{"id":"W7106825722","doi":"10.48448/3tep-c829","title":"MoMentS: A Comprehensive Multimodal Benchmark for Theory of Mind","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Benchmark (surveying); Context (archaeology); Modality (human–computer interaction); Multimodality; Theory of mind","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00381753,0.001431208,0.0005450415,0.002285144,0.001156591,0.002714441,0.00178856,0.001819959,0.0133682],"category_scores_gemma":[0.02742773,0.0003010087,0.0008060479,0.001299275,0.001123519,0.004178335,0.004284252,0.001541383,0.003589072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00153669,"about_ca_system_score_gemma":0.00149886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004746718,"about_ca_topic_score_gemma":0.00493787,"domain_scores_codex":[0.9961007,0.002025587,0.0002063423,0.0004200917,0.00106059,0.0001866549],"domain_scores_gemma":[0.9897502,0.005350625,0.0004998253,0.001819157,0.001812548,0.0007677101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002545416,0.001857694,0.02316347,0.003214696,0.0004199297,0.0006711929,0.004833492,0.1094701,0.02121138,0.1348936,0.2350272,0.4626918],"study_design_scores_gemma":[0.0003168741,0.00162256,0.01910332,0.0008909534,0.0001270132,0.0008112807,0.003347832,0.4305374,0.02400868,0.2226485,0.2962846,0.0003009948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3410284,0.005196532,0.3973812,0.004985498,0.0007262031,0.002201862,0.05287256,0.02298378,0.172624],"genre_scores_gemma":[0.6913236,0.001072075,0.2371203,0.0006860316,0.000193715,0.003327846,0.05499939,0.002182307,0.009094689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0133682,"threshold_uncertainty_score":0.04472107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04982850881263926,"score_gpt":0.3488422456059803,"score_spread":0.299013736793341,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}