{
  "abstract": "How does the human mind organize dynamic social scenes? Existing accounts rely on pre-defined social-affective or action-based taxonomies, yet whether humans use these dimensions to structure their representations of naturalistic social scenes remains unknown. We collected 53,223 human similarity judgments of videos depicting two-person actions and trained a sparse-positive-embedding model to recover the underlying latent dimensions. These learned dimensions explained twice as much variance in similarity judgments as pre-labeled annotations, captured interpretable fine-grained social-event structure (combining information about social relationships and actions), and fractionated broad semantic content (e.g., separating parent-child interactions into caregiving versus affectionate play). The same dimensions also predicted fMRI responses to passively viewed stimuli across visual cortex better than pre-labeled annotations, highlighting their importance beyond similarity judgments. Together, these results suggest that humans represent dynamic social scenes along fine-grained axes not captured by current taxonomies, and offer behaviorally-grounded targets for future studies of social vision.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "name": "Kathy Garcia"
    },
    {
      "name": "Leyla Isik"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2ptneh1s25e9q.bib",
  "cited_by": 0,
  "doi": "10.31234/osf.io/8cn9f_v2",
  "fulltext_url": null,
  "id": "2ptneh1s25e9q",
  "issns": [],
  "landing_url": "https://osf.io/preprints/psyarxiv/8cn9f_v2/",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "bepress",
      "Cognitive Neuroscience"
    ],
    [
      "bepress",
      "Computational Neuroscience"
    ],
    [
      "bepress",
      "Neuroscience"
    ],
    [
      "openalex",
      "3207|Action Observation and Synchronization"
    ]
  ],
  "openalex": "W7223325127",
  "pdf_url": "https://osf.io/8cn9f/download",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-30",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2ptneh1s25e9q.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:20Z",
      "native_id": "8cn9f",
      "source": "osf",
      "url": "https://osf.io/preprints/psyarxiv/8cn9f_v1/"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "bepress:Cognitive Neuroscience",
      "subfield": "neuroscience"
    }
  ],
  "title": "Human similarity judgments reveal fine-grained representations of dynamic social scenes",
  "title_text": "Human similarity judgments reveal fine-grained representations of dynamic social scenes",
  "type": "preprint",
  "updated_at": "2026-10-30T12:22:38Z",
  "url": "https://research.draconitic.com/paper/2ptneh1s25e9q",
  "venue": "PsyArXiv",
  "versions": []
}