Live实时 ·

Intelligence Hub情报中心

What still has room to run — surfaced before the crowd arrives.仍有上行空间的机会 —— 抢在人群之前浮出水面。

Regime格局 Reflation Q2 Cycle周期 mid Liquidity流动性 neutral Fed美联储 Hawkish
Prices from the latest settled build价格来自最近一次结算构建
News新闻流 building record记录积累中 Alt-Data另类数据 measured已有记录 Radar背离雷达 measured已有记录 Buy-Board买入榜 no history暂无记录 Policy政策观察 building record记录积累中 Special特殊事件 no history暂无记录

Emerging edge萌芽优势

1
A leading desk is positioned; the tape has not confirmed yet. Watch — don't chase.领先信号台已建仓，盘面尚未确认。观察 —— 不要追高。
NTRS$167.92 early早期 5
RS -10% vs SPY · radar forming
room left剩余空间 83%

Discovery发掘

what the desks miss各台遗漏之处 14
Leads no desk has picked up yet. Watch — a lead is not a signal.尚无信号台采纳的线索。观察 —— 线索不等于信号。

Exhausted — already run透支 —— 已跑完 12

Desks lean bearish and price is rolling over. De-risk — not a long.各台偏空且价格见顶回落。降低风险 —— 不宜做多。

Dated catalysts有日期的催化 12

Events with a known date. Context for timing — not a reason to buy.有确定日期的事件。用于把握时点 —— 而非买入理由。

Command指挥榜

room left剩余空间 30
Most room left first. A ready-to-review badge means the entry checks agree; review before acting.剩余空间最大者居前。「可复核」表示入场条件一致；行动前仍需复核。

Track record历史战绩

is the edge real?优势是否真实？
5d天 measuring测量中
rank skill排名预测力 -0.017 this regime (Q2) -0.036 · n 86,874本格局 Q2 -0.036 · n 86,874
scored已评分 197,559 72% of 272,652 eligible占可评分 272,652 条的 72%
emerging beat SPY?萌芽跑赢标普？ -0.6% no否
exhausted lagged SPY?透支跑输标普？ -0.3% yes是
10d天 measuring测量中
rank skill排名预测力 -0.012 this regime (Q2) -0.030 · n 78,638本格局 Q2 -0.030 · n 78,638
scored已评分 188,959 71% of 266,959 eligible占可评分 266,959 条的 71%
emerging beat SPY?萌芽跑赢标普？ -1.4% no否
exhausted lagged SPY?透支跑输标普？ -0.7% yes是
21d天 measuring测量中
rank skill排名预测力 -0.008 this regime (Q2) +0.016 · n 63,089本格局 Q2 +0.016 · n 63,089
scored已评分 173,084 68% of 253,301 eligible占可评分 253,301 条的 68%
emerging beat SPY?萌芽跑赢标普？ -2.3% no否
exhausted lagged SPY?透支跑输标普？ -0.8% yes是
63d天 measuring测量中
rank skill排名预测力 -0.047 this regime (Q2) -0.016 · n 27,765本格局 Q2 -0.016 · n 27,765
scored已评分 110,251 60% of 184,494 eligible占可评分 184,494 条的 60%
emerging beat SPY?萌芽跑赢标普？ -1.0% no否
exhausted lagged SPY?透支跑输标普？ -2.7% yes是
Discovery leads · 21d发掘线索 · 21天 context参考
activist ownership -4.5% lagged SPY跑输标普 n 372 · 30% of leads beat SPY30% 的线索跑赢标普 5d -0.4% · 10d -2.1% · 63d -10.1%5天 -0.4% · 10天 -2.1% · 63天 -10.1%
federal velocity -6.3% lagged SPY跑输标普 n 118 · 24% of leads beat SPY24% 的线索跑赢标普 5d -1.4% · 10d -3.0% · 63d -18.2%5天 -1.4% · 10天 -3.0% · 63天 -18.2%
insider cluster -3.4% lagged SPY跑输标普 n 2,435 · 33% of leads beat SPY33% 的线索跑赢标普 5d -0.7% · 10d -1.4% · 63d -9.3%5天 -0.7% · 10天 -1.4% · 63天 -9.3%
radar quiet +1.5% beat SPY跑赢标普 n 141 · 47% of leads beat SPY47% 的线索跑赢标普 5d +1.1% · 10d +1.1% · 63d -0.7%5天 +1.1% · 10天 +1.1% · 63天 -0.7%
Snapshot gaps快照缺口 — 12 of 21 expected snapshot dates in the last 30 days have no snapshot.近 30 天预期的 21 个快照日中，有 12 个没有快照。 Approximate: market holidays count as missing, so this over-reports.为近似值：市场假日也计为缺失，因此偏高。
Desk-history check信号台历史检查 — measuring; not currently pulling any names down.测量中；目前未下调任何标的。 radar雷达 17,553 scored已评分 this page本页 173,084 scored已评分
Desk scorecard研究台记分卡⚠ check⚠ 待复核One horizon is running the wrong way有一个周期方向相反 detail详情

Every name this desk surfaces is scored against what the stock actually did next, measured against SPY. Context only — never a trade instruction. 本台每个入选标的都以其之后的实际走势评分，并与标普对比。仅作参考 —— 绝非交易指令。 274,870 names recorded · 18,047 drops tracked 已记录 274,870 个标的 · 已追踪 18,047 次剔除

Horizon周期 graded已评分 rank skill排名预测力 trend skill趋势预测力 vs SPY对比标普 status状态
5d日 197411 -0.018 -0.010 +4.0% measuring测量中
10d日 188734 -0.014 -0.009 +4.8% measuring测量中
20d日 167269 -0.002 +0.001 +4.3% measuring测量中
30d日 147102 -0.021 +0.001 +0.9% measuring测量中
60d日 83839 -0.044 -0.001 -3.0% check待复核
90d日 0 — — — measuring测量中

Before and after the engine overhaul引擎改版前后对比

5d日 hub-v3-trajectory -0.022 n=163058 · +5.0%
10d日 hub-v3-trajectory -0.019 n=154404 · +7.3%
20d日 hub-v3-trajectory +0.002 n=133117 · +4.5%
30d日 hub-v3-trajectory -0.020 n=113105 · +2.2%
60d日 hub-v3-trajectory -0.021 n=50324 · -2.5%

What the numbers say数据说明了什么

  • ▲ 5d: 'exhausted' (-0.4%) outperforms 'emerging' (-0.9%) — possible residual inversion in the lifecycle staging.5d: 'exhausted' (-0.4%) outperforms 'emerging' (-0.9%) — possible residual inversion in the lifecycle staging.
  • ▲ 10d: departed names (+7.2% avg) OUTPERFORM on-desk names (+4.8%) — the desk may be exiting winners too early.10d: departed names (+7.2% avg) OUTPERFORM on-desk names (+4.8%) — the desk may be exiting winners too early.
  • ▲ 10d: 'exhausted' (-0.8%) outperforms 'emerging' (-2.2%) — possible residual inversion in the lifecycle staging.10d: 'exhausted' (-0.8%) outperforms 'emerging' (-2.2%) — possible residual inversion in the lifecycle staging.
  • ▲ 20d: departed names (+5.4% avg) OUTPERFORM on-desk names (+4.3%) — the desk may be exiting winners too early.20d: departed names (+5.4% avg) OUTPERFORM on-desk names (+4.3%) — the desk may be exiting winners too early.
  • ▲ 20d: 'exhausted' (-1.0%) outperforms 'emerging' (-1.5%) — possible residual inversion in the lifecycle staging.20d: 'exhausted' (-1.0%) outperforms 'emerging' (-1.5%) — possible residual inversion in the lifecycle staging.
  • ● 30d: score VELOCITY IC (+0.001) exceeds LEVEL IC (-0.021) — the change in the desk's score ranks winners better than its level.30d: score VELOCITY IC (+0.001) exceeds LEVEL IC (-0.021) — the change in the desk's score ranks winners better than its level.
  • ⚠ 60d level IC is significantly NEGATIVE (-0.044, n=83839) — the desk's ranking is anti-predictive here; consider inverting or gating the score.60d level IC is significantly NEGATIVE (-0.044, n=83839) — the desk's ranking is anti-predictive here; consider inverting or gating the score.
  • ● 60d: departed names (-5.4% avg) underperform on-desk names (-3.0%) — DROPS ARE CORRECT; the desk sheds names before they lag.60d: departed names (-5.4% avg) underperform on-desk names (-3.0%) — DROPS ARE CORRECT; the desk sheds names before they lag.

Lessons logged经验记录

  • 2026-07-04 2026-07-04 inversion finding: the OLD hub engine was anti-predictive — pooled opportunity IC ~-0.09 @5d, and 'exhausted' names (+1.84% avg fwd) BEAT 'emerging' (-0.77%). The hub-v3-trajectory overhaul is the fix under test; this grader's engine_version A/B is the experiment that proves whether it worked.2026-07-04 inversion finding: the OLD hub engine was anti-predictive — pooled opportunity IC ~-0.09 @5d, and 'exhausted' names (+1.84% avg fwd) BEAT 'emerging' (-0.77%). The hub-v3-trajectory overhaul is the fix under test; this grader's engine_version A/B is the experiment that proves whether it worked.
  • 2026-07-04 PRICE LESSON: grade off data/yahoo/<T>.parquet adjusted closes ONLY. The S&P-1500 breadth close cache (data/breadth/_closes_cache.parquet) is SPLIT-CORRUPTED — using it silently poisons every RS / forward-return number. A name missing from yahoo is a coverage skip here, never a wrong return.PRICE LESSON: grade off data/yahoo/<T>.parquet adjusted closes ONLY. The S&P-1500 breadth close cache (data/breadth/_closes_cache.parquet) is SPLIT-CORRUPTED — using it silently poisons every RS / forward-return number. A name missing from yahoo is a coverage skip here, never a wrong return.
  • 2026-07-04 NOTE on the engine_version A/B: the historical hub ledger carries NO engine_version stamp (all ~63k rows pre-date the stamp), so the pre/post-overhaul split only begins accruing from 2026-07-04 forward. Until enough hub-v3-trajectory rows mature, the A/B reads one-sided; that is expected, not a bug.NOTE on the engine_version A/B: the historical hub ledger carries NO engine_version stamp (all ~63k rows pre-date the stamp), so the pre/post-overhaul split only begins accruing from 2026-07-04 forward. Until enough hub-v3-trajectory rows mature, the A/B reads one-sided; that is expected, not a bug.

~ marks a provisional reading from a single cross-section; the "proven" bar needs at least six separate grading dates. An accountable scorecard of this desk's own surfaced names — its ranking score (level AND velocity) graded against realized SPY-relative forward returns at 5/10/20/30/60/90 trading days, split on-desk vs after-leaving. A signal is 'proven' only past n>=40 with a significant Newey-West t of the right sign; a significant negative IC is an 'alarm'. Context-only — nothing here sizes a position.~ 表示来自单一横截面的暂定读数；"已验证"门槛需至少六个独立评分日。An accountable scorecard of this desk's own surfaced names — its ranking score (level AND velocity) graded against realized SPY-relative forward returns at 5/10/20/30/60/90 trading days, split on-desk vs after-leaving. A signal is 'proven' only past n>=40 with a significant Newey-West t of the right sign; a significant negative IC is an 'alarm'. Context-only — nothing here sizes a position.

Sector heat板块热度

where the desks cluster各台聚集之处
XLK Technology 6 names标的
XLB Materials 1 names标的
XLC Communication 2 names标的
XLY Discretionary 2 names标的
XLF Financials 3 names标的
XLE Energypolicy政策 ↑ 1 names标的