PROPHECY

· gate-removal A/B + wallet-autopsy archetypes

22:26CEST

live

deep-dive · PROPHECY · gate-removal A/B + 3 net-new archetypes · branded 2026-04-24back to overview

command link · unreachable

backend did not respond. every panel below reflects the last cached render, not live state.fetch failed

Prophecy · gate-removal A/B + wallet autopsy

paper mode · master kill switch: WB_PROPHECY_MASTER_ENABLE

live P&L$0.00no resolutions yet

archetypes0/8firing

bets opened00 resolved

bankroll cap$2,500vs Oracle/Zeus $1,500 ea

serviceofflineunknown

group A · unleashed clones (gate-removal A/B)

same scoring code as Oracle counterpart · fires where gate blocks

PYTHIA-U · Q· group A

Pythia Q with NO gate

Same as oracle_pythia_quality but fires only in 0-2h or >72h bands (gate-blocked complement)

Evidence

Empirical: Pythia 0-2h band 70.5% WR (n=44) vs 12-72h 57.2% WR — gate may hurt

Live hit

—

n=0

Live P&L

$0.00

warming

PYTHIA-U · A· group A

Pythia A with NO gate

Same as oracle_pythia_aggressive but in gate-blocked complement

Evidence

Inherits Pythia A OOS 91.7% (n=229, +$0.20/$1)

Live hit

—

n=0

Live P&L

$0.00

warming

CASSANDRA-U· group A

Cassandra with NO gate

Same as oracle_cassandra but in gate-blocked complement

Evidence

Inherits OOS 75.9% (n=29, +$0.425/$1)

Live hit

—

n=0

Live P&L

$0.00

warming

SIBYL-U· group A

Sibyl with NO gate

BUY NO at 1-3¢ when p_mkt ≥ 0.95, no gate; same toxic-station skip

Evidence

Inherits Sibyl backtest 96% WR · MARGINAL fee survival

Live hit

—

n=0

Live P&L

$0.00

warming

ARTEMIS-U· group A

Artemis restored to native -12h to +72h window

BUY YES at 1-5¢; uses include_post_end_hours=12 to recover docstring intent

Evidence

DISABLED 2026-04-24 · ColdMath misclone (clones LOSING leg only)

Live hit

—

n=0

Live P&L

$0.00

warming

group B · net-new archetypes

mechanisms surfaced from 43-wallet autopsy · pre-reg locked

HINDSIGHT· group B

POST_END_PARITY_NO grinder

BUY NO at ≥95¢ POST end_date when temp observation has locked (5h buffer)

Evidence

4 witnesses · 99.84-99.93% WR on $147k+ · NoonienSoong accelerating 2.68× in 2026

Live hit

—

n=0

Live P&L

$0.00

warming

ECHO· group B

Mid-band BUY YES (Pythia mirror)

BUY YES at p_mkt ∈ [0.15, 0.45] when p_pred − p_mkt ≥ 0.20 · standard Oracle window

Evidence

1 witness (HC2 +$1.13/$1 on n=364) · single-witness flag

Live hit

—

n=0

Live P&L

$0.00

warming

FORGE· group B

Paper-mode merge-arb (Phase 2)

BUY YES + BUY NO same conditionId when sum < $1, simulate merge to $1 face

Evidence

3 independent witnesses (Poligarch + neobrother + Lavincey)

Live hit

—

n=0

Live P&L

$0.00

warming

about this generation

Why a separate generation? Two reasons.

Preserve Oracle paper trial integrity. Oracle is locked under current rules through the 2026-04-30 review. Any change to Oracle archetypes contaminates that review.
Test the gate-removal hypothesis. Empirical evidence (Pythia 0-2h band 70.5% WR vs 12-72h 57.2% WR) suggests the gate is hurting Oracle. Group A clones run alongside Oracle, both feeding paper-mode data, for direct A/B at 04-30.

Master kill: WB_PROPHECY_MASTER_ENABLE=false in .env disables ALL Prophecy scanners regardless of per-archetype flags.

See docs/strategies/prophecy/PROPHECY.md + per-archetype docs (HINDSIGHT.md, ECHO.md, FORGE.md, UNLEASHED_CLONES.md).