{"id":"W4380355772","doi":"10.1613/jair.1.14157","title":"Your Prompt is My Command: On Assessing the Human-Centred Generality of Multimodal Models","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agencia Estatal de Investigación; Directorate-General for Communications Networks, Content and Technology; European Regional Development Fund; Generalitat Valenciana; Social Sciences and Humanities Research Council of Canada; Defense Advanced Research Projects Agency; European Commission; Universitat Politècnica de València; Future of Life Institute","keywords":"Generality; Computer science; Human–computer interaction; Cognition; Process (computing); Artificial intelligence; Cognitive science; Psychology; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.004479441,0.0001260094,0.0003020125,0.0004484924,0.000477829,0.0004064892,0.002010008,0.0000853181,0.00002614025],"category_scores_gemma":[0.0004613918,0.0000798277,0.0001775628,0.001141412,0.0003558669,0.0005805594,0.0004113881,0.000734442,0.00004976775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007615482,"about_ca_system_score_gemma":0.000273006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000289614,"about_ca_topic_score_gemma":0.00002358065,"domain_scores_codex":[0.9962688,0.0005775678,0.000806966,0.0002507193,0.001558182,0.0005377275],"domain_scores_gemma":[0.9971399,0.0008902274,0.0003140108,0.0005806201,0.000964225,0.0001110694],"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":[0.0001880538,0.001316276,0.001471804,0.000121068,0.0002341688,0.000365134,0.0380248,0.04387786,0.08578143,0.2454474,0.009838687,0.5733333],"study_design_scores_gemma":[0.00006943614,0.0003155655,0.001564505,0.0001447077,0.000005841988,0.00001828347,0.005268934,0.6368305,0.1614157,0.1940627,0.0001753914,0.0001284331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8448665,0.0002775395,0.142393,0.0109194,0.0005199401,0.0002750369,0.000002753854,0.00004545859,0.0007003862],"genre_scores_gemma":[0.9963483,0.0001402372,0.003084925,0.00008406084,0.0002467447,0.000003480579,4.099224e-7,0.00000823514,0.00008361838],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5929526,"threshold_uncertainty_score":0.3919785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5477049452645087,"score_gpt":0.5082094541283876,"score_spread":0.03949549113612116,"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."}}