A reverse Turing-test for predicting social deficits in people with Autism
Bibliographic record
Abstract
Abstract: Social symptoms of autism spectrum disorder (ASD) are typically viewed as consequences of an impaired Theory of Mind, i.e. the ability to understand others’ covert mental states. Here, we test the assumption that such “mind blindness” may be due to the inability to exploit contextual knowledge about, e.g., the stakes of social interactions, to make sense of otherwise ambiguous cues (e.g., idiosyncratic responses to social competition). In this view, social cognition in ASD may simply reduce to non-social cognition, i.e. cognition that is not informed by the social context. We compared 24 adult participants with ASD to 24 neurotypic participants in a repeated dyadic competitive game against artificial agents with calibrated mentalizing sophistication. Critically, participants were framed to believe that they were competing against humans (social framing) or not (non-social framing), hence the “reverse Turing test”. In contrast to control participants, the strategy of people with ASD is insensitive to the game’s framing, i.e. they do not constrain their understanding of others’ behaviour with the contextual knowledge about the game (cf. competitive social framing). They also outperform controls when playing against simple agents, but are outperformed by them against recursive algorithms framed as human opponents. Moreover, computational analyses of trial-by-trial choice sequences in the game show that individuals with ASD rely on a distinctive cognitive strategy with subnormal flexibility and mentalizing sophistication. These computational phenotypes yield 79% diagnosis classification accuracy and explain 62% of the severity of social symptoms in people with ASD.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.041 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".