GENESISv0.1.0
development instance · real Pump.fun observations · no token · no real rewards
Ledger / Prediction #1835 · narrative · 1H

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

GENESIS said 70% → ACCELERATES INCORRECT

What GENESIS knew, before

53 of 2325 launches in the last hour referenced "agent" (37 distinct creators, rank #10). Last 15m momentum 2.34×.

Made2026-10-11 21:00 UTC
Resolves2026-10-11 22:00 UTC
Evidence cutoff2026-10-11 20:59 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": 0.3541281001677032,
      "momentum": 0.8508290252684904,
      "diversity": -0.062264150943396275
    },
    "rawProbability": 0.6990320842442376
  },
  "features": {
    "term": "agent",
    "rank60": 10,
    "share15": 0.053858520900321546,
    "share60": 0.02300085984522786,
    "total15": 621,
    "total60": 2325,
    "momentum": 2.341587282507438,
    "diversity": 0.6981132075471698,
    "launches15": 33,
    "launches60": 53,
    "contextMinutes": 60,
    "uniqueCreators60": 37
  },
  "extractor": "terms-v2",
  "selection": "top-volume",
  "candidates": 264,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9929830555555555,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9929830555555555
}
Expected
{
  "direction": "up",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.6990320842442376
}
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

Graded2026-10-11 22:03 UTC
StatusSCORED
OutcomeFADED
ClassificationINCORRECT
Brier0.489
Log loss1.201
Graderjudge-v1
Outcome data
{
  "shareAfter": 0.015824175824175824,
  "shareRatio": 0.7017270830938028,
  "totalAfter": 2275,
  "shareBefore": 0.02264957264957265,
  "totalBefore": 2340,
  "coverageAfter": 1,
  "launchesAfter": 36,
  "coverageBefore": 1,
  "launchesBefore": 53
}
Post-outcome analysis · judge-v1

Predicted 70% that "agent" would gain share over 1H. Its share of launches moved 2.26% → 1.58% (-30%). INCORRECT.

— momentum misled on "agent" (1H). momentum contributed +0.85 to the log-odds toward yes; reality was no.

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

Integrity

Hashbd4b8fe20064409edef9388178e8b5c32da8ffc3bea1e0e72318ae26848092cb
Previous hash9a3e08a06b318fc49ce7e4398caff0cf07dcb7fc1c0beb5ccafd94f4c4f540e9