{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2884364,0.001129357,0.001876769,0.002541048,0.003339242,0.00356335,0.002858331,0.004148501,0.001190635],"category_scores_gemma":[0.7079234,0.001239795,0.002203353,0.003173179,0.005650012,0.005255869,0.003974378,0.004180491,0.0004561419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001765197,"about_ca_system_score_gemma":0.002772357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004337637,"about_ca_topic_score_gemma":0.003959932,"domain_scores_codex":[0.7105502,0.2347498,0.02003574,0.01480606,0.01787779,0.001980306],"domain_scores_gemma":[0.1098994,0.8392358,0.008296896,0.0264089,0.01475968,0.00139935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01637701,0.001531963,0.3406557,0.001810624,0.004763205,0.001455308,0.008354795,0.07543158,0.03730179,0.01204996,0.004555818,0.4957123],"study_design_scores_gemma":[0.001707322,0.0104965,0.2350321,0.0007311294,0.004239452,0.004843597,0.002675488,0.6092784,0.09988889,0.02112314,0.009287248,0.0006968181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5959792,0.002485418,0.3933173,0.001850613,0.0005665157,0.0009254026,0.0003919808,0.001828819,0.002654774],"genre_scores_gemma":[0.8301458,0.0002171012,0.1674702,0.0003473823,0.00005977028,0.0005461763,0.0003405217,0.0003864044,0.0004865643],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2884364,"threshold_uncertainty_score":0.8774846,"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."}}