{"id":"W2027244665","doi":"10.1016/j.forsciint.2010.03.017","title":"The impact of data degradation and sample size on the performance of two similarity coefficients used in behavioural linkage analysis","year":2010,"lang":"en","type":"article","venue":"Forensic Science International","topic":"Crime Patterns and Interventions","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Jaccard index; Replicate; Optimal distinctiveness theory; Similarity (geometry); Statistics; Metric (unit); Sample (material); Econometrics; Computer science; Index (typography); Data mining; Mathematics; Psychology; Artificial intelligence; Social psychology; Engineering; Cluster analysis","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":[0.002190173,0.00005141201,0.00008112111,0.00013532,0.0003425162,0.0001018587,0.0009848583,0.00002006236,0.000301213],"category_scores_gemma":[0.001719791,0.00002969911,0.00006868161,0.0006964562,0.001324164,0.0003655658,0.0001603651,0.0001294655,8.538809e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004830585,"about_ca_system_score_gemma":0.0001129036,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01657975,"about_ca_topic_score_gemma":0.03272177,"domain_scores_codex":[0.9988372,0.00004464623,0.0002221993,0.0001701169,0.0005852105,0.0001405847],"domain_scores_gemma":[0.998405,0.0008777201,0.0001594257,0.0003063068,0.0002180157,0.00003346898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009331471,0.00006403391,0.9913383,4.8976e-7,0.00002090598,7.473983e-8,0.0008414145,0.0001267979,0.0009944958,0.003102703,0.0000401272,0.003461286],"study_design_scores_gemma":[0.0001255749,0.00005049156,0.940602,0.00001121458,0.00001757569,2.251005e-7,0.000413772,0.05728643,0.001055598,0.0003741409,0.00002573531,0.0000372394],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9984842,0.000002105113,0.0001401317,0.0005232753,0.0002429387,0.00009918081,0.0001763973,0.000003451084,0.0003283],"genre_scores_gemma":[0.9996035,0.000006304056,0.000292732,0.00001026735,0.00002474188,0.000002638542,0.00001422601,0.000001553937,0.0000440123],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05715964,"threshold_uncertainty_score":0.989969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.104765974948815,"score_gpt":0.4303907387873523,"score_spread":0.3256247638385373,"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."}}