{"id":"W2905405817","doi":"10.1002/gea.21720","title":"Blind test evaluation of consistency in macroscopic lithic raw material sorting","year":2018,"lang":"en","type":"article","venue":"Geoarchaeology","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint John Regional Hospital; University of New Brunswick","funders":"Tel Aviv University; University of New Brunswick","keywords":"Consistency (knowledge bases); Sorting; Reliability (semiconductor); Computer science; Classification scheme; Process (computing); Set (abstract data type); Test (biology); Calibration; Strengths and weaknesses; Archaeology; Artificial intelligence; Statistics; Geology; Machine learning; Mathematics; Algorithm; Psychology; Geography; Paleontology; Physics","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":[0.001808644,0.00009824546,0.0001974169,0.00009805774,0.00006986089,0.00001031625,0.0005053674,0.0001286476,0.0002973799],"category_scores_gemma":[0.001297487,0.00009638956,0.00002693703,0.0002676103,0.0006996525,0.00008794419,0.0005102926,0.0001126749,0.00003148648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002291928,"about_ca_system_score_gemma":0.000182074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001405595,"about_ca_topic_score_gemma":0.0002586426,"domain_scores_codex":[0.9985229,0.0001918544,0.0003893088,0.0003365761,0.0002305541,0.0003287597],"domain_scores_gemma":[0.9988346,0.0001620067,0.0001769025,0.0004069523,0.0003832125,0.00003634443],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001795818,0.000497291,0.4328641,0.0004008577,0.00006016042,0.00008636009,0.02041751,0.0008163666,0.3694068,0.09104545,0.0002836936,0.08394189],"study_design_scores_gemma":[0.004775308,0.001025321,0.1878385,0.0001731865,0.00003868668,0.0002146329,0.0004009469,0.1509275,0.2583026,0.3941517,0.001587949,0.0005636143],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9859871,0.00005507982,0.003415991,0.002474158,0.0004983649,0.0001961014,0.000001532167,0.00003685408,0.007334774],"genre_scores_gemma":[0.9955609,0.000002376541,0.004017385,0.000115172,0.0001151028,0.00002187952,0.000004811497,0.000001666341,0.0001606395],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3031063,"threshold_uncertainty_score":0.3930652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03668008269430519,"score_gpt":0.3030766005405061,"score_spread":0.2663965178462009,"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."}}