{"id":"W2110750141","doi":"","title":"Automatic detection of deception in child-produced speech using syntactic complexity features","year":2013,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Deception detection and forensic psychology","field":"Psychology","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Utterance; Deception; Sentence; Support vector machine; Computer science; Set (abstract data type); Artificial intelligence; Random forest; Measure (data warehouse); Natural language processing; Speech recognition; Pattern recognition (psychology); Machine learning; Psychology; Data mining; Social psychology","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":[0.0007643191,0.0001200487,0.0002600997,0.0002045621,0.00014569,0.00001804265,0.0001533217,0.0001507796,0.00007809643],"category_scores_gemma":[0.004876104,0.0001133603,0.000144234,0.0003892995,0.00007449533,0.00002821908,0.00003119618,0.000184359,0.0000176088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000251493,"about_ca_system_score_gemma":0.00002964392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003854388,"about_ca_topic_score_gemma":0.00006906747,"domain_scores_codex":[0.9983708,0.0002461965,0.0006561288,0.0002152927,0.0003201128,0.0001915255],"domain_scores_gemma":[0.9971058,0.0006224396,0.00112255,0.0001858206,0.0009360791,0.00002724575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009778397,0.00451922,0.450848,0.001324682,0.002258034,0.000003843327,0.01369118,0.2577409,0.05470102,0.1234475,0.01193654,0.07855128],"study_design_scores_gemma":[0.001791282,0.0001362923,0.8587577,0.0001611623,0.0001052659,0.0000237106,0.0004831126,0.08702328,0.003705894,0.04707916,0.0004890181,0.0002441635],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9874063,0.00002908127,0.003365439,0.0002233974,0.004065541,0.0006868414,0.00003181452,0.00005146808,0.004140131],"genre_scores_gemma":[0.9927102,5.488591e-7,0.006734697,0.00007188527,0.0002594093,0.00002252249,0.00001965745,0.00001766552,0.0001633927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4079097,"threshold_uncertainty_score":0.5837504,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03243081732255438,"score_gpt":0.3234808616065863,"score_spread":0.291050044284032,"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."}}