{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.002445869,0.0003624021,0.0004445174,0.0003349218,0.0008113739,0.000314891,0.0004933259,0.005705793,0.0002476084],"category_scores_gemma":[0.002727735,0.0003377382,0.00011233,0.0005409481,0.000072898,0.000283618,0.00009791573,0.01144291,0.0001302336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002136492,"about_ca_system_score_gemma":0.0007339167,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008531113,"about_ca_topic_score_gemma":0.01399979,"domain_scores_codex":[0.9971304,0.0001623675,0.0005313831,0.0007508448,0.0007884538,0.0006365498],"domain_scores_gemma":[0.99853,0.0006901607,0.0001160852,0.0001587563,0.0001664965,0.0003384575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00009230179,0.00001391811,0.002815509,0.0003519161,0.0001451611,0.00001973101,0.7041284,0.0001213353,0.00004918076,0.1653903,0.006329247,0.120543],"study_design_scores_gemma":[0.0001409229,0.00008821387,0.0001206574,0.01310502,0.0004507404,0.000009862,0.6208316,0.06323187,0.00009077992,0.2804955,0.01989438,0.001540479],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6883643,0.007579348,0.005518069,0.007225538,0.004179271,0.0009209962,0.00002621643,0.0007713093,0.285415],"genre_scores_gemma":[0.8988429,0.003886206,0.008078377,0.001543214,0.003201301,0.00007861366,0.0001304467,0.00009906294,0.08413989],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2104786,"threshold_uncertainty_score":0.9999075,"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."}}