{"id":"W6976951696","doi":"10.6084/m9.figshare.17073471","title":"Additional file 4 of Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: evaluation in Alzheimer’s disease","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Solar Energy Systems and Technologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Visualization; Convolutional neural network; Relevance (law); Sequence (biology); Function (biology); Interactive visualization; Data visualization","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00003000452,0.00008489038,0.0001378468,0.00004421323,0.00001831704,0.000006228493,0.00006356603,0.00006169579,0.5826573],"category_scores_gemma":[0.00207893,0.00009638427,0.00004551467,0.0002361727,0.00000999019,0.0001548451,0.00005139443,0.00008184124,0.00002223277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000625918,"about_ca_system_score_gemma":0.00007682139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006971648,"about_ca_topic_score_gemma":0.00005325839,"domain_scores_codex":[0.9992481,0.00005343125,0.000256706,0.0001470202,0.0001907807,0.0001039151],"domain_scores_gemma":[0.9987504,0.0006444533,0.0001084339,0.0001530994,0.0003216617,0.00002188234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001375551,0.00003663181,0.0001003717,0.0001866523,0.00004153662,0.000004341935,0.0000227679,0.1948678,0.0001236573,0.00002761383,0.7950051,0.009569775],"study_design_scores_gemma":[0.0001748496,0.00001350277,0.04511258,0.001744248,0.00001342759,0.000002475791,0.00003355193,0.9333611,0.000486365,0.0002591232,0.01867356,0.0001252084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0009527713,0.001086993,0.00004203587,0.000002850831,0.0000714964,0.0001520572,0.9973729,0.00008533485,0.0002336009],"genre_scores_gemma":[0.4451119,6.959472e-7,0.0003688847,0.000004242827,0.00003640787,0.0002731108,0.5541923,0.000008508964,0.00000393914],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.7763315,"threshold_uncertainty_score":0.4177243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0353559691905276,"score_gpt":0.2608961374299296,"score_spread":0.225540168239402,"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."}}