{"id":"W4313270883","doi":"10.1371/journal.pone.0276726","title":"SPECHT: Self-tuning Plausibility based object detection Enables quantification of Conflict in Heterogeneous multi-scale microscopy","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"National Institute on Aging; Fondation Brain Canada; Natural Sciences and Engineering Research Council of Canada; British Columbia Knowledge Development Fund; Canadian Institutes of Health Research; Canada Foundation for Innovation","keywords":"STED microscopy; Microscopy; Computer science; Artificial intelligence; Pattern recognition (psychology); Object (grammar); Resolution (logic); Computer vision; Physics; Image (mathematics); Optics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004458513,0.0007031454,0.0008646334,0.00159244,0.0005310354,0.001998174,0.001883068,0.001438786,0.001220194],"category_scores_gemma":[0.01824035,0.000543385,0.000829153,0.0008371916,0.002044905,0.00260777,0.003493257,0.001406068,0.0002920528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001009644,"about_ca_system_score_gemma":0.0007375618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008317089,"about_ca_topic_score_gemma":0.0009859881,"domain_scores_codex":[0.9982808,0.0004631665,0.000109554,0.0003474223,0.0006785388,0.0001204894],"domain_scores_gemma":[0.9908379,0.005742333,0.001191544,0.001173996,0.0007011419,0.0003530514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009616492,0.000248276,0.01372596,0.0005627897,0.0004109386,0.0007278603,0.0008251668,0.3725145,0.1471956,0.06518795,0.002240174,0.3953991],"study_design_scores_gemma":[0.00001595425,0.00008208059,0.001935881,0.0000173637,0.0000203506,0.0001798717,0.00003926308,0.9500656,0.02028832,0.02679251,0.0005287203,0.00003401281],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03964673,0.000112954,0.958841,0.00009950134,0.00001269934,0.00003672328,0.000076178,0.0007161575,0.0004582158],"genre_scores_gemma":[0.6592594,0.0001256614,0.339111,0.0001302127,0.00004233987,0.0001187451,0.0002652186,0.0001983508,0.0007489357],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004458513,"threshold_uncertainty_score":0.02357918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02994767379000195,"score_gpt":0.2670682405668376,"score_spread":0.2371205667768357,"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."}}