{"id":"W4387954531","doi":"10.22318/cscl2023.922487","title":"Supporting Collective Inquiry in a Critical Action Game: A Role for Open AI Conversational Agents","year":2023,"lang":"en","type":"article","venue":"Computer-supported collaborative learning/˜The œComputer-Supported Collaborative Learning Conference","topic":"Educational Games and Gamification","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Dystopia; Conversation; Context (archaeology); Computer science; Affordance; Narrative; Collective intelligence; Human–computer interaction; Sociology; Artificial intelligence; Communication; Linguistics","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":[0.002547066,0.0007084099,0.0002882058,0.0007505264,0.0025023,0.004526985,0.001661482,0.001401457,0.005204065],"category_scores_gemma":[0.006707735,0.0003192791,0.0004916044,0.0001848857,0.003810638,0.004688409,0.006170481,0.001911454,0.0007743417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008751638,"about_ca_system_score_gemma":0.001379202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001023104,"about_ca_topic_score_gemma":0.001502236,"domain_scores_codex":[0.9974759,0.00170977,0.00006219297,0.0002756983,0.0003086547,0.0001677522],"domain_scores_gemma":[0.9958863,0.002344205,0.000204944,0.0003410941,0.0002019719,0.001021613],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.001031109,0.001436392,0.00768402,0.0007849286,0.0001025013,0.001848495,0.1573002,0.00907669,0.08148836,0.4989323,0.009988889,0.2303261],"study_design_scores_gemma":[0.0004251243,0.00152199,0.002858514,0.0005824145,0.0001374338,0.001732875,0.03542642,0.1039235,0.02258752,0.2796434,0.5509205,0.0002404498],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2323697,0.0005373113,0.6189467,0.004636295,0.0003835986,0.0009335966,0.00007924974,0.002229536,0.1398841],"genre_scores_gemma":[0.7990602,0.0001249246,0.1884216,0.000414502,0.00004860041,0.0005708705,0.00004987793,0.0001523798,0.01115701],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005204065,"threshold_uncertainty_score":0.01740927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0831696516695471,"score_gpt":0.4275925494404919,"score_spread":0.3444228977709448,"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."}}