free sign in →
← back to pipeline
mom

Will Kim Boo-kyum win the 2026 Daegu mayoral election?

will-kim-boo-kyum-win-the-2026-daegu-mayoral-election · Daegu Mayoral Election Winner · category: Elections, Global Elections, Main Election, Politics, South Korea · resolves
run_id: ed87908d-755b-4726-81cf-75d59b37c9b5 · started · status skipped · planner_skipped · ✕ planner rejected
action_not_tradeable: REVERSE
signal detected

detect_momentum · UR

● executed
direction
DOWN
current price
24.0%
anchor → trigger
35.5% → 24.0%
cusum @ trigger
-3.84
trigger hours
5h
duration
5h
72h range
24.0%—35.5% (Δ11.5pp)
tick density (6h)
0.83

Price fell 11.5pp from 35.5% to 24.0% over 5h (front_loaded). Now at 24.0%.

news gathered

news retrieval (tomographic)

● executed
raw→filtered: 106 → 1 quality: HIGH tokens: 14490
AI verdict

Prompt-UR · continuation analysis

● executed
REVERSE conviction: LOW opportunity: SMALL action: BUY YES
gpt-5 · prompt_2_trend_ur_v6.4.0 · 13054 tokens
Days to resolution: 21 days. Election/leadership market — Theta: NEUTRAL. YES-WORLD: the market resolves YES if Kim Boo-kyum is officially declared the winner of the 2026 Daegu mayoral election. NO-WORLD: it resolves NO if anyone else is officially declared winner or if no official win for Kim is recorded by the settlement date (polls or “near-leads” are near-misses). The one ★DIRECT item is a poll showing a 0.4pp razor-thin race; it is EVIDENCE-tier-via-NEAR-MISS (a poll, not a result) and is STALE (published 2026-05-10), though directionally favorable to YES. The ★DIRECT news thus supports YES and the trend is DOWN in the NO contract, so they align, but with no fresh catalyst the momentum looks starved/plateauing and the front-loaded drop likely reflects late digestion of that older poll. Fresh vs stale: trend_fresh=0, trend_stale=1, counter_fresh=0, counter_stale=0; Momentum signals: trend=0, counter=0. Remaining space: 24pp; with no new YES-side developments, a full follow-through lower is less likely than a partial reversion toward prior levels. Hard-rule checks: no news-trend conflict (Rule 1 not binding); use of “plateauing/starved” blocks CONTINUE (Rule 4), and spike >5pp with no fresh catalyst favors REVERSE (Rule 5).
rule audit

audit_gate

● executed
all
trade plan

position_planner

○ skipped
✕ action_not_tradeable: REVERSE

the deterministic planner rejected this trade. typical causes: poor R:R, spread exceeds gap, settlement danger zone, market too close to resolution. LLM assessment is above (Stage 6); planner is a pure-math gate layered on top.

step post-omit

news watch (A.2 / A.3)

● executed
watch: a5046105
status: ⏳ expired
armed: 2026-05-12T17:54Z
closed: 2026-05-13T18:53Z
polls: 5
signals seen: 4045
decision price: 24.0pct