{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004743072,0.0007437362,0.001874827,0.01169888,0.001315731,0.005115619,0.002552881,0.002473124,0.003898898],"category_scores_gemma":[0.02912906,0.0003530623,0.001561679,0.01308108,0.00247943,0.009679774,0.003245906,0.001948486,0.001632949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001368721,"about_ca_system_score_gemma":0.00126099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007331315,"about_ca_topic_score_gemma":0.0006955389,"domain_scores_codex":[0.9895984,0.00188504,0.001762321,0.002547988,0.003780293,0.0004259386],"domain_scores_gemma":[0.9887316,0.004154519,0.001257788,0.002654615,0.002663011,0.0005384806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005334046,0.0004182734,0.02348525,0.001682411,0.0007539369,0.0005963148,0.001421844,0.0124022,0.03142103,0.4322059,0.01052589,0.4845535],"study_design_scores_gemma":[0.00007429229,0.001005067,0.021629,0.0005353868,0.0003416663,0.005960668,0.001141182,0.1268582,0.009745094,0.780867,0.05160337,0.0002390132],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04520677,0.00312169,0.9387853,0.0005631897,0.0004009666,0.0003648917,0.002099721,0.000668155,0.008789389],"genre_scores_gemma":[0.3883388,0.00225375,0.5961605,0.0005870986,0.0007454078,0.000923077,0.00518264,0.0001972318,0.005611462],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01169888,"threshold_uncertainty_score":0.02508402,"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."}}