{"id":"W4403905936","doi":"10.59934/jaiea.v4i1.644","title":"Application of the KARP RABIN Algorithm for Plagiarism Detection System in Thesis Proposal Submission in the Department of Informatics Engineering STMIK Kaputama","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Informatics; Health informatics; Plagiarism detection; Software engineering; Engineering; Medicine; Information retrieval; Electrical engineering; Nursing","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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002347782,0.0007379432,0.000846928,0.004139063,0.001390477,0.001831298,0.000925757,0.000802804,0.006912511],"category_scores_gemma":[0.007209235,0.0002444609,0.0004372588,0.002351088,0.0002911995,0.001500628,0.0007547548,0.0007275934,0.004594293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008383456,"about_ca_system_score_gemma":0.001538187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001762035,"about_ca_topic_score_gemma":0.00190997,"domain_scores_codex":[0.9979588,0.0002771808,0.0002608362,0.0004983913,0.0008598336,0.0001448779],"domain_scores_gemma":[0.9962631,0.0009593694,0.0004893182,0.000321988,0.001829092,0.0001371016],"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":[0.0004375428,0.0002097556,0.006331819,0.0002875681,0.00004388996,0.0003686539,0.0004987486,0.005284813,0.02960261,0.002129266,0.01913514,0.9356703],"study_design_scores_gemma":[0.0001675729,0.0007801404,0.02651569,0.0001121263,0.0001385781,0.001893452,0.001444879,0.6468959,0.2471523,0.007635168,0.06706198,0.0002021888],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2403006,0.002148146,0.7055495,0.002267179,0.000675173,0.001097996,0.002187961,0.02701087,0.0187626],"genre_scores_gemma":[0.4760258,0.0007982416,0.5015463,0.0001993109,0.000169121,0.0005784963,0.002821191,0.0004037398,0.01745777],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9991972,"threshold_uncertainty_score":0.02312464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01300149316848713,"score_gpt":0.2489049778811379,"score_spread":0.2359034847126508,"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."}}