{"id":"W7124252028","doi":"10.65109/jspm5155","title":"GLIDE-RL: Grounded Language Instruction through DEmonstration in RL","year":2024,"lang":"","type":"article","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Institut national de psychiatrie légale Philippe-Pinel","funders":"","keywords":"Natural language; Natural (archaeology); Grounded theory; Process (computing); Language acquisition; Language understanding","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000737077,0.0003043041,0.0002748789,0.0002662429,0.0001929712,0.001467576,0.0003942219,0.000220482,0.0001947062],"category_scores_gemma":[0.00005592397,0.0002883307,0.0001447324,0.00110847,0.00005861728,0.00236719,0.0001468756,0.000665561,0.0005819389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003596343,"about_ca_system_score_gemma":0.0002109229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003744158,"about_ca_topic_score_gemma":0.0005351732,"domain_scores_codex":[0.9972397,0.000246786,0.0007099009,0.0008407961,0.0004571934,0.0005056271],"domain_scores_gemma":[0.9992452,0.0001160558,0.0001051309,0.0003851615,0.00007784867,0.00007064111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006616192,0.00003576716,0.0003746203,0.0001624419,0.00003168465,0.0001804027,0.01576362,0.0008185214,0.00190435,0.8308536,0.00009578916,0.1497726],"study_design_scores_gemma":[0.0008797401,0.000559859,0.004703401,0.003816237,0.00004735787,0.0005671612,0.01507351,0.8342085,0.02005114,0.01303453,0.1054857,0.001572938],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1382047,0.002424208,0.814114,0.0005812097,0.007032306,0.000341897,0.000001397166,0.0003779101,0.03692239],"genre_scores_gemma":[0.9658372,0.00008514304,0.007253889,0.00008053034,0.0007901108,0.00001388133,0.000003560556,0.00002464067,0.02591104],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8333899,"threshold_uncertainty_score":0.9999569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02504444577938426,"score_gpt":0.2864841911238958,"score_spread":0.2614397453445115,"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."}}