CONNECTED THINKING

Knowledge atlas

Follow people, viewpoints and their original evidence.

1 people · 1 sources · 1 viewpoints

IN CONTEXT

Causal attribution in AI outputs

Choose a viewpoint. Follow it back to the conversation.

Dai ties a data item’s effect to changes in output

IN CONTEXTCausal attribution in AI outputs1 viewpoints
2026-08-18

Equal sectors are reading positions, not rankings.

Showing 1–1 of 1 viewpoints · Newest sources first

1 / 1

Selected viewpoint

Dai ties a data item’s effect to changes in output

Zheng Dai says that if removing a piece of training data leaves the model’s output unchanged, that piece of data did not affect the output.

These are individual perspectives, not a measure of consensus. Source material stays in its original language.

Supporting evidence

When AI art has no author: MIT study finds generated images often can't be traced to any training data | MIT CSAIL

Original excerpt

If you take away a piece of data and the output of the model doesn’t change, then that piece of data didn’t affect the output
Context

" ,"

Publication dates describe the sources, not changes in belief.