{"id":"W3094439952","doi":"10.1073/pnas.2007324117","title":"Improving the taxonomy of fossil pollen using convolutional neural networks and superresolution microscopy","year":2020,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Spectroscopy Techniques in Biomedical and Chemical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":93,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"National Science Foundation","keywords":"Convolutional neural network; Superresolution; Pollen; Microscopy; Taxonomy (biology); Computer science; Artificial intelligence; Biology; Botany; Optics; Physics; Image (mathematics)","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":[],"consensus_categories":[],"category_scores_codex":[0.000441048,0.00005773644,0.00008211785,0.00002157938,0.0001202224,0.000009904059,0.0004534548,0.00008464019,0.000004093954],"category_scores_gemma":[0.0004087512,0.00003390225,0.00004702684,0.0002424304,0.001677951,0.00001291641,0.0002896119,0.0001264914,2.220777e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001013439,"about_ca_system_score_gemma":0.00003519162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008303694,"about_ca_topic_score_gemma":1.901532e-8,"domain_scores_codex":[0.9990951,0.000006294292,0.0001867459,0.0001684721,0.0004227561,0.0001206518],"domain_scores_gemma":[0.9996347,0.00003109752,0.0001603114,0.000007231475,0.0001293951,0.00003723751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000307408,0.000009440187,0.002847803,0.00002526059,0.000006582274,1.072887e-9,0.00000867645,0.00002776769,0.9953288,0.001073284,0.0004755749,0.0001661064],"study_design_scores_gemma":[0.0001003197,0.00008334787,0.001970949,0.00001706731,0.000005666338,0.000003666941,0.00003704672,0.03649062,0.960156,0.0006974224,0.0003970276,0.00004091908],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956062,0.0008452373,0.0002726588,0.002746448,0.000008711643,0.0001549638,0.00001214056,0.000003048498,0.0003505935],"genre_scores_gemma":[0.9970893,0.00005154456,0.002422958,0.0002991704,0.000118547,0.000006303989,2.747587e-7,0.000002114772,0.000009770428],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03646285,"threshold_uncertainty_score":0.6182479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05313233069079971,"score_gpt":0.3325606617477412,"score_spread":0.2794283310569415,"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."}}