{"id":"W6949884699","doi":"10.5281/zenodo.15626668","title":"Experts Against Automation? Comparing Artificial Intelligence and Human Identifications of Phytoliths","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Silicon Effects in Agriculture","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Raw data; Identification (biology); Field (mathematics); Data collection","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":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002763879,0.00007884919,0.0001093384,0.00004347485,0.001308455,0.0003079914,0.0004440268,0.00004513995,0.0009423451],"category_scores_gemma":[0.0002251817,0.00004169167,0.00003044416,0.0005487633,0.0001410468,0.0001220982,0.0003894694,0.00008613857,0.0001418393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003374014,"about_ca_system_score_gemma":6.621568e-7,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001988305,"about_ca_topic_score_gemma":0.000004268,"domain_scores_codex":[0.9990882,0.0001540009,0.0002252378,0.0002413515,0.000146401,0.0001447914],"domain_scores_gemma":[0.9994694,0.00004669778,0.00008215025,0.00009711475,0.0002514502,0.00005317177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000128929,0.0001964955,0.0001708239,0.00004811324,0.00002779915,9.827602e-7,0.000594928,0.00006500928,0.621675,0.05534423,0.01730107,0.3045626],"study_design_scores_gemma":[0.0002839784,0.0004376647,0.3122928,0.0003118972,0.00005359678,0.00003441871,0.006906333,0.003627018,0.1010632,0.009135665,0.565173,0.000680533],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9729571,0.00006301606,0.00037406,0.0006199277,0.00005248102,0.0002962557,0.00003709859,0.0002876369,0.02531236],"genre_scores_gemma":[0.9991932,0.00001333647,0.00004835417,0.00004566851,0.00005074598,8.386302e-8,0.0004655105,0.00001385166,0.0001692375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5478719,"threshold_uncertainty_score":0.9999917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05216827589224225,"score_gpt":0.2747737399923815,"score_spread":0.2226054641001392,"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."}}