{"id":"W1991725986","doi":"10.1002/meet.14504901045","title":"The art of creating an informative data collection for automated deception detection: A corpus of truths and lies","year":2012,"lang":"en","type":"article","venue":"Proceedings of the American Society for Information Science and Technology","topic":"Deception detection and forensic psychology","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Deception; Crowdsourcing; Computer science; Context (archaeology); Set (abstract data type); Task (project management); Data collection; Quality (philosophy); Credibility; Data science; Psychology; Social psychology; World Wide Web; Epistemology","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":[0.03893781,0.0009173402,0.001035286,0.008002131,0.006871294,0.006204331,0.003450596,0.003020231,0.005500101],"category_scores_gemma":[0.1198126,0.001032273,0.0008352618,0.006081224,0.008138574,0.006517029,0.00863781,0.004687688,0.002858231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002054001,"about_ca_system_score_gemma":0.003564678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003034094,"about_ca_topic_score_gemma":0.004859345,"domain_scores_codex":[0.9468008,0.0349195,0.004332027,0.003528935,0.009637488,0.0007811557],"domain_scores_gemma":[0.7599821,0.1165898,0.01039752,0.07306442,0.0356553,0.004310832],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002030011,0.003235634,0.0526193,0.0069525,0.000424716,0.003773572,0.0802462,0.01636149,0.06971189,0.07115383,0.1266286,0.5668624],"study_design_scores_gemma":[0.0005295204,0.001180577,0.07161598,0.004088877,0.0002433512,0.003024183,0.05897446,0.05752563,0.08026868,0.09342562,0.6283694,0.0007538372],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4417018,0.004585562,0.4592285,0.01798353,0.002180931,0.01063554,0.02745516,0.002976176,0.03325294],"genre_scores_gemma":[0.4883724,0.001255588,0.4645668,0.002134732,0.0006551996,0.01111327,0.02377319,0.001004271,0.007124398],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03893781,"threshold_uncertainty_score":0.2059253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02707782098050645,"score_gpt":0.3386298183028858,"score_spread":0.3115519973223794,"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."}}