{"id":"W2133884521","doi":"10.1167/9.7.6","title":"Learning illumination- and orientation-invariant representations of objects throughtemporal association","year":2009,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Eye Institute","keywords":"Spurious relationship; Association (psychology); Invariant (physics); Generalization; Object (grammar); Artificial intelligence; Orientation (vector space); Cognitive neuroscience of visual object recognition; Computer science; Computer vision; Psychology; Cognitive psychology; Communication; Mathematics; Pattern recognition (psychology); Geometry; Machine learning; Mathematical analysis","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":[0.0005323354,0.00005649202,0.0001255967,0.000138224,0.0001456166,0.0000564344,0.00006209421,0.00004984727,0.00004812389],"category_scores_gemma":[0.001271177,0.00004804491,0.00004384742,0.0002508287,0.0000195185,0.0005531277,0.000009886189,0.0001530063,0.000004038842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004642672,"about_ca_system_score_gemma":0.00004488443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002395837,"about_ca_topic_score_gemma":6.7651e-7,"domain_scores_codex":[0.9989062,0.0001305344,0.0003592218,0.0001039897,0.0004223813,0.00007769161],"domain_scores_gemma":[0.9988061,0.0001515414,0.0007272376,0.00004653257,0.0002217591,0.00004687412],"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":[0.00004622324,0.00011172,0.001271827,0.000009996073,0.000002803317,0.000005881575,0.00403737,0.0001975811,0.9817111,0.001500678,0.0002771993,0.01082757],"study_design_scores_gemma":[0.003911396,0.006354101,0.3243647,0.00050201,0.0001057559,0.0002573274,0.006729307,0.01310501,0.6142595,0.0287741,0.001219981,0.0004167483],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939468,0.00002420882,0.003379581,0.001086671,0.000232963,0.00005794392,9.957643e-7,0.00001249606,0.001258353],"genre_scores_gemma":[0.997676,0.0001049656,0.001446465,0.0002207066,0.00006834618,2.373935e-7,0.00000111428,0.000004028519,0.0004781898],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3674516,"threshold_uncertainty_score":0.1959215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03043633981707439,"score_gpt":0.3590679764569848,"score_spread":0.3286316366399104,"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."}}