embeddings, graphs, and models at scale
at scale the model is rarely the hard part. the hard part is what you're allowed to call a positive pair, and what the graph does to your assumptions once it's big enough that you can't look at it.
profiles ──► encoder ──► contrastive space │ ▼ ┌────────────────────┐ │ graph propagation │ 500M nodes │ k-hop, bounded │ └─────────┬──────────┘ ▼ retrieval / match eval: offline ≠ online
propagation is where the wins and the failure modes both live. an unbounded hop count makes the offline metric look better and the product worse, which is a lesson you only learn from the online number.
how much of what looks like representation quality is actually eval design.