Bhārata Strata · Maharashtra · Thane · morphological twins
Places like cell 4970002016
The MH-36 locality cells most similar to this Thane cell across terrain, built form, land cover, climate dynamics and connectivity — ranked by a GUM-confidence-weighted (R24) distance, with the temporal block down-weighted. Each twin is a real cell with its own witnessed dossier.
Twins found
18
across 3 distinct districts
Index confidence
0.91
GUM mean confidence of the anchor (R24)
Dimensions compared
45
morphology-v2 feature dimensions
Closest twin distance
0.199
lower = more alike (weighted)
The twins, closest first
#1 · Thanecell 4970002104
distance 0.199
#2 · Thanecell 4970002025
distance 0.252
#3 · Thanecell 4970002329
distance 0.273
#4 · Thanecell 4970002023
distance 0.278
#5 · Nashikcell 4870001904
distance 0.281 · cross-district
#6 · Thanecell 4970002678
distance 0.281
#7 · Thanecell 4970002024
distance 0.295
#8 · Jalgaoncell 4780008878
distance 0.296 · cross-district
#9 · Thanecell 4970002853
distance 0.299
#10 · Thanecell 4970002796
distance 0.3
#11 · Thanecell 4970002254
distance 0.304
#12 · Jalgaoncell 4780009190
distance 0.304 · cross-district
#13 · Jalgaoncell 4780001952
distance 0.312 · cross-district
#14 · Jalgaoncell 4780008775
distance 0.322 · cross-district
#15 · Jalgaoncell 4780009972
distance 0.325 · cross-district
#16 · Thanecell 4970002401
distance 0.326
#17 · Jalgaoncell 4780002168
distance 0.327 · cross-district
#18 · Thanecell 4970002679
distance 0.33
witness: find_twins — morphology-twin-index-v2 (R24, GUM-confidence-weighted, magnitude-aware, temporal block down-weighted). Distance is the weighted feature distance; lower is more alike. Cross-district twins are the discriminative signal.
Re-witness these twins
curl -s https://api.gridrock.ai/mcp -H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"find_twins",
"arguments":{"admin_code":497,"cluster_id":4970002016}}}'Scope: the live MH-36 cube. Twins are computed from the sha-verified morphology-v2 vector; the engine supplies no goodness/suitability ranking — only morphological similarity.