How much should I trust swarm results?

Here is a print of the total PARAMS dict I’m using:

AGGREGATIONINFO
seconds
 -- 0
fields
 -- [[u'device_temp_c', 'sum'], [u'libversion', 'sum'], [u'media_wear_pct', 'sum'], [u'power_on_hours', 'sum'], [u'write_amp', 'sum']]
months
 -- 0
days
 -- 0
years
 -- 0
hours
 -- 0
microseconds
 -- 0
weeks
 -- 0
minutes
 -- 0
milliseconds
 -- 0
 
('model', ' -- ', 'HTMPrediction')
 
('version', ' -- ', 1)
 
('predictAheadTime', ' -- ', 'null')
 
MODELPARAMS
sensorParams
 ---- verbosity = 0
 -------- media_wear_pct = {'maxval': 2472.0, 'name': u'media_wear_pct', 'clipInput': True, 'minval': 666.0, 'n': 231, 'fieldname': u'media_wear_pct', 'w': 21, 'type': 'ScalarEncoder'}
 -------- _classifierInput = {'maxval': 2472.0, 'classifierOnly': True, 'name': u'media_wear_pct', 'clipInput': True, 'minval': 666.0, 'n': 231, 'fieldname': u'media_wear_pct', 'w': 21, 'type': 'ScalarEncoder'}
 ---- sensorAutoReset = None
spParams
 ---- columnCount = 2048
 ---- spVerbosity = 0
 ---- localAreaDensity = -1.0
 ---- spatialImp = cpp
 ---- inputWidth = 946
 ---- synPermInactiveDec = 0.005
 ---- synPermConnected = 0.1
 ---- synPermActiveInc = 0.04
 ---- seed = 1965
 ---- numActiveColumnsPerInhArea = 40
 ---- boostStrength = 3.0
 ---- globalInhibition = 1
 ---- potentialPct = 0.85
trainSPNetOnlyIfRequested
 -- False
clParams
 ---- maxCategoryCount = 1000
 ---- implementation = cpp
 ---- verbosity = 0
 ---- steps = 1
 ---- alpha = 0.005
 ---- regionName = SDRClassifierRegion
tmParams
 ---- columnCount = 2048
 ---- activationThreshold = 16
 ---- pamLength = 1
 ---- cellsPerColumn = 32
 ---- permanenceInc = 0.1
 ---- minThreshold = 12
 ---- verbosity = 0
 ---- maxSynapsesPerSegment = 32
 ---- outputType = normal
 ---- globalDecay = 0.0
 ---- initialPerm = 0.21
 ---- permanenceDec = 0.1
 ---- seed = 1960
 ---- maxAge = 0
 ---- newSynapseCount = 20
 ---- maxSegmentsPerCell = 128
 ---- temporalImp = cpp
 ---- inputWidth = 2048
tmEnable
 -- True
spEnable
 -- True
inferenceType
 -- TemporalAnomaly