{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001603492,0.0000868749,0.0001915342,0.0002252535,0.0005339577,0.00003229783,0.0003908674,0.00008254636,0.00000172347],"category_scores_gemma":[0.0005903231,0.0000593535,0.00005185985,0.00170448,0.003459316,0.001647008,0.0001203544,0.0000876882,6.930097e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003173776,"about_ca_system_score_gemma":0.00004152275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001468414,"about_ca_topic_score_gemma":0.000002572662,"domain_scores_codex":[0.9990028,0.000005097406,0.0004465861,0.0001210258,0.0001902462,0.0002342378],"domain_scores_gemma":[0.9973789,0.0001266361,0.001216736,0.0002011806,0.001037806,0.00003867645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0007745654,0.0001480678,0.01827203,0.0002176299,0.000230761,2.00592e-9,0.03746262,0.000002847434,0.07695542,0.05694036,0.01431421,0.7946815],"study_design_scores_gemma":[0.004614812,0.00553364,0.1542563,0.0001019926,0.0002914232,0.0002691226,0.5108347,0.09181139,0.1184369,0.004610232,0.1085931,0.0006463766],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931209,0.0000418638,0.003567014,0.0005276126,0.0002984793,0.000692264,0.00004190095,0.0001169082,0.001593038],"genre_scores_gemma":[0.9958989,0.00006910878,0.003760651,0.0001126201,0.00001681683,0.000102151,0.000003917973,0.00000403175,0.00003182467],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7940351,"threshold_uncertainty_score":0.9992527,"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."}}