{"id":"W2148900457","doi":"10.1109/icdm.2008.43","title":"SCS: A New Similarity Measure for Categorical Sequences","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Categorical variable; Similarity (geometry); Computer science; Matching (statistics); Task (project management); Data mining; Artificial intelligence; Pattern recognition (psychology); Range (aeronautics); Sequence (biology); Measure (data warehouse); Similarity measure; Noise (video); Process (computing); Natural language processing; Machine learning; Mathematics; 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":[0.0001164683,0.00007075749,0.00008675151,0.00002594651,0.0002139536,0.00006802801,0.0006646871,0.00003673534,0.00001306437],"category_scores_gemma":[0.00004157664,0.00005633568,0.00004156153,0.000239189,0.00003454778,0.0003095156,0.00008606724,0.00005511863,0.00004389781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001672595,"about_ca_system_score_gemma":0.0002057818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002651173,"about_ca_topic_score_gemma":0.00002669394,"domain_scores_codex":[0.9992766,0.000008318762,0.0001119172,0.0002795215,0.0001523862,0.0001712821],"domain_scores_gemma":[0.999359,0.00006399182,0.00002653961,0.000368771,0.0000628527,0.0001189111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002653559,0.0001150516,0.0003868287,0.000006236141,0.00001858564,0.00001013731,0.0007268786,0.00002598037,0.0002830171,0.4657309,0.3151156,0.2175782],"study_design_scores_gemma":[0.0009930891,0.0002556924,0.00379562,0.00001028074,0.00001649421,0.0002946843,0.0000690674,0.3636191,0.003717922,0.09546191,0.5310517,0.000714495],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004380248,0.00005381438,0.9918854,0.004731921,0.000080062,0.0001311169,0.000006101865,0.0001795985,0.002493958],"genre_scores_gemma":[0.1013001,0.00001344149,0.8946334,0.0006693348,0.0001765571,0.00005257638,0.00001040288,0.000005285771,0.003138906],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.370269,"threshold_uncertainty_score":0.2297302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07981175858382283,"score_gpt":0.2826599722391048,"score_spread":0.2028482136552819,"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."}}