{"slug":"spatial-harmony-computed","title":"Spatial harmony, computed","tag":"Spatial × ML","category":"spatial","status":"Active","kind":"research","fields":["spatial-intelligence","artificial-intelligence"],"parent_project":"auspicia","abstract":"Vastu and Feng Shui encode centuries of priors about how built space should be arranged. Most of it has never been tested, and the parts that have are buried in incompatible vocabularies. This board asks a narrow, falsifiable question: which of those priors can be written as structured constraints a model can reason over — and do they predict anything real?","description":"Can the priors inside Vastu and Feng Shui be expressed as structured constraints a generative model can reason over — and tested against real outcomes?","keywords":["Vastu Shastra","Feng Shui","generative design","spatial constraints","diffusion models"],"contributors":31,"open_threads":9,"open_problems":4,"updated_at":"2026-05-22","lead":{"handle":"mohit-gulati","name":"Mohit Gulati","role":"Co-founder · Steward, Spatial × ML"},"core":[{"handle":"mohit-gulati","name":"Mohit Gulati","role":"Co-founder · Steward, Spatial × ML","affiliation":"Xoop Innovation Labs"},{"handle":"rohan-kapoor","name":"Rohan Kapoor","role":"Architect, Spatial × ML","affiliation":"Independent practice"},{"handle":"jenny-lin","name":"Jenny Lin","role":"ML lead, generative design","affiliation":"PhD, ETH Zürich"}],"problems":[{"id":"SHC-01","title":"A machine-readable schema for directional priors","body":"Define a compact schema that captures orientation, zone function, and adjacency rules across at least two traditions without flattening their differences. Output: a published spec + validator.","difficulty":"medium","watching":4,"status":"unclaimed"},{"id":"SHC-02","title":"Do the priors survive contact with real floor plans?","body":"Take a labelled corpus of residential plans and measure whether harmony-rule compliance correlates with anything we can observe — resale, occupancy satisfaction, light/airflow proxies. Null results are a real contribution.","difficulty":"hard","watching":7,"status":"in progress","workers":2},{"id":"SHC-03","title":"Constraint-conditioned generation","body":"Condition a layout generator on the SHC-01 schema and run a blind preference study: humans, then agents, rate constrained vs unconstrained plans. Pre-register the protocol.","difficulty":"hard","watching":5,"status":"unclaimed"},{"id":"SHC-04","title":"An adversarial test set","body":"Build a small, deliberately tricky test set — symmetrically-flipped plans, near-canonical layouts off by one rule, etc. — and measure how brittle the rule-following models are.","difficulty":"medium","watching":3,"status":"in review","workers":1}],"recent_threads":[{"slug":"deep-test-thread-1779738139529-73glf","title":"Deep test thread 1779738139529","blurb":"Deep test blurb — withdrawn at teardown.","authorHandle":"","postedAgo":"just now","replies":0},{"slug":"deep-test-thread-1779690994932-afklg","title":"Deep test thread 1779690994932","blurb":"Deep test blurb — withdrawn at teardown.","authorHandle":"","postedAgo":"just now","replies":0},{"slug":"deep-test-thread-1779690777242-2kohc","title":"Deep test thread 1779690777242","blurb":"Deep test blurb — withdrawn at teardown.","authorHandle":"","postedAgo":"just now","replies":0},{"slug":"deep-test-thread-1779690553488-sf6te","title":"Deep test thread 1779690553488","blurb":"Deep test blurb — withdrawn at teardown.","authorHandle":"","postedAgo":"just now","replies":0},{"slug":"deep-test-thread-1779689604754-0wwpd","title":"Deep test thread 1779689604754","blurb":"Deep test blurb — withdrawn at teardown.","authorHandle":"","postedAgo":"just now","replies":0},{"slug":"deep-test-thread-1779689523009-fhggp","title":"Deep test thread 1779689523009","blurb":"Deep test blurb — withdrawn at teardown.","authorHandle":"","postedAgo":"just now","replies":0},{"slug":"deep-test-thread-1779689318226-szwnc","title":"Deep test thread 1779689318226","blurb":"Deep test blurb — withdrawn at teardown.","authorHandle":"","postedAgo":"just now","replies":0},{"slug":"deep-test-thread-1779689027653-64a67","title":"Deep test thread 1779689027653","blurb":"Deep test blurb — withdrawn at teardown.","authorHandle":"","postedAgo":"just now","replies":0},{"slug":"deep-test-thread-1779688540975-e1d26","title":"Deep test thread 1779688540975","blurb":"Deep test blurb — withdrawn at teardown.","authorHandle":"","postedAgo":"just now","replies":0},{"slug":"deep-test-thread-1779686765316-3ltoi","title":"Deep test thread 1779686765316","blurb":"Deep test blurb — withdrawn at teardown.","authorHandle":"","postedAgo":"just now","replies":0},{"slug":"deep-test-thread-1779686626080-vi6z4","title":"Deep test thread 1779686626080","blurb":"Deep test blurb — withdrawn at teardown.","authorHandle":"","postedAgo":"just now","replies":0},{"slug":"deep-test-thread-1779686374461-6b3m9","title":"Deep test thread 1779686374461","blurb":"Deep test blurb — withdrawn at teardown.","authorHandle":"","postedAgo":"just now","replies":0},{"slug":"deep-test-thread-1779686306228-c7j82","title":"Deep test thread 1779686306228","blurb":"Deep test blurb — withdrawn at teardown.","authorHandle":"","postedAgo":"just now","replies":0},{"slug":"schema-v0-2-feedback","title":"Draft schema v0.2 — feedback wanted","blurb":"Adjacency rules are still too tradition-specific.","authorHandle":"mohit-gulati","postedAgo":"1 week ago","replies":11},{"slug":"corpus-sourcing","title":"Corpus sourcing: what counts as a clean floor plan?","blurb":"Annotation guidelines, first cut.","authorHandle":"jenny-lin","postedAgo":"3 weeks ago","replies":4},{"slug":"auspicious-as-measurable-claim","title":"Why \"auspicious\" is a measurable claim, not a vibe","blurb":"Reframing the whole board around falsifiability.","authorHandle":"rohan-kapoor","postedAgo":"2 days ago","replies":6}],"related_publications":[{"slug":"encoding-directional-priors-as-model-constraints","title":"Encoding directional priors as model constraints","kind":"Preprint","published":"2026-05-10","url":"https://xooplab.com/publications/encoding-directional-priors-as-model-constraints"},{"slug":"can-a-tradition-be-falsified-kindly","title":"Can a tradition be falsified, kindly?","kind":"Essay","published":"2025-09-12","url":"https://xooplab.com/publications/can-a-tradition-be-falsified-kindly"}],"url":"https://xooplab.com/boards/spatial-harmony-computed"}