{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002556959,0.000519749,0.0005992433,0.0003859848,0.001202557,0.000742514,0.0007947696,0.0004748778,0.0001288884],"category_scores_gemma":[0.002149988,0.0004018782,0.0005291764,0.0004890811,0.0003943577,0.0002851259,0.00224325,0.003271278,0.00002438876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001209842,"about_ca_system_score_gemma":0.0003558075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001087528,"about_ca_topic_score_gemma":0.00009067763,"domain_scores_codex":[0.993992,0.0003886668,0.0005000855,0.002156001,0.001730855,0.001232394],"domain_scores_gemma":[0.9929886,0.004983851,0.0002494272,0.0009031048,0.0006639997,0.0002110517],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001828648,0.0005512472,0.0001692793,0.0004848648,0.0001710004,0.00002821044,0.002128656,0.0004972764,0.9743285,0.001380011,0.01500215,0.003430216],"study_design_scores_gemma":[0.001380577,0.0008540992,0.003351398,0.000429884,0.0001528067,0.000006668659,0.001058047,0.8522575,0.05099493,0.07917877,0.009583563,0.0007517586],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9390891,0.0001436897,0.03412548,0.004541914,0.008252956,0.006836995,0.006199013,0.0004558712,0.0003549475],"genre_scores_gemma":[0.9867253,0.0004121115,0.0003374871,0.0002630162,0.003585088,0.004369592,0.0005707024,0.0001812964,0.003555362],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9233335,"threshold_uncertainty_score":0.9998433,"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."}}