- TRVI LOW Played out
- TWST LOW Played out
- DRTS MEDIUM Played out
- AZZ LOW Played out
- INDI LOW Invalidated kill line fired
- CLFD LOW Invalidated kill line fired
- INOD LOW Invalidated kill line fired
- QCOM MEDIUM Invalidated kill line fired
- PURR LOW Invalidated kill line fired
Open commitments · 158 · soonest to resolve first
Every pick on the active book — held, watchlist or rotation — that ships a published, falsifiable kill line. This is not the full scored set: a name we've stopped actively tracking keeps its published line on its own dossier and still resolves into the record above if that line fires, it just doesn't sit on this board. Distinct from the names held on the live book and the forward theme-bets scored on their own board.
-
Kill line A weekly close below $118 invalidates the recovery price structure; separately, Q3 2026 sales below $2.3 billion or adjusted EPS below $0.85 would break the earnings-trough assumption embedded in AGCO's 2026-07-30 guidance.
-
Kill line A weekly close below $9.00 ends the price-confirmed Matrix-M re-rating thesis; separately, the 2026-09-09 and 2026-09-10 conferences passing without company-confirmed Sanofi Phase 3 initiation timing ends the near-term catalyst case.
-
Kill line A weekly close below $107 invalidates the September repricing thesis by returning the market toward the 2026-09-02 pre-jump close of $106.99.
-
Kill line A weekly close below $12.50 invalidates the September re-rating leg; the reference is Evercore's 2026-08-11 analyst target. Separately, FY2026 agriculture adjusted EBIT margin guidance below 5.0% or adjusted diluted EPS guidance below $0.41 breaks the earnings foundation.
-
Kill line A weekly close below $23 invalidates the cycle-bottom re-rating; independently, next-quarter total inventory above $931.5 million or a cut to fiscal 2027 adjusted EBITDA guidance of $17 million–$29 million breaks the operating recovery case.
-
Kill line A daily close below $40.50 invalidates the completion-before-price-deterioration thesis. A disclosed merger termination, failed shareholder vote or financing failure preventing completion independently breaks the transaction case.
-
Kill line A weekly close below $4.47, the historical 200-day moving-average reference reported on 2026-09-04, breaks the recovery thesis; separately, 2026-09-30 passing without an announced Anaphylm NDA resubmission invalidates the timing premise.
-
Kill line A weekly close below $13.73, the August 28, 2026 reference close, invalidates the renewed September price thesis. A company-announced NDA completion delay beyond Q4 2026 separately breaks the regulatory timetable.
-
Kill line A weekly close below $1.75 ends the enrollment-led re-rating thesis; separately, 2026-09-30 passing without confirmation of MAVERIC target enrollment breaks its execution deadline.
-
Kill line A weekly close below $20.00, the public offering price announced on 2026-06-29, invalidates the market thesis; separately, 2026-12-31 passing without announced US IND submissions for both NXP100 and NXP200 leaves the execution case unmet.
-
Kill line A weekly close below $8.50 invalidates the continuation case tied to the 2026-08-13 trial clearance; a company disclosure that AURORA screening did not begin during October 2026 separately breaks the operating schedule.
-
Kill line A weekly close below $17 breaks the $17.05 shelf reclaimed after the 2026-08-03 results; separately, third-quarter revenue declining more than the guided 1–2% sequentially or a cut to the $231–233 million fiscal-2026 outlook invalidates the operating case.
-
Kill line A weekly close below $19 invalidates the recovery price case; failure to release the guided DM1 and FSHD cohort updates by 2026-12-31 separately invalidates the clinical timetable.
-
Kill line A weekly close below $6.70 breaks the post-Q2 price structure; 2026-10-14 passing without the promised VS-7375 efficacy disclosure separately invalidates the scheduled-catalyst premise.
-
Kill line A weekly close below $12.50 invalidates the July–August recovery structure retained from the 2026-08-30 research note; company confirmation that DME Phase 3 did not start within Q3 2026 separately breaks the timely-execution premise.
-
Kill line A weekly close below $11.00 ends the market case; secondary invalidation is an expanded-cohort CR rate below the 2026-05-21 reported 95%, a disclosed treatment-related death or clinical hold, or no clinical update by 2026-09-30.
-
Kill line A weekly close below $4.40 breaches the market threshold published on 2026-09-07; independently, another manufacturing-related FDA rejection for AVT05 or AVT06, or a disclosed delay beyond Q4 2026, breaks the regulatory-repair thesis.
-
Kill line A weekly close below $98 invalidates the price-continuation thesis, retaining the research boundary published on 2026-09-05. Separately, a reduction in the 2026-08-06 full-year royalty guidance of $1.220–1.245 billion would break the operating premise.
-
Kill line A weekly close below $290 breaks the reclaimed post-Q2 shelf identified in the 2026-08-29 public analysis. A Q3 revenue result below the $736 million guidance floor would separately contradict the commercial case.
-
Kill line A weekly close below $7.50 invalidates the discount-closure recovery thesis; this retains the published research threshold beneath the market's $7.91 weekly close on 2026-08-21 and $8.20 weekly close on 2026-08-28.
-
Kill line A weekly close below $2.97 before a weekly close above $3.01 invalidates the near-term continuation thesis; $2.97 is the September 11, 2026 adjusted daily reference close, not a verified support shelf.
-
Kill line A weekly close below $3.82 breaks the 2026-08-17 Lilly-announcement reference and ends the re-rating thesis; full-year revenue guidance remaining at or below $36 million at the next results fails the fundamental test.
-
Kill line A weekly close below $58 breaks the pre-catalyst shelf identified in the September 5 published dossier and invalidates the recovery thesis; termination of the Personalis merger would separately remove its proposed commercial route.
-
Kill line A weekly close below $47 invalidates the reclaimed August breakout structure. Separately, September-quarter reported TCE at or below the June quarter’s $75,926 per available day defeats the record-quarter earnings case.
-
Kill line A weekly close below $93 ends the thesis, placing the market beneath the $97.32 shelf identified on 2026-08-21; sequentially lower adjusted refinery gross margin on comparable throughput would also contradict the operating case.
-
Kill line A weekly close below $64 breaks the August breakout structure; separately, Q3 throughput below 296,000 barrels per day, operating expenses above $230 million, or an optimization run-rate objective reduced below $220 million invalidates the operating case.
-
Kill line A weekly close below $40 breaks the August shelf identified in the 2026-09-04 public note; separately, company guidance moving Skouries commercial production into 2027 invalidates the operating schedule.
-
Kill line A weekly close below $11.00 before a weekly close above $13.66 invalidates the equity recovery thesis; second-half 2026 AISC at or above $2,157 per gold equivalent ounce would separately contradict management’s cost-improvement forecast.
-
Kill line A weekly close below $18.50 ends the margin-expansion case, retaining the research threshold published on 2026-09-04. An increase in 2026 all-in sustaining cost guidance above the maintained $2,000–$2,150 per-ounce range would independently contradict the operating premise.
-
Kill line A weekly close below $75.48 reverses the breakout above the adjusted series’ former 52-week high reported on 2026-09-04; Q3 adjusted earnings below the Q2 result of $6.22 per share would independently reject the earnings case.
-
Kill line A weekly close below $239 ends the continuation thesis; the reference is Wells Fargo’s 2026-08-06 analyst target, not verified chart support. Q3 realized refining margin below $24.08 per barrel would separately fail the operating persistence test.
-
Kill line A weekly close below $5 ends the recovery thesis retained from the 2026-08-30 public note; independently, Q3 revenue below the $1.70 billion guidance floor invalidates the operating continuation claim.
-
Kill line A weekly close below $33 ends the post-divestiture re-rating thesis, retaining the research boundary published on 2026-09-04. A reduction below the 450,000-ounce lower end of FY2026 production guidance would separately undermine the operating case.
-
Kill line A weekly close below $5.80 invalidates the continuation case; this published research threshold coincides with Goldman Sachs’ 2026-08-26 target. Confirmed termination of the Ipiranga sale process without agreement separately breaks the transaction leg.
-
Kill line A weekly close below $30 invalidates the published momentum thesis; this condition was met on 2026-09-11 at $29.80. Separately, a disclosed GS-1179 Phase 2 delay into 2027 would invalidate the year-end development timetable.
-
Kill line A daily close below $95 invalidates the published breakout thesis; the 2026-09-09 adjusted close of $92.99 already met this condition. Independently, Arc remaining unavailable to the public after 2026-09-16 invalidates the launch premise.
-
Kill line A weekly close below $73 invalidates the continuation thesis by losing the September 11, 2026 reference close; this is a published price test, not a verified historical support shelf.
-
Kill line A weekly close below $10.93 breaks the recovery anchored to the 2026-08-21 market close; secondary fundamental invalidation is Q3 FY26 revenue below the $320 million guidance floor or Components & Systems gross margin below Q2's 26.3%.
-
Kill line A weekly close below $40 ends the market thesis at the research boundary published on 2026-09-04; fiscal fourth-quarter North America direct margin below the $245 million guidance floor independently breaks the operating case.
-
Kill line A weekly close below $9.50 breaks the recovery structure beneath the market's 2026-08-17 range of $9.53–9.96; Q3 revenue at or below management's $123.3 million guidance floor or non-GAAP operating income below its $17.5 million guidance floor would reject operating confirmation.
-
Kill line A weekly close below $49.21 on the adjusted daily-price series invalidates retention of the 2026-09-11 high; third-quarter achieved daily earnings for very large crude carriers below the second-quarter $152,700 benchmark also reject the earnings-persistence case.
-
Kill line A weekly close below $9.38 invalidates continuation above the 2026-09-11 adjusted high; Q3 average time charter equivalent earnings below the disclosed $30,716 per day booking reference would separately fail the operating test.
-
Kill line A weekly close below $456 breaks the pre-results structure beneath the August 31, 2026 close of $456.01. A reduction in the roughly $19 billion next-quarter AI-server revenue outlook, a reported shortfall, or ISG operating margin below 15.0% independently defeats the operating thesis.
-
Kill line A weekly close below $47 invalidates the September announcement leg. Separately, a reduction in fiscal 2026 revenue guidance below the $602 million lower bound issued on 2026-07-23 would break the operating rationale.
-
Kill line A weekly close below $195 invalidates the recovery above the $200 shelf reclaimed on 2026-09-02. Secondary failure conditions are Q3 2026 revenue below the $494 million guidance floor or a reduction of the $3.6 billion 2028 revenue framework published on 2026-07-14.
-
Kill line A weekly close below $230 breaks the recovery structure beneath the August 13, 2026 shelf at $238.51 and September 3 session low near $231.51. Reported third-quarter 2026 revenue below management's July 30 guidance floor of $519 million independently defeats the operating case.
-
Kill line A weekly close below $85.31 invalidates the published spectrum-conversion thesis; the 2026-09-18 adjusted close of $76.99 has already satisfied this condition.
-
Kill line A weekly close below $91 invalidates the August CSL-disclosure gap structure near the 2026-08-14 close of $90.80; secondarily, the November 2026 results call providing neither a quantified positive fiscal 2027 CSL revenue contribution nor a center-transition timetable breaks the near-term monetization thesis.
-
Kill line A weekly close below $44 invalidates the post-July earnings re-rating thesis; withdrawal of the 20–25% FY2026 adjusted EPS growth outlook issued on 2026-07-30 would independently break the operating case.
-
Kill line A weekly close below $6.84 loses the 2026-08-04 post-results reference close; separately, Q3 results estimated for 2026-11-03 that leave FY2026 revenue guidance at $94–96 million or lower, or report net dollar retention below 110%, invalidate the operating case.
-
Kill line A weekly close below $5.00 breaks the consolidation beneath the 2026-08-21 low of $5.05; a reduction in the FY2026 organic-growth or adjusted-gross-margin outlook issued on 2026-08-05 separately invalidates the operating premise.
-
Kill line A weekly close below $545 breaks the structural threshold published on 2026-09-03; alternatively, the 2026-10-28 results passing without disclosed external AI revenue, an annualised revenue run rate or a signed external contract value ends the dated monetisation case.
-
Kill line A weekly close below $43.50 invalidates the merger-premium structure near the market’s $43.52 pre-announcement close on 2026-06-26; formal termination, certified shareholder rejection or a final order blocking completion separately ends the acquisition thesis.
-
Kill line A weekly close below $58.57 breaks the August shelf retained in the September 11, 2026 analysis; deferral of the disclosed second-half Atera shipment plan into 2027 would separately undermine the operating case.
-
Kill line A weekly close below $358 invalidates the published recovery case; the September 18, 2026 close of $337.82 has met that condition. A reduction below the August 5 full-year operating-revenue guidance floor of $725 million separately breaks the operating premise.
-
Kill line A weekly close below $255 invalidates the September price structure. Separately, fiscal Q3 adjusted diluted EPS below management's $4.25 guidance floor in the 2026-09-24 results breaks the earnings-transmission thesis.
-
Kill line A weekly close below $47 invalidates the re-rating thesis; a disclosed increase above the $137 million remaining-capital plan, a tie-in delayed into 2027, or year-end 2026 annual SAF production at or below 80 million gallons also breaks the operating case.
-
Kill line A weekly close below $35 breaks the recovery structure anchored by the 2026-08-28 market close of $35.45. Separately, postponement of the 2026-12-31 deadline or operating ARR below management’s $4 billion target for that date defeats the conversion case.
-
Kill line A weekly close below $58 invalidates the post-August-results price structure. Separately, Q3 2026 FILSPARI US net sales at or below $141.1 million or patient start forms at or below 2,012 would fail the commercial continuation test.
-
Kill line A weekly close below $4.60 ends the recovery thesis at its previously published price boundary; fiscal 2026 revenue below $1.015 billion or adjusted earnings per share below $1.80 would separately break the operating case.
-
Kill line A weekly close below $6.00 invalidates the recovery structure identified on 2026-09-06. Separately, fiscal-year comparable-sales guidance worse than an 8.0% decline or an adjusted EBITDA loss outlook exceeding $27 million contradicts stabilization.
-
Kill line A daily close below $35.08 ends the continuation thesis by losing the 2026-09-11 adjusted reference close and 52-week high; this is a momentum condition, not an established support shelf.
-
Kill line A weekly close below $62 breaks the August price structure and falls below the August 14, 2026 reference close of $62.28. Q2 FY2027 net subscriber additions below 142,472 would separately reject repetition of the July-reported record pace.
-
Kill line A weekly close below $48 breaks the retained July-repricing boundary; a reduction in the approximately $5.38 full-year adjusted earnings-per-share outlook at the 2026-10-27 results independently contradicts the operating premise.
-
Kill line A weekly close below $52 invalidates the post-results re-rating thesis; independently, Q3 2026 product revenue below Q2’s reported $37.568 million or reduced guidance for 2026 revenue above $145 million breaks the operating case.
-
Kill line A weekly close below $17.25, the common-stock offering price announced on 2026-09-15, invalidates the renewed market thesis; full U.S. Mint commercialization slipping beyond Q1 2027 independently breaks the launch case.
-
Kill line A weekly close below $19 ends the price-repair thesis at the threshold retained from the 2026-09-06 research note. A further cut in annual gold guidance below 630,000 ounces or copper below 40 million pounds separately breaks the operating premise.
-
Kill line A weekly close below $164 breaks the recovery thesis; fiscal-Q2 revenue below $2.025 billion, non-GAAP gross margin below 67.0%, or a reduction to the annual revenue outlook issued on 2026-09-02 independently invalidates the operating case.
-
Kill line A weekly close below $135.66 breaks the 2026-08-24 through 2026-09-01 compression floor and invalidates September's price repair. Failure to obtain regulatory acceptance in time for PJM's proposed 2026-09-30 opening separately invalidates the near-term catalyst case.
-
Kill line A weekly close below $50 invalidates the earnings-repricing thesis; a reduction in management's fiscal 2027 revenue-growth framework of 13–17%, announced on 2026-09-02, separately breaks the fundamental premise.
-
Kill line A weekly close below $958 breaks the rebound threshold published on 2026-09-10. Secondary failure: September 30 revenue below June's $50.0 billion ±$1.0 billion guidance range or adjusted gross margin below 86%.
-
Kill line A weekly close below $1400 ends the August recovery thesis, retaining the research threshold published on 2026-08-30; fiscal Q1 2027 revenue below $10.3 billion or non-GAAP gross margin below 83% separately breaks the operating case.
-
Kill line A daily close below $130 was the historical acquisition-thesis break condition. The final supplied close was $135.07 on 2026-09-02; completion on 2026-09-03 and Nasdaq suspension on 2026-09-04 leave no prospective APGE close to grade.
-
Kill line A weekly close below $50 invalidates the merger-completion thesis; transaction termination or failure to complete by 2026-12-31 independently defeats the stated timetable case.
-
Kill line A daily close below $118 invalidates the completion thesis; a disclosed termination or company announcement moving completion beyond year-end 2026 would independently contradict the case.
-
Kill line A weekly close below $210 invalidates the re-rating thesis; separately, the next quarterly report showing outstanding volume above $37.2 billion but net effective spread at or below $117.4 million would break the earnings-conversion case.
-
Kill line A weekly close below $12.00 invalidates the continuation thesis; a reduction of FY2026 adjusted FFO guidance below $1.28 per share or RevPAR growth guidance below 1.5% would separately break the operating case.
-
Kill line A weekly close below $31 invalidates the price thesis; independently, no additional completed facility sale by the Q3 2026 report, provisionally ~2026-11-04, ends the next-sale case, as would loss of a management contract at a sold facility.
-
Kill line A weekly close below $28 invalidates the contract-activation price leg, retaining the research threshold published on 2026-09-05. A disclosed delay beyond year-end 2026 or cancellation at Big Horn or Rivers separately breaks the operating thesis.
-
Kill line A weekly close below $16.00 ends the recovery thesis before a weekly close above $19.24; separately, Q3 revenue below $1,105 million or adjusted EPS below $0.22 would miss the lower bounds of the 2026-08-10 guidance.
-
Kill line A weekly close below $146.15 loses the market’s 2026-08-12 closing peak and invalidates the breakout thesis. A disclosed failure to meet the reported 2026-09-30 Google capacity deadline or begin the new contract on 2026-12-01 breaks the corresponding delivery claim.
-
Kill line A weekly close below $1.60 ends the recovery thesis at the research threshold published on 2026-09-06; a COVALENT-211 primary-endpoint failure or a delay beyond Q1 2027 also breaks the clinical case.
-
Kill line A weekly close below $48 ends the recovery-price thesis; Q3 average paid worksite employees below 305,500 or a full-year adjusted EBITDA guidance floor below $185 million would separately invalidate the operating case.
-
Kill line A weekly close below $11.50 invalidates the August re-rating thesis. Separately, a reported active-program count at or below 160 for 2026-09-30 breaks the operating case against management’s 165–170 guidance.
-
Kill line A weekly close below $134.45 invalidates the published rebound thesis; this condition was met by the $128.73 close on 2026-09-18. A Q3 2026 adjusted Asset-Based operating ratio above 90.8% would separately fail the margin-preservation test.
-
Kill line A weekly close below $185 invalidates the September price thesis; the 2026-09-18 close of $174.25 has met that condition. Separately, a Q3 2026 adjusted less-than-truckload operating ratio of 81% or higher would fail management's 2026-07-30 guidance.
-
Kill line A weekly close below $9.75 breaches the 2026-08-12 offering reference and ends the post-readout price thesis; a company disclosure contradicting the reported efficacy endpoints or pausing ABCL635 development for safety independently breaks the clinical case.
-
Kill line A weekly close below $11.62 breaks the recovery above the 2026-08-28 adjusted close. Negative third-quarter free cash flow would separately contradict the operating thesis anchored in the 2026-07-23 results.
-
Kill line A weekly close below $18 invalidates the crane-order re-rating; a secondary break is Q3 backlog below the $1,050.1 million Q2 mark or a reduction in the $150–170 million 2026 adjusted EBITDA guidance issued on 2026-08-06.
-
Kill line A weekly close below $16.00 invalidates the retained September price boundary. Separately, Q3 2026 net product sales at or below Q2’s $28.5 million contradict the sequential-growth thesis, especially if ordering accounts exceed the 73 reported at 2026-06-30.
-
Kill line A weekly close below $30 ends the post-readout market thesis; separately, submission guidance moving into 2027 or no announced avexitide NDA submission by 2026-12-31 breaks the regulatory timetable.
-
Kill line A daily close below $17.50 invalidates the completion-price thesis, retaining the research threshold published on 2026-09-03; it does not by itself establish that the merger has terminated.
-
Kill line A weekly close below $160 breaks the August recovery structure, undercutting the 2026-08-19 gap-bottom close of $160.20; third-quarter subscription-and-services revenue below the $500 million guidance floor separately invalidates the operating leg.
-
Kill line A weekly close below $15 invalidates the post-Q2 price-recovery thesis; independently, Q3 2026 reported revenue below the $916.3 million guidance floor or adjusted EBITDA margin below management's guided low-2% range breaks the operating case.
-
Kill line A weekly close below $65 invalidates the remaining margin-recovery price structure. Independently, Q3 insurance cost ratio at or above 89.5%, higher FY insurance-cost guidance, or FY revenue guidance below $4.75 billion breaks the fundamental case.
-
Kill line A weekly close below $44 invalidates the price structure supporting the enrollment-timeline thesis. Independently, no NANOPULSE-AF enrollment-completion announcement by 2026-10-31 invalidates schedule delivery.
-
Kill line A weekly close below $44 ends the post-earnings consumption thesis; fiscal Q3 revenue below the $281 million guidance floor announced on 2026-09-01 would independently break the operating case.
-
Kill line A weekly close below $88 invalidates the merger-completion price structure; a disclosed termination or definitive regulatory prohibition independently ends the case.
-
Kill line A weekly close below $68 breaks the published post-results support threshold; separately, Q3 net interest margin below 3.78% or pre-tax pre-provision earnings below $19.8 million invalidates operating continuation.
-
Kill line A weekly close below $4.95 ends the re-rating thesis by losing the March repurchase shelf identified in the 2026-09-07 assessment. Separately, a subsequent treasury disclosure below 0.0754 SOL per fully diluted share breaks the accumulation leg.
-
Kill line A weekly close below $24.08 before a weekly close at or above BTIG's September 9 target of $25 ends the continuation thesis. This condition was met on 2026-09-18 with the adjusted close of $23.94; the original threshold remains unchanged.
-
Kill line A daily close below $383 invalidates the renewed continuation thesis at the price boundary retained from the September 11, 2026 dossier; a reduction in the September 1 full-year adjusted EPS floor of $9.00 would separately break the earnings-stability premise.
-
Kill line A weekly close below $17.20 breaks the post-results advance near the 2026-08-14 close of $17.24; rejection or reduction of the proposed $0.64-per-share distribution, or payment postponed beyond October 2026, also invalidates the cash-return thesis.
-
Kill line A weekly close below $4.70 ends the price-recovery thesis by breaching the previously published support boundary; cancellation of the Canadian contract announced on 2026-09-11 would separately remove its new procurement support.
-
Kill line A weekly close below $167 breaks the published price structure. Separately, no year-over-year growth in truck revenue per load in the 2026-10-27 results invalidates the operating repricing thesis.
-
Kill line A weekly close below $265 invalidates the published freight-recovery structure. This condition was met on 2026-09-18, when the adjusted market close was $234.25; the original thesis has already failed its price test.
-
Kill line A weekly close below $11.00 invalidates the margin-recovery market thesis. Separately, Q3 revenue below $420 million, adjusted EBITDA below $49 million, or a reduction in FY2026 adjusted-EBITDA guidance of $215–235 million breaks the operating case.
-
Kill line A weekly close below $79.69 invalidates the continuation thesis by losing the September 18, 2026 adjusted reference close before a weekly close above the reported $84.20 high; $79.69 is not a verified support shelf.
-
Kill line A weekly close below $456 invalidates the September recovery by undercutting the 2026-09-03 market close of $456.16; independently, AMD or OpenAI confirming activation after Q4 2026, or no activation during that quarter, breaks the deployment timetable.
-
Kill line A weekly close below $29.83 breaks the post-August 6, 2026 earnings structure. Before price confirmation, reduced 2026 operating-earnings guidance below $600 million or a medical loss ratio forecast above 82.0% also ends the case.
-
Kill line A weekly close below $85 breaks the June 2, 2026 public-offering reference; third-quarter revenue below $234 million, adjusted EBITDA below $16 million or a reduction in the August 4 full-year revenue-growth outlook also rejects the operating case.
-
Kill line A weekly close below $65 ends the September continuation thesis. Withdrawal or reduction of fiscal 2026 adjusted EPS guidance above $4.80 independently breaks the fundamental case; failure to record a weekly close above $68.72 by 2026-10-27 ends the time-bounded thesis.
-
Kill line A weekly close below $114 invalidates the recovery thesis by undercutting the 2026-09-01 closing low of $114.52. The 2026-09-18 close of $116.55 has lost the August shelf but has not breached this condition.
-
Kill line A weekly close below $6.75 was the pre-completion thesis-break condition. The 2026-09-11 merger completion and 2026-09-14 Nasdaq suspension retired that test; no live ATAI closing-price trigger remains.
-
Kill line A daily close below $33.50 invalidates the completion-price thesis; an announced merger termination or failed required shareholder vote separately defeats the contractual case.
-
Kill line A daily close below $52 invalidates the merger-completion thesis; a filing announcing termination of the 2026-07-28 agreement or shareholder rejection independently breaks the case.
-
Kill line A weekly close below $84 ends the continuation thesis at the research boundary published on 2026-09-05; negative third-quarter net client cash flows would independently invalidate the organic-growth leg after second-quarter inflows of $4.3 billion.
-
Kill line A weekly close below $7.50 invalidates the price structure; separately, no interim efficacy readout by 2026-12-31 or results showing no improvement in target-area hair count against placebo breaks the clinical thesis.
-
Kill line A weekly close below $70.00 ends the recovery case at the research boundary retained from 2026-09-03. Withdrawal or reduction of the $130–150 million fiscal 2027 revenue guidance issued on 2026-07-14 separately breaks the operating premise.
-
Kill line A weekly close below $34 breaks the post-August earnings structure, beneath the $34.64 weekly close of 2026-08-07; Q3 2026 revenue below $214 million or cloud subscription revenue below $133 million independently invalidates operating confirmation.
-
Kill line A weekly close below $21 invalidates the momentum thesis; a subsequent company disclosure showing declining bitcoin per diluted common share while common issuance continues also breaks the financing case.
-
Kill line A weekly close below $34 invalidates the recovery thesis; Q3 revenue below $1.000 billion accompanied by a reduction in FY2026 adjusted EBITDA guidance of $255–280 million independently breaks the operating case.
-
Kill line A weekly close below $11.75 loses the August 2026 secondary-offering price and invalidates the structural thesis; maintaining or reducing the greater-than-$365 million fiscal 2026 adjusted EBITDA outlook at the next quarterly report separately ends the guidance-raise case.
-
Kill line A weekly close below $22.00 in the dividend-adjusted series ends the continuation thesis; independently, Q3 realised TCE at or below $74,000 per available day or a dividend below $0.95 per share at the 2026-11-24 report defeats the operating case.
-
Kill line A weekly close below $44 invalidates the post-reimbursement continuation case by losing the August $46.69–$48.61 band. Separately, FY2026 revenue guidance reduced below $490 million or a published MolDX restriction narrowing surveillance coverage breaks the operating premise.
-
Kill line A weekly close below $14.00 invalidates the commercial-expansion price thesis; guidance below the $104 million FY2026 revenue floor announced on 2026-08-06 separately breaks its operating premise.
-
Kill line A weekly close below $38 invalidates the cardiovascular re-rating thesis; failure to initiate EDG-7500 Phase 3 by 2026-12-31 separately breaks the Q4 2026 execution case.
-
Kill line A weekly close below $14 invalidates the post-approval price thesis; separately, no announced US commercial launch of SimpleScreen CRC by 2026-12-31 invalidates the commercial-timing case.
-
Kill line A weekly close below $42 invalidates the continuation thesis by surrendering the area around the 2026-08-14 gap-day close of $42.08; a reduction in the $246–250 million revenue or $29–31 million Plaque outlook independently breaks the operating case.
-
Kill line A weekly close below $33 invalidates the post-results re-rating thesis; independently, Q3 2026 revenue at or below the $86 million lower endpoint of guidance issued on 2026-08-03 fails the operating confirmation test.
-
Kill line A weekly close below $7.00 invalidates the commercial-revision thesis; independently, an update retaining or lowering the $350–370 million FY2026 revenue range, or no update by 2026-09-30, removes its fundamental leg.
-
Kill line A weekly close below $32 breaks the August price structure. Separately, Q3 2026 revenue below $160 million or a reduction of the $727–731 million FY2026 revenue outlook invalidates the operating case.
-
Kill line A weekly close below $85 ends the market thesis; failed placebo-controlled efficacy, treatment-related serious adverse events, or 2026-12-31 passing without Study ‘304’ topline results also invalidate the case.
-
Kill line A weekly close below $21 invalidates the post-results structure identified after August 6, 2026. Separately, full-year contribution ex-TAC growth guidance below 13% or the adjusted earnings margin outlook below 37% breaks the financial case.
-
Kill line A weekly close below $7.00 ends the margin-repair re-rating thesis; Q3 adjusted EBITDA below the $43 million guidance floor or a cut to FY2026 adjusted EPS guidance of $1.50–$1.65 also invalidates the operating case.
-
Kill line A weekly close below $24 breaks the June support shelf and invalidates the recovery case. Independently, Q3 2026 revenue at or below $335 million or another reduction to the full-year revenue guidance issued on 2026-08-06 defeats the stabilization premise.
-
Kill line A weekly close below $15.20 invalidates the post-results re-rating structure; independently, Q3 2026 revenue below the $75 million guidance floor announced on 2026-08-06 breaks the operating premise.
-
Kill line A weekly close below $9.00 ends the continuation thesis. Secondary invalidation occurs if AVITA cuts 2026 revenue guidance below $86 million, postpones fourth-quarter cash-flow breakeven, or reports no fourth-quarter cash generation.
-
Kill line A weekly close below $34.00 breaks the earnings-move structure; independently, Q3 Engineering revenue at or below $39.5 million or consolidated gross margin below 25.7% invalidates the operating case.
-
Kill line A weekly close below $116 invalidates the recovery thesis; continued negative Life Sciences organic growth at the next quarterly report, or a reduction below the 4–5% FY2026 organic-growth forecast, also breaks the conversion case.
-
Kill line A weekly close below $15.00 ends the market thesis; an FDA complete response letter or an extension beyond the 2026-11-14 decision date separately defeats the on-time approval case.
-
Kill line A weekly close below $14.59 invalidates the immediate continuation thesis by losing the 2026-09-11 adjusted reference close; this is a defined assessment threshold, not an established support shelf.
-
Kill line A weekly close below $5.25 breaks the consolidation reference identified on 2026-09-05; a reduction in FY2026 revenue guidance of $650–670 million or adjusted EBITDA guidance of $2–7 million, or a reported medical loss ratio above 90%, also breaks the operating thesis.
-
Kill line A weekly close below $36 invalidates the published turnaround structure. Independently, Q3 2026 Strategic Grow revenue below management’s $380 million guidance floor or another GAAP loss breaks the operating case.
-
Kill line A weekly close below $22 invalidates the pre-data price structure; failure to present the promised first-line zoci dataset by 2026-10-27 or initiate the planned registrational Phase 3 by 2026-12-31 separately breaks the development thesis.
-
Kill line A weekly close below $130 invalidates the post-earnings continuation case; Q3 fiscal 2026 EPS below $2.90 or a reduction in the $13.10–$13.60 full-year EPS guidance separately breaks the operating case.
-
Kill line A weekly close below $72 ends the repair case beneath the $72.68 post-results reference close; third-quarter specialty gross margin at or below 18.0% alongside adjusted EBITDA excluding duty benefits below $28.4 million would also break the operating thesis.
-
Kill line A weekly close below $13.30 breaks the June–July shelf identified in the 2026-09-06 published research; separately, a delay of any guided budoprutug dataset beyond Q4 2026, or the quarter ending without its disclosure, breaks the clinical timetable.
-
Kill line A weekly close below $22 invalidates retention of the September 11, 2026 adjusted 52-week high; this is a continuation threshold, not an established support base.
-
Kill line A weekly close below $11.48 invalidates the continuation thesis by losing the adjusted market reference close dated 2026-09-11; this is a reference-price condition, not a verified support shelf.
-
Kill line A weekly close below $28.00 ends the post-refund price thesis; secondary invalidation is third-quarter gross margin excluding comparable tariff benefits below Q2 2026's 26.1%, or 2026 operating-profit guidance reverting to a low-teens decline.
-
Kill line A weekly close below $104 breaks the August shelf defined by the 2026-08-21 and 2026-08-24 market closes; independently, reported failure on the prespecified primary endpoint in the 2026-09-08 HexAgon results ends the clinical thesis.
-
Kill line A weekly close below $27.32 invalidates the recovery thesis by losing the 2026-09-11 adjusted reference close; this level is a research boundary, not an established support shelf.
-
Kill line A weekly close below $10.60 breaks the July shelf and invalidates the recovery case; Q3 revenue below $208 million, ARR below the approximately $812 million company forecast, or withdrawal of the 20% Q4 2026 adjusted operating-margin goal would also defeat it.
-
Kill line A weekly close below $100.83 invalidates retention of the 2026-09-11 adjusted high; third-quarter realized Suezmax or Aframax/LR2 spot rates below the July booking benchmarks separately break the earnings-persistence case.
-
Kill line A weekly close below $24 ends the re-rating structure; a subsequent quarterly like-for-like decline in revenue less pass-through costs worse than Q2 2026’s 2.8%, or a reduction in the 12–13% FY2026 headline operating margin guide, also breaks the stabilisation thesis.
-
Kill line A weekly close below $23.07, the September 18, 2026 adjusted reference close, invalidates the continuation thesis before a weekly close at or above the observed $25.04 annual high.
-
Kill line A weekly close below $23.34 invalidates continuation beyond the market’s 2026-08-14 former-high close; independently, October XmAb819 disclosures abandoning pivotal-dose selection or postponing the planned study start beyond 2027 break the clinical case.
How we're scored
A confident model is easy. A calibrated one is the point.
When a pick resolves, it lands in the ledger above as played out or invalidated, dated, with a flag for whether the published kill line 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 — only whether the falsifiable claim was falsified.
The odds each tier stakes · published in advance
- SUPREME 85%
- HIGH 70%
- MEDIUM 55%
- LOW 40%
Each tier claims this chance of playing out. The Brier score above measures the gap between these stated odds and reality.
Every version of these odds, and when it took effect
- v1 from the first pick supreme 90% · high 75% · medium 60% · low 50% Authored anchors, never validated. Retained verbatim so no published score is ever restated.
- v2 from 27 August 2026 supreme 85% · high 70% · medium 55% · low 40% Pre-registered 2026-08-26 alongside a rewritten writer instruction that states these anchors to the model and asks for a probability rather than a position size. Spans 45 points instead of 10; centred near the 45% base rate.
A pick is scored under the odds in force on the day its dossier was written, so a revision never reaches back. Superseded odds stay on this page: a number published in advance is only checkable if the version it replaced is still here to check it against.
Common questions
- Do AI stock predictions actually work?
- There's no honest one-word answer — only a record. FrontierPicks publishes one: every pick ships a dated, falsifiable kill line, and a real closing price is what settles it — played out, invalidated, or still undecided if neither line has printed. The ones that reached a verdict are scored with a Brier score. The point isn't a headline accuracy figure but that the calls are checkable: a model's predictions only "work" if they survive the lines they published, and that's exactly what the scoreboard above measures.
- How is FrontierPicks scored?
- Every pick ships with a published kill line. When it resolves it's marked played out or invalidated — dated, with whether the line fired. Across resolved picks 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.
- How does a pick resolve, exactly?
- Mechanically, against the pick's own published kill line — no discretion. The reference is the real closing price the day the thesis was last stated. The kill is the price in the published line ("close below $X"); the target is a 1:1 realisation of that same published risk (as far above the entry as the kill is below it). Walking real daily closes forward, whichever is hit first decides it: a close at/below the kill is invalidated, a close at/above the target is played out. "Weekly close" lines are graded on weekly closes. A pick whose stop is within 2% (too tight to grade on price) or whose kill isn't a clean price level stays open. Graded only on whether the published claim was falsified.
- Why does the score start in June 2026?
- We rebuilt the research pipeline in June 2026, and a pick is graded on the thesis as the rebuilt pipeline stated it — from the day that thesis was written, not from the day the ticker entered coverage. Those are different dates for most of this record: 215 of the 419 resolved picks were first published before June 2026, and 2 carry an outcome date from before it, backfilled from outcomes the previous system had already written. So this is not a clean slate — it is a record of theses restated by the current pipeline, over a corpus much of which it inherited.
- 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 a rough reference band: expert human forecasters in Tetlock's Good Judgment work are commonly cited around 0.08, and the strongest LLM forecasters in 2024–25 evaluations around 0.10. Those benchmarks score different questions, so treat them as scale markers, not a like-for-like comparison.
- What does the scoreboard measure?
- Whether each falsifiable claim was falsified — graded against its own published kill line. It scores the reasoning, not a trade.
- What happens when a pick is wrong?
- It's marked invalidated, dated, and kept on the public record — with whether the published kill line fired first. Being wrong in public, on the record, is the point: it's what makes the score trustworthy.