Ledger / Prediction #256 · narrative · 1H

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

GENESIS said 78% → ACCELERATES INCORRECT

What GENESIS knew, before

5 of 2436 launches in the last hour referenced "paradox" (5 distinct creators, rank #427). Last 15m momentum 3.58×.

Made2026-10-09 17:30 UTC

Resolves2026-10-09 18:30 UTC

Evidence cutoff2026-10-09 17:29 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,
      "momentum": 1.2749607474756939,
      "diversity": 0.3
    },
    "rawProbability": 0.781590763309814
  },
  "features": {
    "term": "paradox",
    "rank60": 427,
    "share15": 0.008076358296622614,
    "share60": 0.0022568732047599507,
    "total15": 680,
    "total60": 2436,
    "momentum": 3.57856093979442,
    "diversity": 1,
    "launches15": 5,
    "launches60": 5,
    "contextMinutes": 60,
    "uniqueCreators60": 5
  },
  "extractor": "terms-v2",
  "selection": "random-eligible",
  "candidates": 399,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9971438888888889,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9971438888888889
}

Expected

{
  "direction": "up",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.781590763309814
}

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 18:33 UTC

StatusSCORED

OutcomeFADED

ClassificationINCORRECT

Brier0.611

Log loss1.521

Graderjudge-v1

Outcome data

{
  "shareAfter": 0,
  "shareRatio": 0.09401873464373464,
  "totalAfter": 2367,
  "shareBefore": 0.002042483660130719,
  "totalBefore": 2448,
  "coverageAfter": 1,
  "launchesAfter": 0,
  "coverageBefore": 1,
  "launchesBefore": 5
}

Post-outcome analysis · judge-v1

Predicted 78% that "paradox" would gain share over 1H. Its share of launches moved 0.20% → 0.00% (-100%). INCORRECT.

— momentum misled on "paradox" (1H). momentum contributed +1.27 to the log-odds toward yes; reality was no.

— Overconfident: 78% and wrong on "paradox". 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

Hash25b7fa602c63116e377252a7cffbb08419e4e195ed5a83396823ab3811f4f6d0

Previous hashf2d2833d31b1d4bfae35c55b5351cf2f97fdf275303243c4f28f4cfc9501027a