{"id":"W7115183986","doi":"10.48550/arxiv.2407.09100","title":"Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos","year":2024,"lang":"en","type":"preprint","venue":"Edinburgh Research Explorer","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Discovery Centre","funders":"","keywords":"Benchmark (surveying); Task (project management); Visual cortex; Benchmarking; Predictive coding; Computational model; Process (computing); Competition (biology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008978982,0.006121571,0.002224244,0.002107396,0.001598845,0.003407462,0.004918063,0.003965834,0.0221609],"category_scores_gemma":[0.01480534,0.00108693,0.003027366,0.001987497,0.001127838,0.002900132,0.004111108,0.004016851,0.02242113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002397998,"about_ca_system_score_gemma":0.002630716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02152734,"about_ca_topic_score_gemma":0.04970613,"domain_scores_codex":[0.9953995,0.001077465,0.0002136034,0.00122072,0.001540056,0.0005486002],"domain_scores_gemma":[0.9926013,0.001373112,0.000262477,0.001828874,0.002310639,0.00162357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001332688,0.0007538047,0.002881802,0.000740056,0.0003734158,0.0002450933,0.00006408708,0.01821575,0.004085801,0.001871619,0.9293119,0.04012397],"study_design_scores_gemma":[0.002944981,0.002430812,0.03318325,0.0005193133,0.0003452382,0.001165396,0.0003647242,0.3394488,0.02405523,0.01920752,0.5759516,0.0003831664],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.1482838,0.007022833,0.04882924,0.007754419,0.01053739,0.002053291,0.6678777,0.05822996,0.04941149],"genre_scores_gemma":[0.06056155,0.0004550556,0.02330979,0.000941415,0.0003717741,0.0007976883,0.8921422,0.003194865,0.01822556],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0221609,"threshold_uncertainty_score":0.07413566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07348621713261423,"score_gpt":0.3669344114848697,"score_spread":0.2934481943522555,"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."}}