{"id":"W4412022751","doi":"10.37236/12851","title":"Characterizations of Perfectly Clustering Words","year":2025,"lang":"en","type":"article","venue":"The Electronic Journal of Combinatorics","topic":"Advanced Algebra and Logic","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal; Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Natural language processing; Computer science; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004917863,0.0000805219,0.0001821036,0.0001271593,0.0001041919,0.00003065169,0.0009958307,0.00003035761,0.000002755014],"category_scores_gemma":[0.00006774531,0.00005476381,0.00008453194,0.0007506087,0.00003482538,0.000250898,0.0001332332,0.0003544114,0.000001113523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001144338,"about_ca_system_score_gemma":0.0003670913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.439773e-7,"about_ca_topic_score_gemma":9.987738e-7,"domain_scores_codex":[0.9990805,0.00007574466,0.000318984,0.00007468415,0.0001871216,0.0002630152],"domain_scores_gemma":[0.999087,0.0001397289,0.000302926,0.0002707838,0.0001737928,0.00002576203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000812512,0.00005116336,0.000139955,0.000008412751,0.0000330736,0.000001552503,0.0002133021,0.0002650681,0.001964456,0.9940073,0.000028064,0.003279566],"study_design_scores_gemma":[0.0005279236,0.000359749,0.001606352,0.00005611222,0.00002817784,0.00006600902,0.00005244332,0.003909287,0.00491799,0.9857081,0.002678214,0.00008967899],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08049219,0.001544495,0.9149535,0.001339382,0.0005847774,0.00005637366,1.414068e-7,0.00001479229,0.001014317],"genre_scores_gemma":[0.9989855,0.0003939046,0.0001715557,0.0001186022,0.00002726059,0.000001080001,1.3194e-7,0.000003801654,0.0002981192],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9184933,"threshold_uncertainty_score":0.2233203,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004797784448982438,"score_gpt":0.2333496507858884,"score_spread":0.2285518663369059,"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."}}