{"id":"W6967949380","doi":"10.5281/zenodo.12011535","title":"Scarlet Cloak and the Forest Adventure: The Issue of False Positives in AI Detection Tools","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Generative grammar; Grammar; False positive paradox; Production (economics); Selection (genetic algorithm); Discipline; Natural language generation; Prototype theory","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":[0.1537788,0.001457212,0.002116653,0.006755528,0.008316663,0.01647985,0.006111692,0.02095391,0.008756043],"category_scores_gemma":[0.5260125,0.002079337,0.001471263,0.003287603,0.03358899,0.03381523,0.006649079,0.02370536,0.005625857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00476627,"about_ca_system_score_gemma":0.005090973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01274002,"about_ca_topic_score_gemma":0.01186426,"domain_scores_codex":[0.8696675,0.07970145,0.004907495,0.011678,0.0326433,0.001402197],"domain_scores_gemma":[0.2804424,0.6576562,0.01183023,0.02032756,0.02710216,0.002641521],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005874207,0.0001545748,0.01547345,0.0007900279,0.0001753202,0.0025141,0.02113247,0.002003147,0.001173971,0.2091831,0.3283562,0.4184562],"study_design_scores_gemma":[0.0002236581,0.000258666,0.005398628,0.003222941,0.0001816494,0.006546316,0.007938785,0.01623208,0.004948849,0.574902,0.3796309,0.0005155471],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.01093686,0.02323151,0.09429735,0.8292681,0.005892735,0.000200181,0.0002915297,0.002384764,0.03349699],"genre_scores_gemma":[0.3295843,0.01295341,0.2409756,0.359378,0.01170971,0.0008894934,0.0003463404,0.003517448,0.04064582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1537788,"threshold_uncertainty_score":0.8132699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02969739178697276,"score_gpt":0.3148960804134628,"score_spread":0.28519868862649,"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."}}