{"id":"W4408560767","doi":"10.1162/imag_a_00525","title":"Alignment of auditory artificial networks with massive individual fMRI brain data leads to generalisable improvements in brain encoding and downstream tasks","year":2025,"lang":"en","type":"article","venue":"Imaging Neuroscience","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Institut Universitaire de Gériatrie de Montréal","funders":"Fonds de Recherche du Québec - Santé; Courtois Foundation; Région Bretagne","keywords":"Computer science; Encoding (memory); Brain activity and meditation; Benchmark (surveying); Functional magnetic resonance imaging; Artificial neural network; Artificial intelligence; Convolutional neural network; Psychology; Neuroscience; Electroencephalography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007954318,0.0002496235,0.0002469166,0.0004422878,0.0002759568,0.0002881695,0.00123515,0.00003800552,0.00001008825],"category_scores_gemma":[0.001016757,0.0002292757,0.00002308867,0.001571575,0.0007798463,0.001063664,0.001033994,0.000251038,0.00000367972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006722031,"about_ca_system_score_gemma":0.0001682781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001214738,"about_ca_topic_score_gemma":0.00005271286,"domain_scores_codex":[0.996563,0.0001827633,0.0004185681,0.001496009,0.0006669639,0.0006726519],"domain_scores_gemma":[0.9985982,0.0002572183,0.0001691326,0.000793213,0.0000310061,0.0001512737],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002846393,0.0001009596,0.002911543,0.00001341217,4.237471e-7,0.00003900359,0.0002200338,0.00347578,0.9733475,0.0001995088,0.003135603,0.01652778],"study_design_scores_gemma":[0.002308044,0.0008362427,0.1264408,0.0006233337,0.00005349036,0.0000960766,0.0005720216,0.1556326,0.6955022,0.0004381252,0.01610024,0.001396804],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877224,0.000008915133,0.004109117,0.005811197,0.001151902,0.0005878896,0.00007849745,0.00005614697,0.0004739299],"genre_scores_gemma":[0.9827738,0.00001400999,0.0002393902,0.01643016,0.00008364153,0.00003205976,0.000005063701,0.00001429315,0.0004075136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2778453,"threshold_uncertainty_score":0.9349593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04539880675812569,"score_gpt":0.3123336400787242,"score_spread":0.2669348333205985,"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."}}