{"id":"W4401631931","doi":"10.22215/etd/2024-15985","title":"Predicting Threats to Academic Integrity: A Text-Mining and Scenario Modeling Framework","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Academic integrity and plagiarism","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Cheating; Computer science; Stylometry; Adversarial system; Data science; Phishing; Copying; Artificial intelligence; Computer security; World Wide Web; Psychology; Social psychology; Political science","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":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005273897,0.001446037,0.0007757262,0.007064481,0.001025753,0.00346018,0.002004726,0.002755893,0.002093436],"category_scores_gemma":[0.019128,0.0005595637,0.001959545,0.003306422,0.001136605,0.006319597,0.001730745,0.00249149,0.001121351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00211913,"about_ca_system_score_gemma":0.001275801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005215891,"about_ca_topic_score_gemma":0.005516037,"domain_scores_codex":[0.996332,0.001987688,0.000302923,0.0007007286,0.000474273,0.0002024643],"domain_scores_gemma":[0.9758096,0.01931698,0.002203374,0.00100665,0.001043415,0.0006200254],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004345421,0.001395622,0.08801661,0.0006368357,0.0005524418,0.001820007,0.001985135,0.56931,0.002347174,0.0647273,0.01413818,0.2546361],"study_design_scores_gemma":[0.0000121985,0.0000719114,0.003021801,0.00006847825,0.00003108472,0.0001694777,0.0004070371,0.9565644,0.0004687022,0.03615504,0.003002658,0.00002719083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2655697,0.002459682,0.6947595,0.01411638,0.0002565862,0.001338939,0.009390983,0.001671119,0.0104371],"genre_scores_gemma":[0.7956472,0.0009950181,0.1904571,0.0006760629,0.0003359233,0.0006699493,0.00863553,0.00008147747,0.002501686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9972441,"threshold_uncertainty_score":0.02789134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.051371654340354,"score_gpt":0.3777493348622184,"score_spread":0.3263776805218644,"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."}}