{"id":"W1974256760","doi":"10.1007/s10115-009-0237-8","title":"A general measure of similarity for categorical sequences","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Categorical variable; Similarity (geometry); Computer science; Data mining; Matching (statistics); Similarity measure; Pattern recognition (psychology); Artificial intelligence; Range (aeronautics); Domain (mathematical analysis); Measure (data warehouse); Process (computing); Sequence (biology); Noise (video); Mathematics; Machine learning; Statistics; Image (mathematics)","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":[],"consensus_categories":[],"category_scores_codex":[0.0002869693,0.0000579273,0.0001131149,0.00006209648,0.0000870053,0.0001209881,0.0002171129,0.00004160112,3.208749e-7],"category_scores_gemma":[0.00002311283,0.00004692666,0.00002365747,0.0001799967,0.00001536625,0.001568902,0.00002506785,0.00003174771,0.000008311342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001237544,"about_ca_system_score_gemma":0.00005029297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001632666,"about_ca_topic_score_gemma":7.955496e-7,"domain_scores_codex":[0.9994587,0.00001372798,0.0002680836,0.00007819594,0.00009018845,0.00009107185],"domain_scores_gemma":[0.9994388,0.00002808815,0.00009913321,0.0001704696,0.000217403,0.00004613843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002200736,0.00003021184,0.00004546435,0.00007122772,0.000007106214,5.779373e-8,0.002075634,0.00002778287,0.0001229826,0.7516168,0.007612942,0.2383875],"study_design_scores_gemma":[0.000392234,0.0001668516,0.001549219,0.00003000275,0.000007004767,0.00002048067,0.0001484351,0.6643068,0.0004486484,0.001540283,0.3312348,0.0001551619],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001893299,0.0004866376,0.9859663,0.0003157705,0.0001965208,0.0002968145,0.00003169511,0.00005999723,0.01075299],"genre_scores_gemma":[0.9850036,0.00002513041,0.01459537,0.00008393449,0.00009202908,0.00004693005,0.0000351677,0.000001267372,0.0001165849],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9831103,"threshold_uncertainty_score":0.1913614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02441613477272565,"score_gpt":0.2734250690558867,"score_spread":0.2490089342831611,"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."}}