GENESISv0.1.0
development instance · real Pump.fun observations · no token · no real rewards
Ledger / Prediction #4075 · narrative · 1H

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

GENESIS said 81% → ACCELERATES INCORRECT

What GENESIS knew, before

77 of 2185 launches in the last hour referenced "agent" (64 distinct creators, rank #6). Last 15m momentum 3.53×.

Made2026-10-14 19:00 UTC
Resolves2026-10-14 20:00 UTC
Evidence cutoff2026-10-14 19:00 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": 0.41015512641293755,
      "momentum": 1.262143779395134,
      "diversity": 0.09740259740259746
    },
    "rawProbability": 0.8130120117509173
  },
  "features": {
    "term": "agent",
    "rank60": 6,
    "share15": 0.12525458248472504,
    "share60": 0.03545288197621226,
    "total15": 490,
    "total60": 2185,
    "momentum": 3.5329873201497923,
    "diversity": 0.8311688311688312,
    "launches15": 61,
    "launches60": 77,
    "contextMinutes": 60,
    "uniqueCreators60": 64
  },
  "extractor": "terms-v2",
  "selection": "top-volume",
  "candidates": 286,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9993741666666667,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9993741666666667
}
Expected
{
  "direction": "up",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.8130120117509173
}
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

Graded2026-10-14 20:03 UTC
StatusSCORED
OutcomeFADED
ClassificationINCORRECT
Brier0.661
Log loss1.677
Graderjudge-v1
Outcome data
{
  "shareAfter": 0.006532897806812879,
  "shareRatio": 0.1909364467982667,
  "totalAfter": 2143,
  "shareBefore": 0.035208047553726564,
  "totalBefore": 2187,
  "coverageAfter": 1,
  "launchesAfter": 14,
  "coverageBefore": 1,
  "launchesBefore": 77
}
Post-outcome analysis · judge-v1

Predicted 81% that "agent" would gain share over 1H. Its share of launches moved 3.52% → 0.65% (-81%). INCORRECT.

— momentum misled on "agent" (1H). momentum contributed +1.26 to the log-odds toward yes; reality was no.

— Overconfident: 81% and wrong on "agent". Confidence this high should be wrong about 1 time in 4 or less; track this bucket.

2 memory records written (sealed: written while memory was short-context only).

Integrity

Hashfb983a838c69ebed50b8f1fbfaff0d70de03328319ad82175702f3d716087d54
Previous hash5b27aa920b7fb0d43ef8f92d598ad593dbd5dbf78b70ce355db0e7a4b510b736