{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009268192,0.0002791668,0.0003465033,0.000128948,0.0002866179,0.0007355369,0.002384979,0.0001183188,0.00004369406],"category_scores_gemma":[0.0001848556,0.0001729811,0.00023137,0.0005436881,0.0003105951,0.0006488661,0.0004213608,0.0004636778,0.00006002192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006941707,"about_ca_system_score_gemma":0.000176219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005173642,"about_ca_topic_score_gemma":0.00001110812,"domain_scores_codex":[0.9973009,0.00003998087,0.0008183698,0.0006917281,0.0007630452,0.0003859998],"domain_scores_gemma":[0.9981502,0.0001646341,0.0004394298,0.0006364789,0.0005189967,0.00009026211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003676179,0.0002583805,0.0001501286,0.0001529786,0.00004838927,0.000001859644,0.00730905,0.0004682851,0.1172617,0.8331396,0.0005243586,0.04064855],"study_design_scores_gemma":[0.00003387026,0.00009880754,0.0004706534,0.0006216913,0.00001217633,0.000004271129,0.0007440026,0.2315609,0.5780693,0.1881136,0.00007070101,0.0001999982],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9432436,0.0001888524,0.01869715,0.007801174,0.00148977,0.001249222,0.00002604111,0.0002704897,0.02703376],"genre_scores_gemma":[0.9982726,0.00002042412,0.001160424,0.0002015459,0.0001481081,0.00002804731,8.745657e-7,0.0000152945,0.0001526743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.645026,"threshold_uncertainty_score":0.7092798,"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."}}