{"id":"W4386084618","doi":"10.1002/ajpa.24836","title":"Morphological variability or inter‐observer bias? A methodological toolkit to improve data quality of multi‐researcher datasets for the analysis of morphological variation","year":2023,"lang":"en","type":"article","venue":"American Journal of Biological Anthropology","topic":"Primate Behavior and Ecology","field":"Psychology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Lemur; Kurtosis; Sexual dimorphism; Statistics; Biology; Sample size determination; Variation (astronomy); Data quality; Skewness; Statistical hypothesis testing; Ecology; Zoology; Mathematics; Metric (unit); Primate","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":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01882849,0.0003574624,0.002545396,0.0005029584,0.0001609875,0.00001687793,0.002730146,0.0005090444,0.006344438],"category_scores_gemma":[0.02235517,0.0001759876,0.0006560335,0.002586662,0.004900835,0.0001082592,0.001608339,0.0007051072,0.00003064696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008392469,"about_ca_system_score_gemma":0.0001213323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001425712,"about_ca_topic_score_gemma":0.0001785529,"domain_scores_codex":[0.9882271,0.007134,0.002399329,0.001019014,0.0003442499,0.000876319],"domain_scores_gemma":[0.9736484,0.02207452,0.001885019,0.0016173,0.0005043149,0.0002704319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.04541806,0.009990042,0.5246443,0.00008953111,0.01160716,0.001115867,0.002223007,0.0005212009,0.1422298,0.004983825,0.0166299,0.2405474],"study_design_scores_gemma":[0.001323454,0.00899311,0.9826338,0.000005609165,0.0009039175,0.0001609486,0.002866209,0.0008370513,0.0002213148,0.0005735939,0.001212342,0.0002686459],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.881267,0.00005500153,0.1088727,0.003908412,0.0007566993,0.0006354118,0.004448876,0.00004076002,0.00001513385],"genre_scores_gemma":[0.9787188,0.0001797176,0.01962219,0.000700705,0.0001198168,0.00007883101,0.0005338471,0.00001546488,0.00003068616],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4579896,"threshold_uncertainty_score":0.9978073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6168193841057594,"score_gpt":0.5679412629416353,"score_spread":0.04887812116412416,"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."}}