Today's picks.
▸ Showing the last session — Fri Jul 31. New picks fire after ~9:30 ET.
Live recommendations from validated plays. BUYs are deterministic-gate-cleared, then LLM-scored for conviction tier (HIGH/MED/LOW). SKIPs are grouped by the override mechanism that filtered them. All judgment cites the validated mechanism — no caution-as-rigor.
New confirmed BUYs today (0)
Genuinely new picks that made it through all four stages today: mechanical gate passes, advisor evaluates favorably, AND the play's publication policy is satisfied — for most plays that means a confirming second fire; a play publishes on fire #1 only where its spec validates single-fire edge (see methodology).
Today's gate-filtered SKIPs (1) — research transparency, not action
What fired but the deterministic gate filtered. Grouped by override mechanism — each citation names the rule, not vibes. Subscribers can ignore this section; kept for transparency about what the system rejected.
Open positions — flagship (2) · Proven / Validated plays · ranked by validation tier
One row per ticker, not per fire. Re-fires within each play's hold window are
treated as signal confirmations on the same position (per spec.position).
Sorted by freshness.
Click a column header to re-sort. Entry recomputed from raw bars.
Signal freshness: Fresh 0
Active 0
Mature 2
— factual labels only; no claim about whether to chase or hold (per
backtest 2026-05-26, neither chase nor mean-reversion edge clears permutation per play).
Sectors: ★ AI/DC 1 — AI/DC closed n=142 mean +15.9% WR 68% p=0.0000. Software closed n=38 mean +6.4% but median -3.6%, WR 45%, p=0.75 (mixed). Per validation 2026-05-26. Labeling only.
OSIS shows an unusually clean LEAPS accumulation event: total OI surged 3.1x from 1,872 to 6,604 on July 14–15, with LEAPS call OI alone jumping 12.1x from 413 to 5,012 and retaining 100% of that position through July 22 — six straight days of OI stability despite declining daily RVOL. Put/call OI ratio collapsed from 0.68 to 0.11 and held there, a structural shift in OI composition rather than a day-trade flush. That is one thread: everything — RVOL 4.74x streak avg, 93.4% calls, 92.5% LEAPS, IV rank 83%, iv_rv_ratio 1.99, near-ATM concentration 0.956, gex_percentile 96–98% — comes from the options chain. An independent second thread comes from daily bars: OSIS sits at $209.79, the 10.9th percentile of its 52-week range ($197–$312, 33% below the 52w high of $311.72), with RSI(14) at 41.4 and price below MA20 ($215.58), MA50 ($216.25), and MA200 ($257.53). Institutional LEAPS buying into a sustained drawdown in a defense/security contractor (OSI Systems, $4.7B mkt cap, government inspection systems) is precisely what the UOA thesis predicts — the kind of business where procurement-cycle positioning precedes announcements. Loser-pattern checks: no catalyst requirement is by design for UOA (66–86% unknown-catalyst rate across all outcomes); prior matured OSIS picks (three from upgrade_prediction: +4.46%, +9.40%, +6.66%) show no bidirectional whipsaw; no biotech binary risk. Concerns: individual RVOL on streak days 4–6 fell to 2.87–3.29x (below the 4x sweet spot), though streak average of 4.74x qualifies; Q4 FY2026 earnings (fiscal year ends June 30, likely August 2026 release) may fall within the 20-day hold window, though the spec's earnings_exit_days=5 manages this; ticker-block permutation p=0.058 is a structural play-level concern. Rising conviction from first fire (0.75, streak 4d) to this confirming fire (0.875, streak 6d) is a quality indicator. Forward matured n is too thin to evaluate; load-bearing validation is spec PF 1.56 (robust floor ex-top-5 tickers) to PF 3.98 (full OOS), n=140, perm p=0.017 — two threads agree, one strong and one independent.
GGB (Gerdau SA ~$6.8B Brazilian steel ADR) carries a 5-day UOA streak from 2026-07-06: avg RVOL 4.62x, call_pct 96.6%, LEAPS pct 94.4% — all well above entry thresholds and in the streak≥4 sub-cell (phase_2_audit OOS PF 6.51 n=49 vs 4.37 for streak≥3). Thread 1 is the UOA flow signal itself; the play's load-bearing backtest is PF alpha 2.63 (BH q=0.0038), OOS PF alpha 3.86 (n=52); live matured n=46 tracks above at mean +6.0%, WR 61%, PF proxy ~3.8. Thread 2 (partially independent): on 2026-07-10, total OI grew +92 contracts (leaps_call_oi 5769→5854) — first net accumulation after 3+ weeks of flat/declining OI, indicating new positions opened, not day-trading churn. Thread 3 (independent, equity bars): RSI recovered from oversold 33-37 (early July) to 57.4 today; stock up 10.6% in 5 days from $4.06 to $4.50, at 80.9% of 52w range ($2.85–$4.89) with 8.7% to 52w high. The streak PRECEDED the equity move (started at $4.28 on Jul 6), consistent with the informed-flow lead-then-follow thesis. No catalyst flag applies (uoa_slow_build is a pure-technical play; unknown catalyst is by design). Sub-$5 underlying is not a deflator per v1.6.0 re-validation (price floor removed after broader-universe sweep showed it subtracts edge). No earnings trap, no biotech binary. Conviction escalated 0.50→0.75 over the 4-day refire interval. Three threads (one strong UOA, one partial OI build, one independent equity RSI/momentum) support a MED score.
Pipeline (1) · picks from Emerging-tier plays
Picks from plays still in the Emerging tier — validated in backtest, now accumulating a live forward sample. They publish in real time with the same audit trail, columns, and track-record treatment as every other pick, but they are the pipeline, not the headline product: a play graduates to the flagship book above only when its forward evidence clears the promotion gates.
Three independent threads for TRMB. Thread 1 (options flow): score 13/17, call_pct averaging 87.1% over the 3-day qualifying streak (Jul 13–15), vw_otm 77.5% (deep-OTM positioning), delta_dollars $868K today with mean $1.47M/day on all qualifying sessions past 4 weeks, and OI +9.8% over 15 days (17,122→18,794 after a June 18 unwind reset the chain — the rebuild into rising OI is the signal). Thread 2 (pre-earnings calendar, independent): d2e=14, squarely in the spec-validated d2e 0–14d bucket (n=42, WR 71.4%, PF 3.56, avg +11.45% at 10d, perm p=0.0064 on broader cohort); hold-through-earnings explicitly validated (earnings_exit_days=0), so this is a real independent booster, not an IV trap. Thread 3 (price structure): TRMB at 10.1% of its 52-week range ($47.92–$87.50), RSI 45.7 recovering from oversold 33–34 in late June; prior TRMB fire on 2026-06-15 returned +1.87% at 10d and +3.34% at 20d. Meaningful deflators pull this to low-MED: LEAPS% 69.4% is in the weakest LEAPS bucket (leaps_pts=0; spec: 30-50% optimal at PF 2.59, 70%+ lowest at PF 1.42); streak is at the T+3 minimum (T+6+ bucket has PF 9.02 vs T+3-5 combined PF 1.49); score=13 is the worst alpha bin in the intra-cohort calibration note (mean alpha −6.1% vs +10.9% at score=10); RVOL=0.66 (<1.3x) shows no equity-volume confirmation of the options accumulation.
Provisional (1) — single fires from playbook-eligible plays, watching for confirmation
Single fires of second_fire plays — preliminary signals, not yet
held. A confirming second fire on the same ticker (any play) promotes them to
Open. If none arrives within the hold window, the signal closes to the Track
Record. See docs/POSITION_MODEL.md.
Track record
Closed positions only — one row per ticker per continuous holding period. Re-fires within 20 days are rolled into the same position. Entry / exit prices recomputed from raw market bars.
The methodology's edge is established by out-of-sample backtest, per play — there is no single blended figure. Live forward (below) is a sanity check: the published track record is still thin (since 2026-05-08).
Show all 18 closed positions (filterable)
Recently exited (2)
Positions the system closed mechanically within the last 5 trading days. Final move is realized at the exit close. Cradle-to-grave audit trail — every BUY broadcast has a symmetric CLOSE.
2 recently exited positions
Get picks by email
Every published pick, as it lands — conviction score and the model's full reasoning. No spam, unsubscribe anytime.