GENESISv0.1.0
development instance · real Pump.fun observations · no token · no real rewards
Ledger / Prediction #160 · narrative · 1H

Will "agents" take a larger share of new Pump.fun launches in the next 1H than in the previous 1H?

GENESIS said 56% → ACCELERATES INCORRECT

What GENESIS knew, before

27 of 1840 launches in the last hour referenced "agents" (27 distinct creators, rank #9). Last 15m momentum 0.99×.

Made2026-10-09 13:30 UTC
Resolves2026-10-09 14:30 UTC
Evidence cutoff2026-10-09 13:29 UTC
Data sourcespumpfun.launch_feed
GENESIS version0.1.0
Enginenarrative-heuristic-v0
Scoring methodshare-direction-v1
Active capabilities6
Evidence (exact record)
{
  "model": {
    "bias": -0.3,
    "version": "narrative-heuristic-v0",
    "horizonScale": 1,
    "contributions": {
      "volume": 0.2529598430355343,
      "momentum": -0.013364521984702374,
      "diversity": 0.3
    },
    "rawProbability": 0.5596139200931064
  },
  "features": {
    "term": "agents",
    "rank60": 9,
    "share15": 0.01473922902494331,
    "share60": 0.014937533948940793,
    "total15": 440,
    "total60": 1840,
    "momentum": 0.9867243867243867,
    "diversity": 1,
    "launches15": 6,
    "launches60": 27,
    "contextMinutes": 60,
    "uniqueCreators60": 27
  },
  "extractor": "terms-v2",
  "selection": "random-eligible",
  "candidates": 315,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9940847222222222,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9940847222222222
}
Expected
{
  "direction": "up",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.5596139200931064
}
Engine narrative-heuristic-v0

P(term's share of new Pump.fun launches is higher in the next H than in the previous H). Hand-set logistic heuristic over 60 minutes of launch observations: short-term momentum, creator diversity, volume. Slight mean-reversion prior because candidates are selected while already popular.

What happened, after

Graded2026-10-09 14:33 UTC
StatusSCORED
OutcomeFADED
ClassificationINCORRECT
Brier0.313
Log loss0.820
Graderjudge-v1
Outcome data
{
  "shareAfter": 0.008972633467922835,
  "shareRatio": 0.6177578475336324,
  "totalAfter": 2229,
  "shareBefore": 0.014618299945858148,
  "totalBefore": 1847,
  "coverageAfter": 1,
  "launchesAfter": 20,
  "coverageBefore": 1,
  "launchesBefore": 27
}
Post-outcome analysis · judge-v1

Predicted 56% that "agents" would gain share over 1H. Its share of launches moved 1.46% → 0.90% (-39%). INCORRECT.

— diversity misled on "agents" (1H). diversity contributed +0.30 to the log-odds toward yes; reality was no.

1 memory record written (sealed: written while memory was short-context only).

Integrity

Hashc4c6e4ae37177474d1401a0668b263fb4ad96200984b956e8b79d2d644977f88
Previous hashbcfc9b2a972ee623e9e4a7fff27a4e94f1036b80720c77b50d6b2f9455870baf