Bhārata Strata · Maharashtra · Sangli · morphological twins
Places like cell 4930006196
The MH-36 locality cells most similar to this Sangli 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 2 distinct districts
Index confidence
0.93
GUM mean confidence of the anchor (R24)
Dimensions compared
45
morphology-v2 feature dimensions
Closest twin distance
0.106
lower = more alike (weighted)
The twins, closest first
#1 · Sanglicell 4930006396
distance 0.106
#2 · Sanglicell 4930006199
distance 0.13
#3 · Kolhapurcell 4800005042
distance 0.138 · cross-district
#4 · Kolhapurcell 4800005474
distance 0.139 · cross-district
#5 · Kolhapurcell 4800003952
distance 0.14 · cross-district
#6 · Sanglicell 4930006335
distance 0.143
#7 · Sanglicell 4930005725
distance 0.144
#8 · Sanglicell 4930004073
distance 0.146
#9 · Sanglicell 4930005723
distance 0.153
#10 · Sanglicell 4930006188
distance 0.158
#11 · Sanglicell 4930006462
distance 0.159
#12 · Sanglicell 4930005324
distance 0.161
#13 · Kolhapurcell 4800005124
distance 0.162 · cross-district
#14 · Kolhapurcell 4800005558
distance 0.163 · cross-district
#15 · Sanglicell 4930005722
distance 0.165
#16 · Sanglicell 4930004654
distance 0.166
#17 · Kolhapurcell 4800004622
distance 0.167 · cross-district
#18 · Sanglicell 4930005192
distance 0.168
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":493,"cluster_id":4930006196}}}'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.