{"id":"W1598033829","doi":"10.48550/arxiv.1209.3089","title":"Pattern Detection with Rare Item-set Mining","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Algoma University","funders":"","keywords":"Set (abstract data type); Computer science; Data mining; Artificial intelligence; Information retrieval; Pattern recognition (psychology); Programming language","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"],"consensus_categories":[],"category_scores_codex":[0.0001592461,0.0002462555,0.0002030892,0.0001968871,0.0001995023,0.0001693392,0.001335019,0.0001696405,0.00002161678],"category_scores_gemma":[0.00001245992,0.0002534511,0.00007760331,0.0005247438,0.00005696119,0.0005070851,0.001274004,0.0003604959,0.0001103542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001040525,"about_ca_system_score_gemma":0.00007874704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001548976,"about_ca_topic_score_gemma":0.000055006,"domain_scores_codex":[0.9985546,0.00005193398,0.0001372138,0.0008481321,0.00008864728,0.000319496],"domain_scores_gemma":[0.9981546,0.00006903994,0.0002191974,0.001263427,0.0001307138,0.0001629611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007037237,0.0006534026,0.0559635,0.0005294397,0.0008186984,0.0008623257,0.005732678,0.0526152,0.0003449991,0.04468986,0.004082368,0.8336372],"study_design_scores_gemma":[0.0005062784,0.00007926128,0.007885436,0.0002244547,0.0001213312,0.0000367639,0.0002735303,0.9829895,0.0004561785,0.001257104,0.005291745,0.0008783415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1803192,0.00003089102,0.8181231,0.00005741937,0.0002475547,0.000156032,0.00004582073,0.0002407761,0.0007791579],"genre_scores_gemma":[0.9894764,0.00003014207,0.009443489,0.00007853447,0.0001278011,0.000003871565,0.00005233215,0.00001785187,0.0007695521],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9303744,"threshold_uncertainty_score":0.9999918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07141462304812494,"score_gpt":0.1869632028222865,"score_spread":0.1155485797741615,"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."}}