Ledger / Prediction #231 · narrative · 1H

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

GENESIS said 85% → ACCELERATES INCORRECT

What GENESIS knew, before

87 of 2579 launches in the last hour referenced "instead" (87 distinct creators, rank #5). Last 15m momentum 3.82×.

Made2026-10-09 16:30 UTC

Resolves2026-10-09 17:30 UTC

Evidence cutoff2026-10-09 16:29 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": 0.42847053093307247,
      "momentum": 1.3408319870431333,
      "diversity": 0.3
    },
    "rawProbability": 0.8543709109203461
  },
  "features": {
    "term": "instead",
    "rank60": 5,
    "share15": 0.12962962962962962,
    "share60": 0.03391472868217054,
    "total15": 674,
    "total60": 2579,
    "momentum": 3.8222222222222224,
    "diversity": 1,
    "launches15": 87,
    "launches60": 87,
    "contextMinutes": 60,
    "uniqueCreators60": 87
  },
  "extractor": "terms-v2",
  "selection": "top-volume",
  "candidates": 362,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9943619444444445,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9943619444444445
}

Expected

{
  "direction": "up",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.8543709109203461
}

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 17:33 UTC

StatusSCORED

OutcomeFADED

ClassificationINCORRECT

Brier0.730

Log loss1.927

Graderjudge-v1

Outcome data

{
  "shareAfter": 0.0004084967320261438,
  "shareRatio": 0.018185848451262906,
  "totalAfter": 2448,
  "shareBefore": 0.03350019252984213,
  "totalBefore": 2597,
  "coverageAfter": 1,
  "launchesAfter": 1,
  "coverageBefore": 1,
  "launchesBefore": 87
}

Post-outcome analysis · judge-v1

Predicted 85% that "instead" would gain share over 1H. Its share of launches moved 3.35% → 0.04% (-99%). INCORRECT.

— momentum misled on "instead" (1H). momentum contributed +1.34 to the log-odds toward yes; reality was no.

— Overconfident: 85% and wrong on "instead". 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

Hash54273486f827c8bb43c02d82150c4bae8218997f2241222ba8603604d4db920e

Previous hash49abf9ee7278574d2e4a0b867e186f9e96fadc35604814df46131a31af7e0716