{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005353339,0.0002742274,0.0001576436,0.0001654004,0.0004548838,0.001169233,0.0004271057,0.0006847202,0.009543304],"category_scores_gemma":[0.003390853,0.000113087,0.0002187971,0.000111876,0.0004442522,0.001093886,0.0008734838,0.0004359569,0.001308277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002987364,"about_ca_system_score_gemma":0.0003072684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000863199,"about_ca_topic_score_gemma":0.001057097,"domain_scores_codex":[0.9994155,0.0003374446,0.00002275511,0.0000985412,0.00008974828,0.00003606727],"domain_scores_gemma":[0.9983809,0.001067853,0.0001556129,0.0001708195,0.0001128484,0.0001120614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001738274,0.001744655,0.01140569,0.001295018,0.0001593241,0.004386992,0.03221953,0.009611687,0.563596,0.04145754,0.014021,0.3183643],"study_design_scores_gemma":[0.0007114675,0.005915779,0.05584976,0.0004049276,0.0003540356,0.006886428,0.01338406,0.1790704,0.2597865,0.03998502,0.4372689,0.0003827096],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6947337,0.0005057877,0.2444689,0.001383128,0.0001700771,0.0004582767,0.0003820062,0.00333981,0.05455835],"genre_scores_gemma":[0.9290025,0.0001474183,0.05506755,0.0001886923,0.00003862647,0.0002182053,0.0001676141,0.00009024693,0.01507909],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009543304,"threshold_uncertainty_score":0.0319255,"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."}}