{"id":"W4396893649","doi":"10.1111/cogs.13448","title":"Learning the Meanings of Function Words From Grounded Language Using a Visual Question Answering Model","year":2024,"lang":"en","type":"article","venue":"Cognitive Science","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Social Sciences and Humanities Research Council","keywords":"Function (biology); Question answering; Computer science; Meaning (existential); Artificial intelligence; Semantics (computer science); Visual reasoning; Natural language processing; Context (archaeology); Logical reasoning; Cognitive science; Linguistics; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000918096,0.0006697173,0.0004135039,0.0004152823,0.0002102354,0.001147781,0.001390943,0.001060569,0.002423408],"category_scores_gemma":[0.005286507,0.0004428966,0.001278675,0.0002226521,0.0009099828,0.002718855,0.0009199699,0.001711096,0.0004014079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008789172,"about_ca_system_score_gemma":0.0005812487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003089834,"about_ca_topic_score_gemma":0.003433353,"domain_scores_codex":[0.9996314,0.0001387689,0.00001894379,0.0001356994,0.00004014659,0.00003497042],"domain_scores_gemma":[0.998376,0.001066335,0.0001753232,0.0001732677,0.0001434528,0.00006560678],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004676979,0.000336364,0.01145164,0.0004517478,0.0002647974,0.0007835813,0.004423328,0.5615109,0.07044822,0.1722323,0.003015157,0.1746143],"study_design_scores_gemma":[0.00002131801,0.0000696656,0.0007005882,0.00001717006,0.00002765957,0.00006191425,0.0001201522,0.9357633,0.004055622,0.05838297,0.0007619031,0.00001769018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3573879,0.0001631524,0.6352383,0.0007234598,0.00003980333,0.00009541403,0.0003014519,0.001039761,0.005010674],"genre_scores_gemma":[0.8893181,0.0001022789,0.1068003,0.0001512769,0.00001453262,0.0001156825,0.0004169883,0.00007507657,0.003005742],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003089834,"threshold_uncertainty_score":0.008107126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01854238115936758,"score_gpt":0.3358049106398018,"score_spread":0.3172625294804343,"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."}}