{"id":"W4393146392","doi":"10.1609/aaai.v38i20.30612","title":"Your Prompt Is My Command: On Assessing the Human-Centred Generality of Multimodal Models (Abstract Reprint)","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reprint; Generality; Computer science; Cognitive science; Psychology; Human–computer interaction; Psychotherapist; Physics","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":[0.03715419,0.0006531034,0.0004528305,0.001915392,0.0009237094,0.005421076,0.0008951942,0.001664991,0.004553299],"category_scores_gemma":[0.2452154,0.0004037189,0.0006354268,0.001142474,0.004111698,0.008624887,0.005165283,0.001721463,0.0006139264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001648155,"about_ca_system_score_gemma":0.0005307523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001941232,"about_ca_topic_score_gemma":0.00190159,"domain_scores_codex":[0.9857896,0.01026314,0.0006453898,0.00124609,0.001785525,0.0002702927],"domain_scores_gemma":[0.7550524,0.2178308,0.006753521,0.01179512,0.006388035,0.002180208],"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":[0.008052161,0.001437371,0.1819834,0.003174846,0.0007639152,0.0005966981,0.0770357,0.0681271,0.01927555,0.0592889,0.01199674,0.5682676],"study_design_scores_gemma":[0.0005029057,0.008309297,0.3548434,0.002560782,0.000698849,0.001580242,0.05831783,0.3457135,0.02330907,0.1740206,0.02913518,0.001008367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.861816,0.001761442,0.1023118,0.002164271,0.0001484325,0.001034411,0.0004459193,0.0006136691,0.02970405],"genre_scores_gemma":[0.9681341,0.0003873625,0.02986798,0.0002673098,0.00003410372,0.0002677361,0.0001911595,0.00008002968,0.0007702029],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03715419,"threshold_uncertainty_score":0.1964924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.212102811081108,"score_gpt":0.3623498035420163,"score_spread":0.1502469924609083,"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."}}