{"id":"W2151534635","doi":"10.1177/0165551506064361","title":"Sample size and informetric model goodness-of-fit outcomes: a search engine log case study","year":2006,"lang":"en","type":"article","venue":"Journal of Information Science","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Goodness of fit; Sample size determination; Sample (material); Statistics; Computer science; Mathematics; Data mining","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003426982,0.0001161954,0.0002397029,0.001418009,0.0002675249,0.0004990308,0.0008593124,0.00003621982,0.000007453209],"category_scores_gemma":[0.001169664,0.00008217915,0.00006459915,0.002936423,0.0001744144,0.01478127,0.0002762923,0.0002201741,0.000007013927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008609817,"about_ca_system_score_gemma":0.0006572008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002059536,"about_ca_topic_score_gemma":0.000003841727,"domain_scores_codex":[0.9968096,0.00002326218,0.001152628,0.00007808321,0.001652584,0.0002838474],"domain_scores_gemma":[0.9968383,0.0004155003,0.00062096,0.0002630529,0.001689817,0.0001723597],"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":[0.0002155925,0.001659827,0.2684879,0.0003768437,0.00008890665,0.0004055634,0.09705468,0.2302238,0.001039507,0.05791152,0.0004151109,0.3421207],"study_design_scores_gemma":[0.002420352,0.0009853854,0.1614431,0.00002745654,0.00002151717,0.002848157,0.007258119,0.8222202,0.001522592,0.0007721915,0.000171434,0.0003094572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.666166,0.000005895174,0.333186,0.00007690036,0.00009576273,0.0001611328,0.000005372667,0.00001203318,0.0002909578],"genre_scores_gemma":[0.9582853,0.000006250137,0.04157204,0.0001003322,0.00001091388,0.00000186109,2.768761e-7,0.000001570424,0.00002141636],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5919964,"threshold_uncertainty_score":0.9989985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05333578672184987,"score_gpt":0.3381249566369604,"score_spread":0.2847891699151106,"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."}}