{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007723648,0.0008203998,0.0004485723,0.0003096738,0.0002268759,0.001014901,0.002028347,0.001273215,0.01535559],"category_scores_gemma":[0.003153324,0.000356499,0.0004302131,0.0001643493,0.001224407,0.001779006,0.002339829,0.001853505,0.00365104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002965011,"about_ca_system_score_gemma":0.0006363088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001663043,"about_ca_topic_score_gemma":0.001579406,"domain_scores_codex":[0.9994357,0.0002081446,0.00003175986,0.0001376262,0.0001283856,0.00005822993],"domain_scores_gemma":[0.9990314,0.0006058133,0.00004118992,0.0001797216,0.00006777742,0.00007405459],"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":[0.001348598,0.0007740705,0.001194411,0.001162971,0.0001173667,0.001347597,0.001542895,0.1100513,0.1384488,0.07927245,0.02181055,0.642929],"study_design_scores_gemma":[0.0007591869,0.000970241,0.0007969649,0.0001832225,0.00006995929,0.000604309,0.0001823992,0.7636481,0.1231271,0.04672572,0.06280754,0.0001252649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0165774,0.0001565071,0.9287253,0.0002516551,0.0001029592,0.0002356734,0.0003099759,0.04069901,0.01294146],"genre_scores_gemma":[0.398878,0.0003271973,0.5823277,0.0002547717,0.00003327845,0.000584121,0.0008100094,0.002301471,0.0144835],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01535559,"threshold_uncertainty_score":0.05136955,"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."}}