{"id":"W4413945335","doi":"10.1145/3765284","title":"Designing Smarter Conversational Agents for Kids: Lessons from Cognitive Work and Means-Ends Analyses","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Computer-Human Interaction","topic":"AI in Service Interactions","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Work (physics); Cognition; Computer science; Psychology; Human–computer interaction; Cognitive science; Data science; Engineering; Neuroscience; Mechanical engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001689602,0.0003415798,0.0003232494,0.0006780963,0.0008662224,0.0005571655,0.0007119644,0.0001472763,0.0001677119],"category_scores_gemma":[0.00003996539,0.0003750423,0.0002324063,0.0005900121,0.00008164694,0.001449871,0.00006235833,0.0004683041,0.00003682205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002523345,"about_ca_system_score_gemma":0.00007214934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002182331,"about_ca_topic_score_gemma":0.0001678511,"domain_scores_codex":[0.9978211,0.000183032,0.0005308363,0.0008739261,0.0002691572,0.0003219738],"domain_scores_gemma":[0.9962804,0.002353103,0.0002194452,0.0006602482,0.0003710534,0.000115776],"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":[0.001161228,0.002996131,0.002626149,0.0002266184,0.005911747,0.00003993378,0.01255676,0.02971458,0.007139358,0.01478901,0.01675997,0.9060785],"study_design_scores_gemma":[0.01069095,0.001941821,0.05313603,0.004088431,0.001956326,0.00007758749,0.004158683,0.7810308,0.05882474,0.05234037,0.02842836,0.003325853],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01965038,0.00002061035,0.9723389,0.004278575,0.002650798,0.0004363355,0.0000632457,0.0002953858,0.0002658035],"genre_scores_gemma":[0.8867838,0.00001140057,0.1105652,0.001709774,0.0001682503,0.0002169341,0.0000928197,0.00002350838,0.0004283758],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9027526,"threshold_uncertainty_score":0.9998701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09819109148931882,"score_gpt":0.39207439652124,"score_spread":0.2938833050319212,"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."}}