{"id":"W2896348621","doi":"10.1007/978-3-030-01298-4_2","title":"A Self-representation Model for Robust Clustering of Categorical Sequences","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Cluster analysis; Categorical variable; Computer science; Pattern recognition (psychology); Artificial intelligence; Pairwise comparison; Representation (politics); CURE data clustering algorithm; Similarity (geometry); Correlation clustering; Noise (video); Data mining; Subspace topology; Machine learning; 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":[0.002706427,0.0006549809,0.001491477,0.001924077,0.0007518224,0.002015358,0.004383781,0.002608766,0.003277227],"category_scores_gemma":[0.008507132,0.0007121093,0.00202977,0.002524185,0.001405753,0.003622704,0.002790636,0.002390277,0.001951857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001826631,"about_ca_system_score_gemma":0.001307846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005420919,"about_ca_topic_score_gemma":0.005222634,"domain_scores_codex":[0.9978885,0.0006116253,0.0001275317,0.0006913842,0.0004808895,0.000199966],"domain_scores_gemma":[0.9961766,0.001379515,0.0003799213,0.001088234,0.0007946101,0.0001811127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003487237,0.0002131408,0.001457904,0.000192177,0.0001857298,0.0001056029,0.0003461679,0.5142828,0.00747615,0.1951279,0.00815564,0.272108],"study_design_scores_gemma":[0.000005163002,0.00002304997,0.0001089826,0.00000684166,0.000009885081,0.00002285646,0.00001128245,0.9695438,0.0004853727,0.02917246,0.000599732,0.00001064392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005192594,0.00008932473,0.9937156,0.00009866059,0.00002570249,0.0000244736,0.0001206061,0.0003885481,0.0003445414],"genre_scores_gemma":[0.356146,0.0004757923,0.6279228,0.0004481696,0.0002701223,0.0004613303,0.002625607,0.0005757905,0.01107433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005420919,"threshold_uncertainty_score":0.0143131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05873108898476034,"score_gpt":0.3234088260772834,"score_spread":0.2646777370925231,"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."}}