{"id":"W3199661966","doi":"10.1515/pjbr-2021-0028","title":"Use and usability of software verification methods to detect behaviour interference when teaching an assistive home companion robot: A proof-of-concept study","year":2021,"lang":"en","type":"article","venue":"Paladyn Journal of Behavioral Robotics","topic":"Social Robot Interaction and HRI","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Engineering and Physical Sciences Research Council; Royal Academy of Engineering","keywords":"Robot; Usability; Human–computer interaction; Computer science; Personalization; Human–robot interaction; Software; Interference (communication); Artificial intelligence; World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.001110164,0.0002169638,0.0006938111,0.0001950182,0.0001088256,0.00008144094,0.0002689996,0.000142126,0.0001782185],"category_scores_gemma":[0.0005210667,0.0002116777,0.0001697236,0.0001978425,0.000120909,0.0004098171,0.0001007752,0.0006845958,0.000001140646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001315391,"about_ca_system_score_gemma":0.0001126917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003647792,"about_ca_topic_score_gemma":0.0001857039,"domain_scores_codex":[0.9963368,0.001675563,0.001107159,0.0003321086,0.0003284947,0.0002198557],"domain_scores_gemma":[0.9969586,0.0004038977,0.0009260649,0.0004098529,0.001067236,0.0002343599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003941468,0.003756467,0.7861904,0.00002036965,0.0001298596,0.00004624276,0.04170637,0.001406142,0.008772283,0.00009491913,0.00004629121,0.1574365],"study_design_scores_gemma":[0.0008243545,0.003131998,0.9649532,0.0001460068,0.0005145048,0.0001001807,0.02199,0.0000587777,0.007888679,0.0001431738,0.00001060777,0.0002384757],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7004647,0.00007070525,0.298316,0.00005472706,0.0008017433,0.0002573643,0.00001657644,0.00001165978,0.000006520616],"genre_scores_gemma":[0.8101545,0.000001315874,0.189692,0.00001839677,0.00005646431,0.000007448838,0.000006293632,0.00002162765,0.00004195738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1787628,"threshold_uncertainty_score":0.8631965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1557848323534539,"score_gpt":0.4525489895193135,"score_spread":0.2967641571658597,"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."}}