{"id":"W4391682754","doi":"10.1016/j.neuron.2024.01.016","title":"Data science opportunities of large language models for neuroscience and biomedicine","year":2024,"lang":"en","type":"article","venue":"Neuron","topic":"Topic Modeling","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital","funders":"","keywords":"Biomedicine; Cognitive reframing; Cognitive science; Cognitive neuroscience; Neuroscience; Computational neuroscience; Cognition; Computer science; Psychology; Data science; Biology; Bioinformatics","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":[0.0006012723,0.00006435248,0.00008321772,0.0001731352,0.00007815068,0.0001219507,0.001244738,0.00001333161,8.599228e-7],"category_scores_gemma":[0.00008307031,0.00005374806,0.00001030543,0.0003281802,0.0001857953,0.001455302,0.0008170963,0.00005360536,3.655394e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005872665,"about_ca_system_score_gemma":0.0001370784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001079422,"about_ca_topic_score_gemma":0.000001667945,"domain_scores_codex":[0.9988812,0.00001091607,0.000132664,0.0005035404,0.0002665584,0.0002051673],"domain_scores_gemma":[0.9990727,0.000063065,0.00002570683,0.0007397874,0.00003172288,0.00006701757],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004649143,0.00004925198,0.00002502131,0.0003748071,0.000002533209,0.00008288801,0.002968371,0.0003602773,0.182388,0.621816,0.0009377094,0.1909905],"study_design_scores_gemma":[0.0000741501,0.00006024677,0.0000577998,0.00002831235,0.000003041951,0.0000156329,0.0000560755,0.9914998,0.001075129,0.001221537,0.005857877,0.00005037786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06719126,0.0009022859,0.9283286,0.001949172,0.0007622134,0.0001426791,0.00008112298,0.0001211406,0.0005215264],"genre_scores_gemma":[0.9910598,0.00008631304,0.008177307,0.0004757791,0.00004482261,0.000003344597,0.000002947266,0.000005459076,0.0001442372],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9911395,"threshold_uncertainty_score":0.2313053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1726156762272152,"score_gpt":0.3524486334844527,"score_spread":0.1798329572572375,"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."}}