{"id":"W2047808289","doi":"10.1167/7.8.15","title":"Inducing features from visual noise","year":2007,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Eye Institute; National Institute of Mental Health","keywords":"Artificial intelligence; Computer science; Noise (video); Unitary state; Object (grammar); Task (project management); Pattern recognition (psychology); Pixel; Cognitive neuroscience of visual object recognition; Line (geometry); Expression (computer science); Visual Objects; Computer vision; Image (mathematics); Mathematics; Perception; Psychology; Neuroscience; Engineering","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":[0.0007236967,0.00005909609,0.0001057332,0.0001440103,0.00005468159,0.0001015924,0.000393682,0.00005792001,0.00001126239],"category_scores_gemma":[0.00007875545,0.00004233936,0.00007044559,0.0002246708,0.00001492324,0.0005411481,0.00006770597,0.0002088818,0.000009576876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004110079,"about_ca_system_score_gemma":0.0000378814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008381615,"about_ca_topic_score_gemma":5.753636e-7,"domain_scores_codex":[0.999136,0.0000268179,0.0002882433,0.00009277507,0.0003511314,0.0001049969],"domain_scores_gemma":[0.9992247,0.0001003815,0.0002765897,0.0001356556,0.0001850694,0.00007764847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003496303,0.00009537887,0.000332605,0.000002428413,0.000008499167,0.00005479755,0.0003102978,7.853193e-7,0.4503978,0.001012281,0.002029541,0.5457206],"study_design_scores_gemma":[0.0003469159,0.0004740903,0.306648,0.0001353842,0.000007891662,0.00009639627,0.00006941301,0.0009703275,0.6797177,0.004433938,0.006965121,0.000134857],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1088376,0.0003503682,0.8892725,0.0007060888,0.0003161001,0.00002633604,2.389009e-7,0.00003607262,0.0004547136],"genre_scores_gemma":[0.939784,0.00004323642,0.05965649,0.0001998505,0.0002348826,7.740541e-8,2.836722e-7,0.000003563963,0.00007755052],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8309464,"threshold_uncertainty_score":0.1726549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01285819224001021,"score_gpt":0.3197720319888092,"score_spread":0.306913839748799,"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."}}