{"id":"W4221155737","doi":"10.48550/arxiv.2203.09016","title":"Natural Language Communication with a Teachable Agent","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Social Robot Interaction and HRI","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Context (archaeology); Task (project management); Modality (human–computer interaction); Human–computer interaction; Natural (archaeology); Psychology; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001356712,0.0001878191,0.0002091534,0.0001530047,0.0002513018,0.00003522392,0.0006210103,0.0001498969,0.009245368],"category_scores_gemma":[0.00001051549,0.0002081931,0.000137821,0.0002325648,0.00008294657,0.00007313722,0.0006115002,0.001223513,0.0003380463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003400075,"about_ca_system_score_gemma":0.00006269416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002584655,"about_ca_topic_score_gemma":0.0004716348,"domain_scores_codex":[0.9987985,0.0003188619,0.0001149628,0.00048539,0.00006748111,0.0002148395],"domain_scores_gemma":[0.9986443,0.00009178974,0.0002113984,0.0009247572,0.00005634908,0.00007141258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003784431,0.002795982,0.03404985,0.0002173814,0.003917072,0.003841246,0.1059262,0.06065612,0.000139942,0.6737433,0.09902939,0.01189905],"study_design_scores_gemma":[0.01150049,0.001055671,0.08080569,0.0005551261,0.001996293,0.0001652751,0.3732471,0.03786011,0.00008722708,0.01297533,0.4743477,0.005403947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7845639,0.001011332,0.001711907,0.0003205264,0.001873505,0.0005055614,0.00003892011,0.0003540959,0.2096202],"genre_scores_gemma":[0.9146113,0.00006609329,0.00009552947,0.0002655531,0.00005911033,0.000006096778,0.0001575985,0.00002602884,0.08471273],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.660768,"threshold_uncertainty_score":0.9916603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08951936729686967,"score_gpt":0.2635410743718338,"score_spread":0.1740217070749641,"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."}}