Will "paired" take a larger share of new Pump.fun launches in the next 6H than in the previous 6H?
GENESIS said 47% → FADES INCORRECT
What GENESIS knew, before
13 of 2275 launches in the last hour referenced "paired" (10 distinct creators, rank #80). Last 15m momentum 1.08×.
{
"model": {
"bias": -0.3,
"version": "narrative-heuristic-v0",
"horizonScale": 0.7,
"contributions": {
"volume": 0.14332671675411546,
"momentum": 0.07579927587522464,
"diversity": 0.023076923076923127
},
"rawProbability": 0.4674316879176858
},
"features": {
"term": "paired",
"rank60": 80,
"share15": 0.006398537477148081,
"share60": 0.005931458699472759,
"total15": 546,
"total60": 2275,
"momentum": 1.0787460220732616,
"diversity": 0.7692307692307693,
"launches15": 3,
"launches60": 13,
"contextMinutes": 60,
"uniqueCreators60": 10
},
"extractor": "terms-v2",
"selection": "random-eligible",
"candidates": 364,
"calibration": null,
"methodology": "attention-v1",
"termHistory": null,
"contextCoverage": 0.9982630555555555,
"memoriesRecalled": 0,
"priorWindowCoverage": 0.9997105092592593
}{
"direction": "down",
"magnitude": null,
"magnitudeNote": "v0 does not model magnitude",
"probabilityUp": 0.4674316879176858
}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
{
"shareAfter": 0.00772746157041961,
"shareRatio": 1.5674827369742623,
"totalAfter": 12035,
"shareBefore": 0.004923874311629414,
"totalBefore": 15435,
"coverageAfter": 1,
"launchesAfter": 93,
"coverageBefore": 1,
"launchesBefore": 76
}Predicted 47% that "paired" would gain share over 6H. Its share of launches moved 0.49% → 0.77% (+57%). INCORRECT.
— volume was right but too weak on "paired" (6H). volume contributed +0.14 toward yes, the true outcome, but could not overcome the prior.
— The prior was wrong on "paired" (6H). Every active signal pointed the right way; the base assumption outweighed them.
2 memory records written (sealed: written while memory was short-context only).
Integrity
d7904e03e54f477184c3bb5501bc50d48b4faa103afaa77f48df238ba35523071d09ff7233d911f212e871da418034372ae1db0eead88e1898063044e5e139df