{"id":"W4402512774","doi":"10.1038/s41598-024-72071-1","title":"Large language models predict human sensory judgments across six modalities","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Categorization, perception, and language","field":"Psychology","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; NOMIS Stiftung","keywords":"Perception; Computer science; Pairwise comparison; Variation (astronomy); Modalities; Natural language processing; Artificial intelligence; Similarity (geometry); Task (project management); Modality (human–computer interaction); Visual perception; Cognition; Cognitive psychology; Psychology; Image (mathematics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001505123,0.000205191,0.0001981033,0.0001973049,0.000605577,0.0006713889,0.0001568649,0.0001468475,0.00524832],"category_scores_gemma":[0.00002232657,0.0001892644,0.0001532377,0.0004306036,0.0002337608,0.0004002208,0.00008237023,0.0001794448,0.0004027254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007955313,"about_ca_system_score_gemma":0.00006849397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003950685,"about_ca_topic_score_gemma":0.0003563777,"domain_scores_codex":[0.9971998,0.00009153838,0.0005442922,0.001024096,0.0005389595,0.0006013122],"domain_scores_gemma":[0.9985518,0.00002426829,0.0001127434,0.001078567,0.00009774212,0.0001348498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002396677,0.0006135017,0.009304348,0.0003528221,0.0002982035,0.006674218,0.6355664,0.0004470992,0.05498352,0.03062571,0.2587543,0.002355989],"study_design_scores_gemma":[0.002223754,0.00027261,0.03471518,0.0005638478,0.0004166818,0.004354238,0.2639437,0.008346851,0.009213812,0.1218584,0.550781,0.003309981],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9481734,0.001271417,0.001449465,0.00004296988,0.01573798,0.0003103626,0.0001388412,0.0005627401,0.0323128],"genre_scores_gemma":[0.7682623,0.00000286867,0.00001868731,0.00004389271,0.0003770725,0.00004031609,0.0006054176,0.00003679133,0.2306127],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3716227,"threshold_uncertainty_score":0.995661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02987171211641267,"score_gpt":0.3489717679857248,"score_spread":0.3191000558693122,"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."}}